Unsupervised & Semi-Supervised Learning

Blog Posts

Innovation Grants

Workshop Papers

Venue Title
NeurIPS 2024 Improving Power Plant CO2 Emission Estimation with Deep Learning and Satellite/Simulated Data (Papers Track)
Abstract and authors: (click to expand)

Abstract: CO2 emissions from power plants, as significant super emitters, contribute substantially to global warming. Accurate quantification of these emissions is crucial for effective climate mitigation strategies. While satellite-based plume inversion offers a promising approach, challenges arise from data limitations and the complexity of atmospheric conditions. This study addresses these challenges by (a) expanding the available dataset through the integration of NO2 data from Sentinel-5P, generating continuous XCO2 maps, and incorporating real satellite observations from OCO-2/3 for over 71 power plants in data-scarce regions; and (b) employing a customized U-Net model capable of handling diverse spatio-temporal resolutions for emission rate estimation. Our results demonstrate significant improvements in emission rate accuracy compared to previous methods [11]. By leveraging this enhanced approach, we can enable near real-time, precise quantification of major CO2 emission sources, supporting environmental protection initiatives and informing regulatory frameworks.

Authors: Dibyabha Deb (Manipal Institute of Technology); Kamal Das (IBM Research)
NeurIPS 2024 Learning the Indicators of Energy Burden for Knowledge Informed Policy (Papers Track)
Abstract and authors: (click to expand)

Abstract: The United States is one of the largest energy consumers per capita, which puts an expectation on households to have adequate energy expenditures to keep up with modern society. This adds additional stress on low-income households that may need to limit energy use due to financial constraints. This paper investigates energy burden, the ratio of household energy bills to household income, within the United States West. Self-Organizing Maps, an unsupervised neural network, is used to learn the indicators attributed to energy burden to inform public policy. This is one of the first studies to consider environmental justice indicators, which include outdoor air quality metrics and health disparities as energy burden indicators. The results show significant (p<0.05) differences among high energy burden areas and those with no energy burden for the environmental justice indicators. Thus, beyond the socioeconomic hardships of marginalized communities, counties with high energy burden suffer from environmental and health hazards, which will be amplified under a changing climate.

Authors: Jasmine Garland (University of Colorado Boulder); Rajagopalan Balaji (University of Colorado, Boulder); Kyri Baker (University of Colorado, Boulder); Ben Livneh (University of Colorado, Boulder)
NeurIPS 2024 Modeling Pollution Spread with Obstructions using Physics-Informed Neural Networks (Papers Track)
Abstract and authors: (click to expand)

Abstract: Pollution modeling plays a crucial role in combating climate change and protecting public health. Scientists rely on traditional numerical methods, such as finite difference and computational fluid dynamics, for accurate pollution simulations; however, they are resource-intensive and time-consuming often taking days to execute. Physics-Informed Neural Networks (PINNs) present a promising alternative, capable of significantly improving speed while maintaining high accuracy. In our research, we developed a PINN to model pollution spread under laminar flow conditions in a two-dimensional environment with obstructions and reflecting boundaries. Our model integrates the Navier-Stokes and advection-diffusion partial differential equations (PDEs) and enforces zero-flux Neumann boundaries at obstruction surfaces and simulation edges. We used a hybrid learning approach, generating a dataset of 6.1 million colocation points for supervised learning and embedding physical laws into the loss function for unsupervised learning. In our experiments, the PINN was over 2520 times faster than the traditional numerical solver, returning results in under 2190 milliseconds and achieving a mean squared error below 3E-5. Our findings demonstrate that PINNs not only offer a drastic reduction in computational time but also scale favorably with both the time domain and spatial resolution, making them a viable solution for real-time pollution monitoring and emergency response planning. Future work will focus on extending our model to dynamic obstructions and arbitrary grid geometries.

Authors: Yash Ranjith (Westmont)
NeurIPS 2024 Sliced-Wasserstein-based Anomaly Detection and Open Dataset for Localized Critical Peak Rebates (Papers Track)
Abstract and authors: (click to expand)

Abstract: In this work, we present a new unsupervised anomaly (outlier) detection (AD) method using the sliced-Wasserstein metric. This filtering technique is conceptually interesting for MLOps pipelines deploying machine learning models in critical sectors, e.g., energy, as it offers a conservative data selection. Additionally, we open the first dataset showcasing localized critical peak rebate demand response in a northern climate. We demonstrate the capabilities of our method on synthetic datasets as well as standard AD datasets and use it in the making of a first benchmark for our open-source localized critical peak rebate dataset.

Authors: Julien Pallage (Polytechnique Montréal, Mila, GERAD); Bertrand Scherrer (Hydro-Québec); Salma Naccache (Hydro-Québec); Christophe Bélanger (Hydro-Québec); Antoine Lesage-Landry (Polytechnique Montréal & GERAD)
NeurIPS 2024 Probabilistic representation learning of subseasonal to seasonal ocean dynamics (Papers Track)
Abstract and authors: (click to expand)

Abstract: Data-driven weather and climate forecasts on subseasonal-to-seasonal (S2S) scales face a two-fold challenge: the observational records are comparatively short and predictability strongly depends on the coupling of earth systems evolving on very different timescales. As a first step towards general subseasonal-to-seasonal predictions, we model the El Niño Southern Oscillation (ENSO), one of the principal sources of predictability on S2S scales. Characterised by anomalously warm sea surface temperatures in the tropical Pacific, an El Niño event arises from a combination of slow heat transfer within the Pacific and between ocean basins, as well as fast atmospheric dynamics, such as westerly wind bursts and convection. Here, we design a deep learning model that can flexibly represent information from modalities on different timescales, trained as a Masked Autoencoder and optimising the Empirical Continuous Ranked Probability Score. We find that the representation learning approach exhibits zero-shot performance that is competitive with task-specific models on S2S of ENSO in terms of correlation skill. To the best of our knowledge, we are the first to predict well-calibrated uncertainty estimates on a 24 month horizon.

Authors: Jannik Thuemmel (University of Tuebingen); Jakob Schlör (ECMWF); Florian Ebmeier (University of Tuebingen); Bedartha Goswami (University of Tübingen)
NeurIPS 2024 Composing Open-domain Vision with RAG for Ocean Monitoring and Conservation (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Climate change's destruction of marine biodiversity is threatening communities and economies around the world which rely on healthy oceans for their livelihoods. The challenge of applying computer vision to niche, real-world domains such as ocean conservation lies in the dynamic and diverse environments where traditional top-down learning struggle with long-tailed distributions, generalization, and domain transfer. Scalable species identification for ocean monitoring is particularly difficult due to the need to adapt models to new environments and identify rare or unseen species. To overcome these limitations, we propose leveraging bottom-up, open-domain learning frameworks–specifically vision-language models (VLMs) combined with retrieval-augmented generation (RAG)–as a resilient, scalable solution for image and video analysis in marine applications. We validate this approach through a preliminary application in classifying fish from video onboard fishing vessels, demonstrating impressive emergent retrieval and prediction capabilities without domain-specific training or knowledge of the task itself.

Authors: Sepand Dyanatkar (OnDeck Fisheries AI); Angran Li (OnDeck Fisheries AI); Alexander Dungate (OnDeck Fisheries AI)
NeurIPS 2024 Enhanced PINNs for high-order power grid dynamics (Proposals Track)
Abstract and authors: (click to expand)

Abstract: We develop improved physics-informed neural networks (PINNs) for high-order and high-dimensional power system models described by nonlinear ordinary differential equations. We propose some novel enhancements to improve PINN training and accuracy and also implement several other recently proposed ideas from the literature. We successfully apply these to study the transient dynamics of synchronous generators. We also make progress towards applying PINNs to advanced inverter models. Such enhanced PINNs can allow us to accelerate high-fidelity simulations needed to ensure a stable and reliable renewables-rich future grid.

Authors: Vineet Jagadeesan Nair (MIT)
NeurIPS 2024 Leveraging Artificial Intelligence for Real-Time Carbon Emission Management and Climate Change Resilience Planning in Kenya (Proposals Track)
Abstract and authors: (click to expand)

Abstract: As climate change intensifies, reducing carbon emissions has emerged as a critical global objective. Countries like Kenya, which heavily depend on agriculture and pastoral systems, are disproportionately affected by changing climatic conditions. In 2020, Kenya’s Nationally Determined Contribution (NDC) set a target to reduce carbon emissions by 32% by 2030. However, traditional methods for tracking and managing carbon emissions are derailed by inconsistencies, such as data manipulation and lack of real-time monitoring. This project leverages blockchain technology to provide a transparent and reliable platform for tracking CO2 emissions. Additionally, remote sensing and machine learning models will be used to enhance data collection, monitoring, and predicting emissions. The study will be piloted in 16 sugar companies and 16 plastic companies, as they are among the highest carbon emitters in Kenya. The findings from this study will assist the government and industries in planning climate change resilience strategies and adaptation measures.

Authors: Alukwe Jones (Kabarak University); Theophilus Owiti (Kabarak University); Mercy Gachoka (Kabarak Univeristy); Peter Rogendo (Kabarak University)
ICLR 2024 Categorization of Meteorological Data by Contrastive Clustering (Papers Track)
Abstract and authors: (click to expand)

Abstract: Visualized ceilometer backscattering data, displaying meteorological phenomena like clouds, precipitation, and aerosols, is mostly analyzed manually by meteorology experts. In this work, we present an approach for the categorization of backscattering data using a contrastive clustering approach, incorporating image and spatiotemporal information into the model. We show that our approach leads to meteorologically meaningful clusters, opening the door to the automatic categorization of ceilometer data, and how our work could potentially create insights in the field of climate science.

Authors: Michael Dammann (HAW Hamburg); Ina Mattis (DWD); Michael Neitzke (HAW Hamburg); Ralf Möller (University of Lübeck)
ICLR 2024 Semi-Supervised Domain Adaptation for Wildfire Detection (Papers Track)
Abstract and authors: (click to expand)

Abstract: Recently, both the frequency and intensity of wildfires have increased worldwide, primarily due to climate change. In this paper, we propose a novel protocol for wildfire detection, leveraging semi-supervised Domain Adaptation for object detection, accompanied by a corresponding dataset designed for use by both academics and industries. Our dataset encompasses 30 times more diverse labeled scenes than the current largest benchmark wildfire dataset, HPWREN, and introduces a new labeling policy for wildfire detection. Inspired by coordconv., we propose a robust baseline, Location-Aware Object Detection for Semi-Supervised Domain Adaptation (LADA), utilizing a teacher-student based self-supervised Domain Adaptation framework capable of extracting translational variance features characteristic of wildfires. Our framework significantly outperforms the existing baseline by a notable margin of 3.8\%p in mean Average Precision on the HPWREN wildfire dataset.

Authors: Joo Young Jang (Alchera); Youngseo Cha (Alchera); Jisu Kim (Alchera); SooHyung Lee (Alchera); Geonu Lee (Alchera); Minkook Cho (Alchera); Young Hwang (Alchera); Nojun Kwak (Seoul National University)
ICLR 2024 Near-real-time monitoring of global ocean carbon sink (Papers Track)
Abstract and authors: (click to expand)

Abstract: The ocean, absorbing about 25% of anthropogenic CO2 emissions, plays a crucial role in mitigating climate change. However, the delayed (by one year) traditional estimates of ocean-atmosphere CO2 flux hinder timely understanding and response to the global carbon cycle’s dynamics. Addressing this challenge, we introduce Carbon Monitor Ocean (CMO-NRT), a pioneering dataset providing near-real-time, monthly gridded estimates of global surface ocean fugacity of CO2 (fCO2) and ocean-atmosphere CO2 flux from January 2022 to July 2023. This dataset marks a significant advancement by updating the global carbon budget’s estimates through a fusion of data from 10 Global Ocean Biogeochemical Models (GOBMs) and 8 data products into a near-real-time analysis framework. By harnessing the power of Convolutional Neural Networks (CNNs) and semi-supervised learning techniques, we decode the complex nonlinear relationships between model or product estimates and observed environmental predictors. The predictive models, both for GOBM and data products, exhibit exceptional accuracy, with root mean square errors (RMSEs) maintaining below the 5% threshold. This advancement supports more effective climate change mitigation efforts by providing scientists and policymakers with timely and accurate data.

Authors: Xiaofan Gui (Microsoft Research); Jiang Bian (Microsoft Research)
ICLR 2024 Model Failure or Data Corruption? Exploring Inconsistencies in Building Energy Ratings with Self-Supervised Contrastive Learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: Building Energy Rating (BER) stands as a pivotal metric, enabling building owners, policymakers, and urban planners to understand the energy-saving potential through improving building energy efficiency. As such, enhancing buildings' BER levels is expected to directly contribute to the reduction of carbon emissions and promote climate improvement. Nonetheless, the BER assessment process is vulnerable to missing and inaccurate measurements. In this study, we introduce CLEAR, a data-driven approach designed to scrutinize the inconsistencies in BER assessments through self-supervised contrastive learning. We validated the effectiveness of CLEAR using a dataset representing Irish building stocks. Our experiments uncovered evidence of inconsistent BER assessments, highlighting measurement data corruption within this real-world dataset.

Authors: Qian Xiao (Trinity College Dublin); Dan Liu (Trinity College Dublin); Kevin Credit (Maynooth University)
ICLR 2024 A Deep Learning Technology Suite for Cost-Effective Sequestered CO2 Monitoring (Papers Track)
Abstract and authors: (click to expand)

Abstract: Carbon capture and storage (CCS) is a way of reducing carbon emissions to help tackle global warming. Injecting CO2 into rock formations and preventing it from escaping to the surface is a main step in a CCS project. Therefore, monitoring of geologically sequestered CO2 is important for CCS security assessment. Time-lapse seismic (4D seismic) is one of the most effective tools for CO2 monitoring. Unfortunately, the main challenge of 4D seismic is the high cost due to repeated monitoring seismic data acquisition surveys and the subsequent time-consuming data processing that involves imaging and inversion. To address this, we developed a technology suite powered by deep learning engines that significantly reduces the cost by (1) acquiring very sparse monitoring data; (2) firing multiple seismic sources simultaneously; (3) converting 2D images to 3D volume; (4) enforcing repeatability between baseline data and monitoring data; and (5) nonlinearly mapping seismic data to subsurface property model to bypass complex wave-equation-based seismic data processing procedures.

Authors: Wenyi Hu (SLB); Son Phan (SLB); Cen Li (SLB); Aria Abubakar (SLB)
NeurIPS 2023 Weakly-semi-supervised object detection in remotely sensed imagery (Papers Track)
Abstract and authors: (click to expand)

Abstract: Deep learning for detecting objects in remotely sensed imagery can enable new technologies for important applications including mitigating climate change. However, these models often require large datasets labeled with bounding box annotations which are expensive to curate, prohibiting the development of models for new tasks and geographies. To address this challenge, we develop weakly-semi-supervised object detection (WSSOD) models on remotely sensed imagery which can leverage a small amount of bounding boxes together with a large amount of point labels that are easy to acquire at scale in geospatial data. We train WSSOD models which use large amounts of point-labeled images with varying fractions of bounding box labeled images in FAIR1M and a wind turbine detection dataset, and demonstrate that they substantially outperform fully supervised models trained with the same amount of bounding box labeled images on both datasets. Furthermore, we find that the WSSOD models trained with 2-10x fewer bounding box labeled images can perform similarly to or outperform fully supervised models trained on the full set of bounding-box labeled images. We believe that the approach can be extended to other remote sensing tasks to reduce reliance on bounding box labels and increase development of models for impactful applications.

Authors: Ji Hun Wang (Stanford University); Jeremy Irvin (Stanford University); Beri Kohen Behar (Stanford University); Ha Tran (Stanford University); Raghav Samavedam (Stanford University); Quentin Hsu (Stanford University); Andrew Ng (Stanford University)
NeurIPS 2023 Explainable Offline-online Training of Neural Networks for Multi-scale Climate Modeling (Papers Track)
Abstract and authors: (click to expand)

Abstract: In global climate models, small-scale physical processes are represented using subgrid-scale (SGS) models known as parameterizations, and these parameterizations contribute substantially to uncertainties in climate projections. Recently, machine learning techniques, particularly deep neural networks (NNs), have emerged as novel tools for developing SGS parameterizations. Different strategies exist for training these NN-based SGS models. Here, we use a 1D model of the quasi-biennial oscillation (QBO) and atmospheric gravity wave (GW) parameterizations as testbeds to explore various learning strategies and challenges due to scarcity of high-fidelity training data. We show that a 12-layer convolutional NN that predicts GW forcings for given wind profiles, when trained offline in a big-data regime (100-years), produces realistic QBOs once coupled to the 1D model. In contrast, offline training of this NN in a small-data regime (18-months) yields unrealistic QBOs. However, online re-training of just two layers of this NN using ensemble Kalman inversion and only time-averaged QBO statistics leads to parameterizations that yield realistic QBOs. Fourier analysis of these three NNs’ kernels suggests how/why re-training works and reveals that these NNs primarily learn low-pass, high-pass, and a combination of band-pass Gabor filters, consistent with the importance of both local and non-local dynamics in GW propagation/dissipation. These strategies/findings apply to data-driven parameterizations of other climate processes generally.

Authors: Hamid Alizadeh Pahlavan (Rice University); Pedram Hassanzadeh (Rice University); M. Joan Alexander (NorthWest Research Associates)
NeurIPS 2023 Lightweight, Pre-trained Transformers for Remote Sensing Timeseries (Papers Track)
Abstract and authors: (click to expand)

Abstract: Machine learning models for parsing remote sensing data have a wide range of societally relevant applications, but labels used to train these models can be difficult or impossible to acquire. This challenge has spurred research into self-supervised learning for remote sensing data. Current self-supervised learning approaches for remote sensing data draw significant inspiration from techniques applied to natural images. However, remote sensing data has important differences from natural images -- for example, the temporal dimension is critical for many tasks and data is collected from many complementary sensors. We show we can create significantly smaller performant models by designing architectures and self-supervised training techniques specifically for remote sensing data. We introduce the Pretrained Remote Sensing Transformer (Presto), a transformer-based model pre-trained on remote sensing pixel-timeseries data. Presto excels at a wide variety of globally distributed remote sensing tasks and performs competitively with much larger models while requiring far less compute. Presto can be used for transfer learning or as a feature extractor for simple models, enabling efficient deployment at scale.

Authors: Gabriel Tseng (NASA Harvest); Ruben Cartuyvels (KULeuven); Ivan Zvonkov (University of Maryland); Mirali Purohit (Arizona State University (ASU)); David Rolnick (McGill University, Mila); Hannah R Kerner (Arizona State University)
NeurIPS 2023 Resource Efficient and Generalizable Representation Learning of High-Dimensional Weather and Climate Data (Papers Track)
Abstract and authors: (click to expand)

Abstract: We study self-supervised representation learning on high-dimensional data under resource constraints. Our work is motivated by applications of vision transformers to weather and climate data. Such data frequently comes in the form of tensors that are both higher dimensional and of larger size than the RGB imagery one encounters in many computer vision experiments. This raises scaling issues and brings up the need to leverage available compute resources efficiently. Motivated by results on masked autoencoders, we show that it is possible to use sampling of subtensors as the sole augmentation strategy for contrastive learning with a sampling ratio of $\sim$1\%. This is to be compared to typical masking ratios of $75\%$ or $90\%$ for image and video data respectively. In an ablation study, we explore extreme sampling ratios and find comparable skill for ratios as low as $\sim$0.0625\%. Pursuing efficiencies, we are finally investigating whether it is possible to generate robust embeddings on dimension values which were not present at training time. We answer this question to the positive by using learnable position encoders which have continuous dependence on dimension values.

Authors: Juan Nathaniel (Columbia University); Marcus Freitag (IBM); Patrick Curran (Environment and Climate Change Canada); Isabel Ruddick (Environment and Climate Change Canada); Johannes Schmude (IBM)
NeurIPS 2023 Towards Global, General-Purpose Pretrained Geographic Location Encoders (Papers Track)
Abstract and authors: (click to expand)

Abstract: Location information is essential for modeling tasks in climate-related fields ranging from ecology to the Earth system sciences. However, obtaining meaningful location representation is challenging and requires a model to distill semantic location information from available data, such as remote sensing imagery. To address this challenge, we introduce SatCLIP, a global, general-purpose geographic location encoder that provides vector embeddings summarizing the characteristics of a given location for convenient usage in diverse downstream tasks. We show that SatCLIP embeddings, pretrained on multi-spectral Sentinel-2 satellite data, can be used for various predictive out-of-domain tasks, including temperature prediction and animal recognition in imagery, and outperform existing competing approaches. SatCLIP embeddings also prove helpful in overcoming geographic domain shift. This demonstrates the potential of general-purpose location encoders and opens the door to learning meaningful representations of our planet from the vast, varied, and largely untapped modalities of geospatial data.

Authors: Konstantin Klemmer (Microsoft Research); ESTHER ROLF (Google Research); Caleb Robinson (Microsoft AI for Good Research Lab); Lester Mackey (Microsoft Research); Marc Rußwurm (École Polytechnique Fédérale de Lausanne)
NeurIPS 2023 Sand Mining Watch: Leveraging Earth Observation Foundation Models to Inform Sustainable Development (Proposals Track)
Abstract and authors: (click to expand)

Abstract: As the major ingredient of concrete and asphalt, sand is vital to economic growth, and will play a key role in aiding the transition to a low carbon society. However, excessive and unregulated sand mining in the Global South has high socio-economic and environmental costs, and amplifies the effects of climate change. Sand mines are characterized by informality and high temporal variability, and data on the location and extent of these mines tends to be sparse. We propose to build custom sand-mine detection tools by fine-tuning foundation models for earth observation, which leverage self supervised learning - a cost-effective and powerful approach in sparse data regimes. Our preliminary results show that these methods outperform fully supervised approaches, with the best performing model achieving an average precision score of 0.57 for this challenging task. These tools allow for real-time monitoring of sand mining activity and can enable more effective policy and regulation, to inform sustainable development.

Authors: Ando Shah (UC Berkeley); Suraj R Nair (UC Berkeley); Tom Boehnel (TU Munich); Joshua Blumenstock (University of California, Berkeley)
ICLR 2023 Unsupervised machine learning techniques for multi-model comparison: A case study on Antarctic Intermediate Water in CMIP6 models (Papers Track)
Abstract and authors: (click to expand)

Abstract: The Climate Model Intercomparison Project provides access to ensembles of model experiments that are widely used to better understand past, present, and future climate changes. In this study, we use Principal Component Analysis and K-means and hierarchical clustering techniques to guide identification of models in the CMIP6 dataset that are best suited for specific modelling objectives. An example is discussed here that focuses on how CMIP6 models reproduce the physical properties of Antarctic Intermediate Water, a key feature of the global oceanic circulation and of the ocean-climate system, noting that the tools and methods introduced here can readily be extended to the analysis of other features and regions.

Authors: Ophelie Meuriot (Imperial College London); Yves Plancherel (Imperial College London); Veronica Nieves (University of Valencia)
ICLR 2023 Topology Estimation from Voltage Edge Sensing for Resource-Constrained Grids (Papers Track)
Abstract and authors: (click to expand)

Abstract: Electric grids are the conduit for renewable energy delivery and will play a crucial role in mitigating climate change. To do so successfully in resource-constrained low- and middle-income countries (LMICs), increasing operational efficiency is key. Such efficiency demands evolving knowledge of the grid’s state, of which topology---how points on the network are physically connected---is fundamental. In LMICs, knowledge of distribution topology is limited and established methods for topology estimation rely on expensive sensing infrastructure, such as smart meters or PMUs, that are inaccessible at scale. This paper lays the foundation for topology estimation from more accessible data: outlet-level voltage magnitude measurements. It presents a graph-based algorithm and explanatory visualization using the Fielder vector for estimating and communicating topological proximity from this data. We demonstrate the method on a real dataset collected in Accra, Ghana, thus opening the possibility of globally accessible, cutting-edge grid monitoring through non-traditional sensing strategies coupled with ML.

Authors: Mohini S Bariya (nLine); Genevieve Flaspohler (nLine)
ICLR 2023 Sub-seasonal to seasonal forecasts through self-supervised learning (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Sub-seasonal to seasonal (S2S) weather forecasts are an important decision- making tool that informs economical and logistical planning in agriculture, energy management, and disaster mitigation. They are issued on time scales of weeks to months and differ from short-term weather forecasts in two important ways: (i) the dynamics of the atmosphere on these timescales can be described only statistically and (ii) these dynamics are characterized by large-scale phenomena in both space and time. While deep learning (DL) has shown promising results in short-term weather forecasting, DL-based S2S forecasts are challenged by comparatively small volumes of available training data and large fluctuations in predictability due to atmospheric conditions. In order to develop more reliable S2S predictions that leverage current advances in DL, we propose to utilize the masked auto-encoder (MAE) framework to learn generic representations of large-scale atmospheric phenomena from high resolution global data. Besides exploring the suitability of the learned representations for S2S forecasting, we will also examine whether they account for climatic phenomena (e.g., the Madden-Julian Oscillation) that are known to increase predictability on S2S timescales.

Authors: Jannik Thuemmel (University of Tuebingen); Felix Strnad (Potsdam Institute for Climate Impact Research); Jakob Schlör (Eberhard Karls Universität Tübingen); Martin V. Butz (University of Tübingen); Bedartha Goswami (University of Tübingen)
ICLR 2023 Mining Effective Strategies for Climate Change Communication (Papers Track)
Abstract and authors: (click to expand)

Abstract: With the goal of understanding effective strategies to communicate about climate change, we build interpretable models to rank tweets related to climate change with respect to the engagement they generate. Our models are based on the Bradley-Terry model of pairwise comparison outcomes and use a combination of the tweets’ topic and metadata features to do the ranking. To remove confounding factors related to author popularity and minimise noise, they are trained on pairs of tweets that are from the same author and around the same time period and have a sufficiently large difference in engagement. The models achieve good accuracy on a held-out set of pairs. We show that we can interpret the parameters of the trained model to identify the topic and metadata features that contribute to high engagement. Among other observations, we see that topics related to climate projections, human cost and deaths tend to have low engagement while those related to mitigation and adaptation strategies have high engagement. We hope the insights gained from this study will help craft effective climate communication to promote engagement, thereby lending strength to efforts to tackle climate change.

Authors: Aswin Suresh (EPFL); Lazar Milikic (EPFL); Francis Murray (EPFL); Yurui Zhu (EPFL); Matthias Grossglauser (École Polytechnique Fédérale de Lausanne (EPFL))
NeurIPS 2022 Improving the predictions of ML-corrected climate models with novelty detection (Papers Track)
Abstract and authors: (click to expand)

Abstract: While previous works have shown that machine learning (ML) can improve the prediction accuracy of coarse-grid climate models, these ML-augmented methods are more vulnerable to irregular inputs than the traditional physics-based models they rely on. Because ML-predicted corrections feed back into the climate model’s base physics, the ML-corrected model regularly produces out of sample data, which can cause model instability and frequent crashes. This work shows that adding semi-supervised novelty detection to identify out-of-sample data and disable the ML-correction accordingly stabilizes simulations and sharply improves the quality of predictions. We design an augmented climate model with a one-class support vector machine (OCSVM) novelty detector that provides better temperature and precipitation forecasts in a year-long simulation than either a baseline (no-ML) or a standard ML-corrected run. By improving the accuracy of coarse-grid climate models, this work helps make accurate climate models accessible to researchers without massive computational resources.

Authors: Clayton H Sanford (Columbia); Anna Kwa (Allen Institute for Artificial Intelligence); Oliver Watt-Meyer (Allen Institute for AI); Spencer Clark (Allen Institute for AI); Noah Brenowitz (Allen Institute for AI); Jeremy McGibbon (Allen Institute for AI); Christopher Bretherton (Allen Institute for AI)
NeurIPS 2022 Scene-to-Patch Earth Observation: Multiple Instance Learning for Land Cover Classification (Papers Track)
Abstract and authors: (click to expand)

Abstract: Land cover classification (LCC), and monitoring how land use changes over time, is an important process in climate change mitigation and adaptation. Existing approaches that use machine learning with Earth observation data for LCC rely on fully-annotated and segmented datasets. Creating these datasets requires a large amount of effort, and a lack of suitable datasets has become an obstacle in scaling the use of LCC. In this study, we propose Scene-to-Patch models: an alternative LCC approach utilising Multiple Instance Learning (MIL) that requires only high-level scene labels. This enables much faster development of new datasets whilst still providing segmentation through patch-level predictions, ultimately increasing the accessibility of using LCC for different scenarios. On the DeepGlobe-LCC dataset, our approach outperforms non-MIL baselines on both scene- and patch-level prediction. This work provides the foundation for expanding the use of LCC in climate change mitigation methods for technology, government, and academia.

Authors: Joseph Early (University of Southampton); Ying-Jung C Deweese (Georgia Insititute of Technology); Christine Evers (University of Southampton); Sarvapali Ramchurn (University of Southampton)
NeurIPS 2022 Data-Driven Optimal Solver for Coordinating a Sustainable and Stable Power Grid (Papers Track)
Abstract and authors: (click to expand)

Abstract: With today's pressing climate change concerns, the widespread integration of low-carbon technologies such as sustainable generation systems (e.g. photovoltaics, wind turbines, etc.) and flexible consumer devices (e.g. storage, electric vehicles, smart appliances, etc.) into the electric grid is vital. Although these power entities can be deployed at large, these are highly variable in nature and must interact with the existing grid infrastructure without violating electrical limits so that the system continues to operate in a stable manner at all times. In order to ensure the integrity of grid operations while also being economical, system operators will need to rapidly solve the optimal power flow (OPF) problem in order to adapt to these fluctuations. Inherent non-convexities in the OPF problem do not allow traditional model-based optimization techniques to offer guarantees on optimality, feasibility and convergence. In this paper, we propose a data-driven OPF solver built on information-theoretic and semi-supervised machine learning constructs. We show that this solver is able to rapidly compute solutions (i.e. in sub-second range) that are within 3\% of optimality with guarantees on feasibility on a benchmark IEEE 118-bus system.

Authors: Junfei Wang (York University); Pirathayini Srikantha (York University)
NeurIPS 2022 Cross Modal Distillation for Flood Extent Mapping (Papers Track)
Abstract and authors: (click to expand)

Abstract: The increasing intensity and frequency of floods is one of the many consequences of our changing climate. In this work, we explore ML techniques that improve the flood detection module of an operational early flood warning system. Our method exploits an unlabelled dataset of paired multi-spectral and Synthetic Aperture Radar (SAR) imagery to reduce the labeling requirements of a purely supervised learning method. Past attempts have used such unlabelled data by creating weak labels out of them, but end up learning the label mistakes in those weak labels. Motivated by knowledge distillation and semi supervised learning, we explore the use of a teacher to train a student with the help of a small hand labeled dataset and a large unlabelled dataset. Unlike the conventional self distillation setup, we propose a cross modal distillation framework that transfers supervision from a teacher trained on richer modality (multi-spectral images) to a student model trained on SAR imagery. The trained models are then tested on the Sen1Floods11 dataset. Our model outperforms the Sen1Floods11 SAR baselines by an absolute margin of 4.15% pixel wise Intersection-over-Union (IoU) on the test split.

Authors: Shubhika Garg (Google); Ben Feinstein (Google); Shahar Timnat (Google); Vishal V Batchu (Google); gideon dror (The Academic College of Tel-Aviv-Yaffo); Adi Gerzi Rosenthal (Google); Varun Gulshan (Google Research)
NeurIPS 2022 Reconstruction of Grid Measurements in the Presence of Adversarial Attacks (Papers Track)
Abstract and authors: (click to expand)

Abstract: In efforts to mitigate the adverse effects of climate change, policymakers have set ambitious goals to reduce the carbon footprint of all sectors - including the electric grid. To facilitate this, sustainable energy systems like renewable generation must { be} deployed at high numbers throughout the grid. As these are highly variable in nature, the grid must be closely monitored so that system operators will have elevated situational awareness and can execute timely actions to maintain stable grid operations. With the widespread deployment of sensors like phasor measurement units (PMUs), an abundance of data is available for conducting accurate state estimation. However, due to the cyber-physical nature of the power grid, measurement data can be perturbed in an adversarial manner to enforce incorrect decision-making. In this paper, we propose a novel reconstruction method that leverages on machine learning constructs like CGAN and gradient search to recover the original states when subjected to adversarial perturbations. Experimental studies conducted on the practical IEEE 118-bus benchmark power system show that the proposed method can reduce errors due to perturbation by large margins (i.e. up to 100%).

Authors: Amirmohammad Naeini (York University); Samer El Kababji (Western University); Pirathayini Srikantha (York University)
NeurIPS 2022 An Unsupervised Learning Perspective on the Dynamic Contribution to Extreme Precipitation Changes (Papers Track)
Abstract and authors: (click to expand)

Abstract: Despite the importance of quantifying how the spatial patterns of extreme precipitation will change with warming, we lack tools to objectively analyze the storm-scale outputs of modern climate models. To address this gap, we develop an unsupervised machine learning framework to quantify how storm dynamics affect precipitation extremes and their changes without sacrificing spatial information. Over a wide range of precipitation quantiles, we find that the spatial patterns of extreme precipitation changes are dominated by spatial shifts in storm regimes rather than intrinsic changes in how these storm regimes produce precipitation.

Authors: Griffin S Mooers (UC Irvine); Tom Beucler (University of Lausanne); Michael Pritchard (UCI); Stephan Mandt (University of California, Irivine)
NeurIPS 2022 Towards the Automatic Analysis of Ceilometer Backscattering Profiles using Unsupervised Learning (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Ceilometers use a laser beam to capture certain phenomena in the atmosphere like clouds, precipitation, or aerosol layers. These measurements can be visualized in so-called quick looks that at the moment are mostly analyzed manually by meteorology experts. In this work, we illustrate the path towards the automatic analysis of quick looks by using a hybrid approach combining an image segmentation algorithm with unsupervised representation learning and clustering. We present a first proof of concept and give an outlook on possible future work.

Authors: Michael Dammann (HAW Hamburg); Ina Mattis (Deutscher Wetterdienst); Michael Neitzke (HAW Hamburg); Ralf Möller (University of Lübeck)
NeurIPS 2022 Modelling the performance of delivery vehicles across urban micro-regions to accelerate the transition to cargo-bike logistics (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Light goods vehicles (LGV) used extensively in the last mile of delivery are one of the leading polluters in cities. Cargo-bike logistics has been put forward as a high impact candidate for replacing LGVs, with experts estimating over half of urban van deliveries being replaceable by cargo bikes, due to their faster speeds, shorter parking times and more efficient routes across cities. By modelling the relative delivery performance of different vehicle types across urban micro-regions, machine learning can help operators evaluate the business and environmental impact of adding cargo-bikes to their fleets. In this paper, we introduce two datasets, and present initial progress in modelling urban delivery service time (e.g. cruising for parking, unloading, walking). Using Uber’s H3 index to divide the cities into hexagonal cells, and aggregating OpenStreetMap tags for each cell, we show that urban context is a critical predictor of delivery performance.

Authors: Max C Schrader (University of Alabama); Navish Kumar (IIT Kharagpur); Nicolas Collignon (University of Edinburgh); Maria S Astefanoaei (IT University of Copenhagen); Esben Sørig (Kale Collective); Soonmyeong Yoon (Kale Collective); Kai Xu (University of Edinburgh); Akash Srivastava (MIT-IBM)
NeurIPS 2021 Flood Segmentation on Sentinel-1 SAR Imagery with Semi-Supervised Learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: Floods wreak havoc throughout the world, causing billions of dollars in damages, and uprooting communities, ecosystems and economies. The NASA Impact Emerging Techniques in Computational Intelligence (ETCI) competition on Flood Detection tasked participants with predicting flooded pixels after training with synthetic aperture radar (SAR) images in a supervised setting. We propose a semi-supervised learning pseudo-labeling scheme that derives confidence estimates from U-Net ensembles, thereby progressively improving accuracy. Concretely, we use a cyclical approach involving multiple stages (1) training an ensemble model of multiple U-Net architectures with the provided high confidence hand-labeled data and, generated pseudo labels or low confidence labels on the entire unlabeled test dataset, and then, (2) filter out quality generated labels and, (3) combine the generated labels with the previously available high confidence hand-labeled dataset. This assimilated dataset is used for the next round of training ensemble models. This cyclical process is repeated until the performance improvement plateaus. Additionally, we post process our results with Conditional Random Fields. Our approach sets a high score, and a new state-of-the-art on the Sentinel-1 dataset for the ETCI competition with 0.7654 IoU, an impressive improvement over the 0.60 IOU baseline. Our method, which we release with all the code including trained models, can also be used as an open science benchmark for the Sentinel-1 released dataset.

Authors: Siddha Ganju (Nvidia Corporation); Sayak Paul (Carted)
NeurIPS 2021 Hurricane Forecasting: A Novel Multimodal Machine Learning Framework (Papers Track)
Abstract and authors: (click to expand)

Abstract: This paper describes a machine learning (ML) framework for tropical cyclone intensity and track forecasting, combining multiple distinct ML techniques and utilizing diverse data sources. Our framework, which we refer to as Hurricast (HURR), is built upon the combination of distinct data processing techniques using gradient-boosted trees and novel encoder-decoder architectures, including CNN, GRU and Transformers components. We propose a deep-learning feature extractor methodology to mix spatial-temporal data with statistical data efficiently. Our multimodal framework unleashes the potential of making forecasts based on a wide range of data sources, including historical storm data, and visual data such as reanalysis atmospheric images. We evaluate our models with current operational forecasts in North Atlantic (NA) and Eastern Pacific (EP) basins on 2016-2019 for 24-hour lead time, and show our models consistently outperform statistical-dynamical models and compete with the best dynamical models. Furthermore, the inclusion of Hurricast into an operational forecast consensus model leads to a significant improvement of 5% - 15% over NHC's official forecast, thus highlighting the complementary properties with existing approaches.

Authors: Léonard Boussioux (MIT, CentraleSupélec); Cynthia Zeng (MIT); Dimitris Bertsimas (MIT); Théo J Guenais (Harvard University)
NeurIPS 2021 Resolving Super Fine-Resolution SIF via Coarsely-Supervised U-Net Regression (Papers Track)
Abstract and authors: (click to expand)

Abstract: Climate change presents challenges to crop productivity, such as increasing the likelihood of heat stress and drought. Solar-Induced Chlorophyll Fluorescence (SIF) is a powerful way to monitor how crop productivity and photosynthesis are affected by changing climatic conditions. However, satellite SIF observations are only available at a coarse spatial resolution (e.g. 3-5km) in most places, making it difficult to determine how individual crop types or farms are doing. This poses a challenging coarsely-supervised regression task; at training time, we only have access to SIF labels at a coarse resolution (3 km), yet we want to predict SIF at a very fine spatial resolution (30 meters), a 100x increase. We do have some fine-resolution input features (such as Landsat reflectance) that are correlated with SIF, but the nature of the correlation is unknown. To address this, we propose Coarsely-Supervised Regression U-Net (CSR-U-Net), a novel approach to train a U-Net for this coarse supervision setting. CSR-U-Net takes in a fine-resolution input image, and outputs a SIF prediction for each pixel; the average of the pixel predictions is trained to equal the true coarse-resolution SIF for the entire image. Even though this is a very weak form of supervision, CSR-U-Net can still learn to predict accurately, due to its inherent localization abilities, plus additional enhancements that facilitate the incorporation of scientific prior knowledge. CSR-U-Net can resolve fine-grained variations in SIF more accurately than existing averaging-based approaches, which ignore fine-resolution spatial variation during training. CSR-U-Net could also be useful for a wide range of "downscaling'" problems in climate science, such as increasing the resolution of global climate models.

Authors: Joshua Fan (Cornell University); Di Chen (Cornell University); Jiaming Wen (Cornell University); Ying Sun (Cornell University); Carla P Gomes (Cornell University)
NeurIPS 2021 Semi-Supervised Classification and Segmentation on High Resolution Aerial Images (Papers Track)
Abstract and authors: (click to expand)

Abstract: FloodNet is a high-resolution image dataset acquired by a small UAV platform, DJI Mavic Pro quadcopters, after Hurricane Harvey. The dataset presents a unique challenge of advancing the damage assessment process for post-disaster scenarios using unlabeled and limited labeled dataset. We propose a solution to address their classification and semantic segmentation challenge. We approach this problem by generating pseudo labels for both classification and segmentation during training and slowly incrementing the amount by which the pseudo label loss affects the final loss. Using this semi-supervised method of training helped us improve our baseline supervised loss by a huge margin for classification, allowing the model to generalize and perform better on the validation and test splits of the dataset. In this paper, we compare and contrast the various methods and models for image classification and semantic segmentation on the FloodNet dataset.

Authors: Sahil S Khose (Manipal Institute of Technology); Abhiraj Tiwari (Manipal Institute of Technology); Ankita Ghosh (Manipal Institute of Technology)
NeurIPS 2021 Unsupervised Machine Learning framework for sensor placement optimization: analyzing methane leaks (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Methane is one of the most potent greenhouse gases, with the global oil and gas industry being the second largest source of anthropogenic methane emissions, accounting for about 63% of the whole energy sector. This underscores the importance of detecting and remediating methane leaks for the entire oil and gas value chain. Methane sensor networks are a promising technology to detect methane leaks in a timely manner. While they provide near-real-time monitoring of an area of interest, the density of the network can be cost prohibitive, and the identification of the source of the leak is not apparent, especially where there could be more than one source. To address these issues, we developed a machine learning framework that leverages various data sources including oil and gas facilities data, historical methane leak rate distribution and meteorological data, to optimize sensor placement. The determination of sensor locations follows the objective to maximize the detection of possible methane leaks with a limited sensor budget.

Authors: Shirui Wang (University of Houston); Sara Malvar (Microsoft); Leonardo Nunes (Microsoft); Kim Whitehall (Microsoft); YAGNA DEEPIKA ORUGANTI (MICROSOFT); Yazeed Alaudah (Microsoft); Anirudh Badam (Microsoft)
NeurIPS 2021 Machine Learning Speeding Up the Development of Portfolio of New Crop Varieties to Adapt to and Mitigate Climate Change (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Climate change poses serious challenges to achieving food security in a time of a need to produce more food to keep up with the world’s increasing demand for food. There is an urgent need to speed up the development of new high yielding varieties with traits of adaptation and mitigation to climate change. Mathematical approaches, including ML approaches, have been used to search for such traits, leading to unprecedented results as some of the traits, including heat traits that have been long sought-for, have been found within a short period of time.

Authors: Abdallah Bari (OperAI Canada - Operational AI); Hassan Ouabbou (INRA); Abderrazek Jilal (INRA); Frederick Stoddard (University of Helsinki); Mikko Sillanpää (University of Oulu); Hamid Khazaei (World Vegetable Center)
NeurIPS 2021 Predicting Cascading Failures in Power Systems using Graph Convolutional Networks (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Worldwide targets are set for the increase of renewable power generation in electricity networks on the way to combat climate change. Consequently, a secure power system that can handle the complexities resulted from the increased renewable power integration is crucial. One particular complexity is the possibility of cascading failures — a quick succession of multiple component failures that takes down the system and might also lead to a blackout. Viewing the prediction of cascading failures as a binary classification task, we explore the efficacy of Graph Convolution Networks (GCNs), to detect the early onset of a cascading failure. We perform experiments based on simulated data from a benchmark IEEE test system. Our preliminary findings show that GCNs achieve higher accuracy scores than other baselines which bodes well for detecting cascading failures. It also motivates a more comprehensive study of graph-based deep learning techniques for the current problem.

Authors: Tabia Ahmad (University of Strathclyde); Yongli Zhu (Texas A&M Universersity); Panagiotis Papadopoulos (University of Strathclyde)
ICML 2021 Estimation of Corporate Greenhouse Gas Emissions via Machine Learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: As an important step to fulfill the Paris Agreement and achieve net-zero emissions by 2050, the European Commission adopted the most ambitious package of climate impact measures in April 2021 to improve the flow of capital towards sustainable activities. For these and other international measures to be successful, reliable data is key. The ability to see the carbon footprint of companies around the world will be critical for investors to comply with the measures and hit climate neutrality. However, with only a small portion of companies volunteering to disclose their greenhouse gas (GHG) emissions, it is nearly impossible for investors to align their investment strategies with the measures. By training a machine learning model on disclosed GHG emissions, we are able to estimate the emissions of other companies globally who do not disclose their emissions. In this paper, we show that our model provides accurate estimates of corporate GHG emissions to investors such that they are able to align their investments with the regulatory measures and achieve net-zero goals.

Authors: You Han (Bloomberg L.P.); Achintya Gopal (Bloomberg LP); Liwen Ouyang (Bloomberg L.P.); Aaron Key (Bloomberg LP)
ICML 2021 Physics-Informed Graph Neural Networks for Robust Fault Location in Power Grids (Papers Track) Best Paper: ML Innovation
Abstract and authors: (click to expand)

Abstract: The reducing cost of renewable energy resources, such as solar photovoltaics (PV) and wind farms, is accelerating global energy transformation to mitigate climate change. However, a high level of intermittent renewable energy causes power grids to have more stability issues. This accentuates the need for quick location of system failures and follow-up control actions. In recent events such as in California, line failures have resulted in large-scale wildfires leading to loss of life and property. In this article, we propose a two-stage graph learning framework to locate power grid faults in the challenging but practical regime characterized by (a) sparse observations, (b) low label rates, and (c) system variability. Our approach embeds the geometrical structure of power grids into the graph neural networks (GNN) in stage I for fast fault location, and then stage II further enhances the location accuracy by employing the physical similarity of the labeled and unlabeled data samples. We compare our approach with three baselines in the IEEE 123-node benchmark system and show that it outperforms the others by significant margins in various scenarios.

Authors: Wenting Li (Los Alamos National Laboratory); Deepjyoti Deka (Los Alamos National Laboratory)
ICML 2021 Reconstructing Aerosol Vertical Profiles with Aggregate Output Learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: Aerosol-cloud interactions constitute the largest source of uncertainty in assessments of the anthropogenic climate change. This uncertainty arises in part from the inability to observe aerosol amounts at the cloud formation levels, and, more broadly, the vertical distribution of aerosols. Hence, we often have to settle for less informative two-dimensional proxies, i.e. vertically aggregated data. In this work, we formulate the problem of disaggregation of vertical profiles of aerosols. We propose some initial solutions for such aggregate output regression problem and demonstrate their potential on climate model data.

Authors: Sofija Stefanovic (University of Oxford); Shahine Bouabid (University of Oxford); Philip Stier (University of Oxford); Athanasios Nenes (EPFL); Dino Sejdinovic (University of Oxford)
ICML 2021 DeepOPF-NGT: A Fast Unsupervised Learning Approach for Solving AC-OPF Problems without Ground Truth (Papers Track)
Abstract and authors: (click to expand)

Abstract: AC optimal power flow (AC-OPF) problems need to be solved more frequently in the future to maintain the reliable and cost-effective operation of power systems. Recently, supervised-learning approaches have been developed to speed up the solving time of AC-OPF problems without incurring infeasibility or much optimality loss by learning the load-solution mapping embedded in the training dataset. However, it is non-trivial and computationally expensive to prepare the training dataset with single embedded mapping, due to that AC-OPF problems are non-convex and may admit multiple optimal solutions. In this paper, we develop an unsupervised learning approach (DeepOPF-NGT) for solving AC-OPF problems, which does not require training datasets with ground truth to operate. Instead, it uses a properly designed loss function to guide the tuning of the neural network parameters to directly learn one load-solution mapping. Preliminary results on the IEEE 30-bus test system show that the unsupervised DeepOPF-NGT approach can achieve comparable optimality, feasibility, and speedup performance against an existing supervised learning approach.

Authors: Wanjun Huang (City University of Hong Kong); Minghua Chen (City University of Hong Kong)
ICML 2021 Learning Granger Causal Feature Representations (Papers Track)
Abstract and authors: (click to expand)

Abstract: Tackling climate change needs to understand the complex phenomena occurring on the Planet. Discovering teleconnection patterns is an essential part of the endeavor. Events like El Niño Southern Oscillation (ENSO) impact essential climate variables at large distances, and influence the underlying Earth system dynamics. However, their automatic identification from the wealth of observational data is still unresolved. Nonlinearities, nonstationarities and the (ab)use of correlation analyses hamper the discovery of true causal patterns. We here introduce a deep learning methodology that extracts nonlinear latent functions from spatio-temporal Earth data and that are Granger causal with the index altogether. We illustrate its use to study the impact of ENSO on vegetation, which allows for a more rigorous study of impacts on ecosystems globally.

Authors: Gherardo Varando (Universitat de València); Miguel-Ángel Fernández-Torres (Universitat de València); Gustau Camps-Valls (Universitat de València)
ICML 2021 Self-supervised Contrastive Learning for Irrigation Detection in Satellite Imagery (Papers Track)
Abstract and authors: (click to expand)

Abstract: Climate change has caused reductions in river runoffs and aquifer recharge resulting in an increasingly unsustainable crop water demand from reduced freshwater availability. Achieving food security while deploying water in a sustainable manner will continue to be a major challenge necessitating careful monitoring and tracking of agricultural water usage. Historically, monitoring water usage has been a slow and expensive manual process with many imperfections and abuses. Ma-chine learning and remote sensing developments have increased the ability to automatically monitor irrigation patterns, but existing techniques often require curated and labelled irrigation data, which are expensive and time consuming to obtain and may not exist for impactful areas such as developing countries. In this paper, we explore an end-to-end real world application of irrigation detection with uncurated and unlabeled satellite imagery. We apply state-of-the-art self-supervised deep learning techniques to optical remote sensing data, and find that we are able to detect irrigation with up to nine times better precision, 90% better recall and 40% more generalization ability than the traditional supervised learning methods.

Authors: Chitra Agastya (UC Berkeley, IBM); Sirak Ghebremusse (UC Berkeley); Ian Anderson (UC Berkeley); Colorado Reed (UC Berkeley); Hossein Vahabi (University California Berkeley); Alberto Todeschini (UC Berkeley)
ICML 2021 Self-Supervised Learning on Multispectral Satellite Data for Near-Term Solar Forecasting (Papers Track)
Abstract and authors: (click to expand)

Abstract: With the unprecedented increase in distributed photovoltaic (PV) capacity across the globe, there is an increasing need for reliable and accurate forecasting of solar power generation. While PV output is affected by many factors, the atmosphere, i.e., cloud cover, plays a dominant role in determining the amount of downwelling solar irradiance that reaches PV modules. This paper demonstrates that self-supervised learning of multispectral satellite data from the recently launched GOES-R series of satellites can improve near-term (15 minutes) solar forecasting. We develop deep auto-regressive models using convolutional neural networks (CNN) and long short-term memory networks (LSTM) that are globally trained across many solar sites on the raw spatio-temporal data from GOES-R satellites. This self-supervised model provides estimates of future solar irradiance that can be fed directly to a regression model trained on smaller site-specific solar data to provide near-term solar PV forecasts at the site. The regression implicitly models site-specific characteristics, such as capacity, panel tilt, orientation, etc, while the self-supervised CNN-LSTM implicitly captures global atmospheric patterns affecting a site's solar irradiation. Results across 25 solar sites show the utility of such self-supervised modeling by providing accurate near-term forecast with errors close to that of a model using current ground-truth observations.

Authors: Akansha Singh Bansal (University of Massachusetts Amherst); Trapit Bansal (University of Massachusetts Amherst); David Irwin (University of Massachusetts Amherst)
ICML 2021 EVGen: Adversarial Networks for Learning Electric Vehicle Charging Loads and Hidden Representations (Papers Track)
Abstract and authors: (click to expand)

Abstract: The nexus between transportation, the power grid, and consumer behavior is much more pronounced than ever before as the race to decarbonize intensifies. Electrification in the transportation sector has led to technology shifts and rapid deployment of electric vehicles (EVs). The potential increase in stochastic and spatially heterogeneous charging load presents a unique challenge that is not well studied, and will have significant impacts on grid operations, emissions, and system reliability if not managed effectively. Realistic scenario generators can help operators prepare, and machine learning can be leveraged to this end. In this work, we develop generative adversarial networks (GANs) to learn distributions of electric vehicle (EV) charging sessions and disentangled representations. We show that this model successfully parameterizes unlabeled temporal and power patterns and is able to generate synthetic data conditioned on these patterns. We benchmark the generation capability of this model with Gaussian Mixture Models (GMMs), and empirically show that our proposed model framework is better at capturing charging distributions and temporal dynamics.

Authors: Robert Buechler (Stanford University); Emmanuel O Balogun (Stanford University); Arun Majumdar (Stanford University); Ram Rajagopal (Stanford University)
ICML 2021 From Talk to Action with Accountability: Monitoring the Public Discussion of Policy Makers with Deep Neural Networks and Topic Modelling (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Decades of research on climate have provided a consensus that human activity has changed the climate and we are currently heading into a climate crisis. While public discussion and research efforts on climate change mitigation have increased, potential solutions need to not only be discussed but also effectively deployed. For preventing mismanagement and holding policy makers accountable, transparency and degree of information about government processes have been shown to be crucial. However, currently the quantity of information about climate change discussions and the range of sources make it increasingly difficult for the public and civil society to maintain an overview to hold politicians accountable. In response, we propose a multi-source topic aggregation system (MuSTAS) which processes policy makers speech and rhetoric from several publicly available sources into an easily digestible topic summary. MuSTAS uses novel multi-source hybrid latent Dirichlet allocation to model topics from a variety of documents. This topic digest will serve the general public and civil society in assessing where, how, and when politicians talk about climate and climate policies, enabling them to hold politicians accountable for their actions to mitigate climate change and lack thereof.

Authors: Vili Hätönen (Emblica); Fiona Melzer (University of Edinburgh)
ICML 2021 NeuralNERE: Neural Named Entity Relationship Extraction for End-to-End Climate Change Knowledge Graph Construction (Proposals Track)
Abstract and authors: (click to expand)

Abstract: This paper proposes an end-to-end Neural Named Entity Relationship Extraction model (called NeuralNERE) for climate change knowledge graph (KG) construction, directly from the raw text of relevant news articles. The proposed model will not only remove the need for any kind of human supervision for building knowledge bases for climate change KG construction (used in the case of supervised or dictionary-based KG construction methods), but will also prove to be highly valuable for analyzing climate change by summarising relationships between different factors responsible for climate change, extracting useful insights & reasoning on pivotal events, and helping industry leaders in making more informed future decisions. Additionally, we also introduce the Science Daily Climate Change dataset (called SciDCC) that contains over 11k climate change news articles scraped from the Science Daily website, which could be used for extracting prior knowledge for constructing climate change KGs.

Authors: Prakamya Mishra (Independent Researcher); Rohan Mittal (Independent Researcher)
ICML 2021 Enhancing Laboratory-scale Flow Imaging of Fractured Geological Media with Deep Learning Super Resolution (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Injection into deep geological formations is a promising approach for the utilization, sequestration, and removal from the atmosphere of CO2 emissions. Laboratory experiments are essential to characterize how CO2 flows and reacts in various types of geological media. We reproduce such dynamic injection processes while imaging using Computed Tomography (CT) at sufficient temporal resolution to visualize changes in the flow field. The resolution of CT, however, is on the order of 100's of micrometers and insufficient to characterize fine-scale reaction-induced alterations to micro-fractures. Super resolution deep learning is, therefore, an essential tool to improve spatial resolution of dynamic CT images. We acquired and processed pairs of multi-scale low- and high-resolution CT rock images. We also show the performance of our baseline model on fractured rock images using peak signal to noise ratio and structural similarity index. Coupling dynamic CT imaging with deep learning results in visualization with enhanced spatial resolution of about a factor of 4 thereby enabling improved interpretation.

Authors: Manju Pharkavi Murugesu (Stanford University); Timothy Anderson (Stanford University); Niccolo Dal Santo (MathWorks, Inc.); Vignesh Krishnan (The MathWorks Ltd); Anthony Kovscek (Stanford University)
ICML 2021 On the Role of Spatial Clustering Algorithms in Building Species Distribution Models from Community Science Data (Proposals Track) Best Paper: Proposals
Abstract and authors: (click to expand)

Abstract: This paper discusses opportunities for developments in spatial clustering methods to help leverage broad scale community science data for building species distribution models (SDMs). SDMs are tools that inform the science and policy needed to mitigate the impacts of climate change on biodiversity. Community science data span spatial and temporal scales unachievable by expert surveys alone, but they lack the structure imposed in smaller scale studies to allow adjustments for observational biases. Spatial clustering approaches can construct the necessary structure after surveys have occurred, but more work is needed to ensure that they are effective for this purpose. In this proposal, we describe the role of spatial clustering for realizing the potential of large biodiversity datasets, how existing methods approach this problem, and ideas for future work.

Authors: Mark Roth (Oregon State University); Tyler Hallman (Swiss Ornithological Institute); W. Douglas Robinson (Oregon State University); Rebecca Hutchinson (Oregon State University)
ICML 2021 Leveraging Domain Adaptation for Low-Resource Geospatial Machine Learning (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Machine learning in remote sensing has matured alongside a proliferation in availability and resolution of geospatial imagery, but its utility is bottlenecked by the need for labeled data. What's more, many labeled geospatial datasets are specific to certain regions, instruments, or extreme weather events. We investigate the application of modern domain-adaptation to multiple proposed geospatial benchmarks, uncovering unique challenges and proposing solutions to them.

Authors: John M Lynch (NC State University); Sam Wookey (Masterful AI)
ICML 2021 APPLYING TRANSFORMER TO IMPUTATION OF MULTI-VARIATE ENERGY TIME SERIES DATA (Proposals Track)
Abstract and authors: (click to expand)

Abstract: To reduce the greenhouse gas emissions from electricity production, it is necessaryto switch to an energy system based on renewable energy sources (RES). However,intermittent electricity generation from RES poses challenges for energy systems.The primary input for data-driven solutions is data on electricity generation fromRES, which usually contain many missing values. This proposal studies the useof attention-based algorithms to impute missing values of electricity production,electricity demand and electricity prices. Since attention mechanisms allow us totake into account dependencies between time series across multiple dimensionsefficiently, our approach goes beyond classic statistical methods and incorporatesmany related variables, such as electricity price, demand and production by othersources. Our preliminary results show that while transformers can come at highercomputational costs, they are more precise than classical imputation methods.

Authors: Hasan Ümitcan Yilmaz (Karlsruhe Institute of Technology); Max Kleinebrahm (Karlsruhe Institut für Technologie); Christopher Bülte (Karlsruhe Institute of Technology); Juan Gómez-Romero (Universidad de Granada)
NeurIPS 2020 Machine learning for advanced solar cell production: adversarial denoising, sub-pixel alignment and the digital twin (Papers Track)
Abstract and authors: (click to expand)

Abstract: Photovoltaic is a main pillar to achieve the transition towards a renewable energy supply. In order to continue the tremendous cost decrease of the last decades, novel cell techologies and production processes are implemented into mass production to improve cell efficiency. Raising their full potential requires novel techniques of quality assurance and data analysis. We present three use-cases along the value chain where machine learning techniques are investigated for quality inspection and process optimization: Adversarial learning to denoise wafer images, alignment of surface structuring processes via sub-pixel coordinate regression, and the development of a digital twin for wafers and solar cells for material and process analysis.

Authors: Matthias Demant (Fraunhofer ISE); Leslie Kurumundayil (Fraunhofer ISE); Philipp Kunze (Fraunhofer ISE); Aditya Kovvali (Fraunhofer ISE); Alexandra Woernhoer (Fraunhofer ISE); Stefan Rein (Fraunhofer ISE)
NeurIPS 2020 Narratives and Needs: Analyzing Experiences of Cyclone Amphan Using Twitter Discourse (Papers Track)
Abstract and authors: (click to expand)

Abstract: People often turn to social media to comment upon and share information about major global events. Accordingly, social media is receiving increasing attention as a rich data source for understanding people's social, political and economic experiences of extreme weather events. In this paper, we contribute two novel methodologies that leverage Twitter discourse to characterize narratives and identify unmet needs in response to Cyclone Amphan, which affected 18 million people in May 2020.

Authors: Ancil S Crayton (Booz Allen Hamilton); Joao Fonseca (NOVA Information Management School); Kanav Mehra (Independent Researcher); Jared Ross (Booz Allen Hamilton); Marcelo Sandoval-Castañeda (New York University Abu Dhabi); Michelle Ng (International Water Management Institute); Rachel von Gnechten (International Water Management Institute)
NeurIPS 2020 Emerging Trends of Sustainability Reporting in the ICT Industry: Insights from Discriminative Topic Mining (Papers Track)
Abstract and authors: (click to expand)

Abstract: The Information and Communication Technologies (ICT) industry has a considerable climate change impact and accounts for approximately 3 percent of global carbon emissions. Despite the increasing availability of sustainability reports provided by ICT companies, we still lack a systematic understanding of what has been disclosed at an industry level. In this paper, we make the first major effort to use modern unsupervised learning methods to investigate the sustainability reporting themes and trends of the ICT industry over the past two decades. We build a cross-sector dataset containing 22,534 environmental reports from 1999 to 2019, of which 2,187 are ICT specific. We then apply CatE, a text embedding based topic modeling method, to mine specific keywords that ICT companies use to report on climate change and energy. As a result, we identify (1) important shifts in ICT companies' climate change narratives from physical metrics towards climate-related disasters, (2) key organizations with large influence on ICT companies, and (3) ICT companies' increasing focus on data center and server energy efficiency.

Authors: Lin Shi (Stanford University); Nhi Truong Vu (Stanford University)
NeurIPS 2020 High-resolution global irrigation prediction with Sentinel-2 30m data (Papers Track)
Abstract and authors: (click to expand)

Abstract: An accurate and precise understanding of global irrigation usage is crucial for a variety of climate science efforts. Irrigation is highly energy-intensive, and as population growth continues at its current pace, increases in crop need and water usage will have an impact on climate change. Precise irrigation data can help with monitoring water usage and optimizing agricultural yield, particularly in developing countries. Irrigation data, in tandem with precipitation data, can be used to predict water budgets as well as climate and weather modeling. With our research, we produce an irrigation prediction model that combines unsupervised clustering of Normalized Difference Vegetation Index (NDVI) temporal signatures with a precipitation heuristic to label the months that irrigation peaks for each cropland cluster in a given year. We have developed a novel irrigation model and Python package ("Irrigation30") to generate 30m resolution irrigation predictions of cropland worldwide. With a small crowdsourced test set of cropland coordinates and irrigation labels, using a fraction of the resources used by the state-of-the-art NASA-funded GFSAD30 project with irrigation data limited to India and Australia, our model was able to achieve consistency scores in excess of 97% and an accuracy of 92% in a small geo-diverse randomly sampled test set.

Authors: Will Hawkins (UC Berkeley); Weixin Wu (UC Berkeley); Sonal Thakkar (UC Berkeley); Puya Vahabi (UC Berkeley); Alberto Todeschini (UC Berkeley)
NeurIPS 2020 In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness (Papers Track)
Abstract and authors: (click to expand)

Abstract: Many machine learning applications used to tackle climate change involve lots of unlabeled data (such as satellite imagery) along with auxiliary information such as climate data. In this work, we show how to use auxiliary information in a semi-supervised setting to improve both in-distribution and out-of-distribution (OOD) accuracies (e.g. for countries in Africa where we have very little labeled data). We show that 1) on real-world datasets, the common practice of using auxiliary information as additional input features improves in-distribution error but can hurt OOD. Oppositely, we find that 2) using auxiliary information as outputs of auxiliary tasks to pre-train a model improves OOD error. 3) To get the best of both worlds, we introduce In-N-Out, which first trains a model with auxiliary inputs and uses it to pseudolabel all the in-distribution inputs, then pre-trains a model on OOD auxiliary outputs and fine-tunes this model with the pseudolabels (self-training). We show both theoretically and empirically on remote sensing datasets for land cover prediction and cropland prediction that In-N-Out outperforms auxiliary inputs or outputs alone on both in-distribution and OOD error.

Authors: Robbie M Jones (Stanford University); Sang Michael Xie (Stanford University); Ananya Kumar (Stanford University); Fereshte Khani (Stanford); Tengyu Ma (Stanford University); Percy Liang (Stanford University)
NeurIPS 2020 Wildfire Smoke and Air Quality: How Machine Learning Can Guide Forest Management (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Prescribed burns are currently the most effective method of reducing the risk of widespread wildfires, but a largely missing component in forest management is knowing which fuels one can safely burn to minimize exposure to toxic smoke. Here we show how machine learning, such as spectral clustering and manifold learning, can provide interpretable representations and powerful tools for differentiating between smoke types, hence providing forest managers with vital information on effective strategies to reduce climate-induced wildfires while minimizing production of harmful smoke.

Authors: Lorenzo Tomaselli (Carnegie Mellon University); Coty Jen (Carnegie Mellon University); Ann Lee (Carnegie Mellon University)
NeurIPS 2020 Machine Learning Informed Policy for Environmental Justice in Atlanta with Climate Justice Implications (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Environmental hazards are not evenly distributed between the privileged and the protected classes in the U.S. Neighborhood zoning and planning of hazardous treatment, storage, and disposal facilities (TSDs) play a significant role in this sanctioned environmental racism. TSDs and toxic chemical releases into the air are accounted for by the U.S. Environmental Protection Agency’s (EPA) Toxic Release Inventories (TRIs) [2,4,7, 14]. TSDs and toxic chemical releases not only emit carbon dioxide and methane, which are the top two drivers of climate change, but also emit contaminants, such as arsenic, lead, and mercury into the water, air, and crops [12]. Studies on spatial disparities in TRIs and TSDs based on race/ethnicity and socioeconomic status (SES) in U.S. cities, such as Charleston, SC, San Joaquin Valley, CA, and West Oakland, CA showed that there are more TRIs and TSDs in non-white and low SES areas in those cities [2,4,7]. Environmental justice recognizes that the impacts of environmental burdens, such as socioeconomic and public health outcomes, are not equitably distributed, and in fact bear the heaviest burden on marginalized people, including communities of color and low-income communities [12]. In our case, environmental justice has a strong tie to climate justice since the TRIs release carbon dioxide and methane into the atmosphere.

Authors: Lelia Hampton (Massachusetts Institute of Technology)
NeurIPS 2020 Expert-in-the-loop Systems Towards Safety-critical Machine Learning Technology in Wildfire Intelligence (Proposals Track)
Abstract and authors: (click to expand)

Abstract: With the advent of climate change, wildfires are becoming more frequent and severe across several regions worldwide. To prevent and mitigate its effects, wildfire intelligence plays a pivotal role, e.g. to monitor the evolution of wildfires and for early detection in high-risk areas such as wildland-urban-interface regions. Recent works have proposed deep learning solutions for fire detection tasks, however the current limited databases prevent reliable real-world deployments. We propose the development of expert-in-the-loop systems that combine the benefits of semi-automated data annotation with relevant domain knowledge expertise. Through this approach we aim to improve the data curation process and contribute to the generation of large-scale image databases for relevant wildfire tasks and empower the application of machine learning techniques in wildfire intelligence in real scenarios.

Authors: Maria João Sousa (IDMEC, Instituto Superior Técnico, Universidade de Lisboa); Alexandra Moutinho (IDMEC, Instituto Superior Técnico, Universidade de Lisboa); Miguel Almeida (ADAI, University of Coimbra)