AAAI 2022 Fall Symposium: The Role of AI in Responding to Climate Challenges

About

Climate change is one of the most pressing challenges of our time, requiring rapid action across society. As artificial intelligence tools (AI) are rapidly deployed, it is therefore crucial to understand how they will impact climate action. On the one hand, AI can support applications in climate change mitigation (reducing or preventing greenhouse gas emissions), adaptation (preparing for the effects of a changing climate), and climate science. These applications have implications in areas ranging as widely as energy, agriculture, and finance. At the same time, AI is used in many ways that hinder climate action (e.g., by accelerating the use of greenhouse gas-emitting fossil fuels). In addition, AI technologies have a carbon and energy footprint themselves. This symposium brought together participants from across academia, industry, government, and civil society to explore these intersections of AI with climate change, as well as how each of these sectors can contribute to solutions.

About the AAAI Fall Symposium Series

This symposium was part of the AAAI Fall Symposium Series, which aims to provide a forum to present ongoing work, hold focused discussions, build new communities for emerging disciplines, and build ties between existing disciplines. The Symposium Series is run via the Association for the Advancement of Artificial Intelligence (AAAI), the premier international scientific society devoted to promoting research in, and the responsible use of, artificial intelligence. Symposia are open to the public; it is not necessary to submit to the symposium in order to attend, though submissions are strongly encouraged.

About the Symposium

COVID Policy

The 2022 Fall Symposium Series was a primarily in-person event. The guidelines provided by AAAI were as follows:

Schedule

The symposium ran from November 17-19 in Arlington, VA, USA, and included keynote talks, panels, presentations of contributed work, poster sessions, and discussion sessions.

Jump to: Thursday (17th), Friday (18th), Saturday (19th)

Thursday, November 17

Time (ET) Event
Welcome and Opening Remarks
Overview of Conference Themes
Burcu Akinci: Digital Twins and Context-aware AI for Energy Efficient Buildings (Keynote)
Details: (click to expand) Speaker Bio: Dr. Burcu Akinci is the Paul Christiano Professor of Civil & Environmental Engineering at Carnegie Mellon University and a member of the National Academies of Construction. Her research interests include modeling and reasoning about information rich histories of buildings and infrastructure systems, to streamline construction and infrastructure operations. She specifically focuses on investigating utilization and integration of building information models with data capture technologies, such as 3D imaging and embedded sensors, to create digital twins of construction projects and infrastructure operations, and develop approaches to support proactive and predictive operations and management. Dr. Akinci has two patents, and one provisional patent and over 70 refereed journal publications and 100 conference publications. She was the PI of more than $6M grants and co-PI of more than $10M grants, supported by federal and state agencies and industry. She has given over 100 invited presentations and co-edited books on CAD/GIS Integration and on Embedded Commissioning. She earned a bachelor’s degree in civil engineering from the Middle East Technical University (Ankara, Turkey), MBA from Bilkent University (Ankara, Turkey), and Master’s and PhD degrees in Civil and Environmental Engineering with a specialization in Construction Engineering and Management from Stanford University.
Adiba Proma: NADBenchmarks - a compilation of Benchmark Datasets for Machine Learning Tasks related to Natural Disasters (Contributed Paper)
Coffee Break
Laure Berti-Equille: Discovering Transition Pathways Towards Coviability with Machine Learning (Contributed Paper)
Kim Bente: Probabilistic Machine Learning in Polar Earth and Climate Science: A Review of Applications and Opportunities (Contributed Paper)
Troy Harvey: Architecting a Path Toward Generalized Autonomy: Addressing the Biggest Opportunity in Decarbonization (Keynote)
Details: (click to expand) Speaker Bio: Troy Harvey is CEO and co-founder of PassiveLogic, the creator of the first platform for generalized autonomy. As architect of the Quantum Digital Twin standard and Deep Physics AI engine, his empathic, systems-oriented approach to technology development is transforming the way we control systems and equipment. Optimizing buildings, cities, and other controlled systems is the clearest opportunity Troy sees to contribute to the world’s most pressing climate challenges.
Lunch
Jose Manuel Carbo: Machine Learning Methods in Climate Finance: A Systematic Review (Contributed Paper)
Alix Auzepy: The Impact of TCFD Reporting - A New Application of Zero-Shot Analysis to Climate-Related Financial Disclosures (Contributed Paper)
Tristan Ballard: Contrastive Learning for Climate Model Bias Correction and Super-Resolution (Contributed Paper)
Paula Harder: Generating physically-consistent high-resolution climate data with hard-constrained neural networks (Contributed Paper)
Break
Matthew Cooper: Predicting Wildfire Risk Under Novel 21st-Century Climate Conditions (Contributed Paper)
Rendani Mbuvha: Imputation of Missing Streamflow Data at Multiple Gauging Stations in Benin Republic (Contributed Paper)
Lightning Talks
Sebastian Hickman & Paul Griffiths, "Predicting Daily Ozone Air Pollution With Transformers"
Pedro Roberto Barbosa Rocha, "Data-Driven Reduced-Order Model for Atmospheric CO2 Dispersion"
Arjun Ashok, "Self-Supervised Representations of Geo-located Weather Time Series - An Evaluation and Analysis"
Thai-Nam Hoang, "Wildfire Forecasting with Satellite Images and Deep Generative Model"
Panel: Where is the funding, and is it sufficient to meet the 2030 and 2050 goals?
Details: (click to expand) Panelists: Dr. Fahmida Chowdhury (NSF), Dr. David Tew (ARPA-E), Jon Greene (ITA International), Andrés Alonso Robisco (Banco de España)
Moderator: Dr. Jim Spohrer (ISSIP, formerly IBM)

Panelist bios:
  • Dr. Fahmida Chowdhury is a Program Director in the Office of International Science and Engineering (OISE) at the National Science Foundation (NSF). Before joining NSF in 2008, she was a Professor of Electrical and Computer Engineering at the University of Louisiana, Lafayette, where she held the W. Hansen Hall and Mary O. Hall Endowed Chair in Computer Engineering. Fahmida was born in Bangladesh, received a combined BSc/MSc degree in electromechanical engineering from Moscow Power Engineering Institute, Moscow, Russia (1981), and PhD in electrical engineering from Louisiana State University, Baton Rouge, Louisiana (1988). She was a Fulbright Fellow (2001) and is currently an IEEE Distinguished Lecturer. She has served as an Associate Editor for IEEE Transactions on Control Systems Technology and IEEE Transactions on Neural Networks; she currently serves on the editorial board of the IEEE Transactions on Artificial Intelligence.
  • Dr. David Tew is currently a Program Director at ARPA-E, where he is leading a $200M portfolio of projects focused on the development of technological solutions to our energy and climate challenges. This portfolio includes a $36M program that is developing machine learning enhanced energy technology design tools – DIFFERENTIATE. The efforts within this program are seeking to enhance the productivity of energy engineers by accelerating the design process via the development of three capabilities: optimizers with energy-domain knowledge, surrogate models that are capable of providing nearly instantaneous high fidelity design performance predictions, and generative models/inverse design tools that are capable of automatically generating design concepts from requirements. Before coming to ARPA-E, he had a nearly twenty-year career at United (now Raytheon) Technologies, where he either led or played a key role in the development of range of power and aerospace propulsion technologies – including pulse detonation rocket engines, microturbine-based combined cooling heating and power systems, organic Rankine cycle waste heat recovery systems and solid oxide fuel cell-based small aircraft propulsion systems. Dr. Tew has an S.M. and Ph.D. in Aeronautics and Astronautics from M.I.T., a B.S.E. in Aerospace Engineering from the University of Michigan, and an M.B.A. from Columbia Business School.
  • Jon Greene serves as a Senior Advisor to the CEO. He seeks to develop new opportunities around sustainable human ecosystems, to assist the Growth team and to help identify and bring new technology to serve ITA’s customers. Greene was in the U.S. Navy for over 28 years to include serving as Commanding Officer USS McInerney (FFG 8), Reactor Officer on USS Theodore Roosevelt (CVN 71) and Commanding Officer of Combat Direction System Activity, Dam Neck in Virginia Beach, Virginia. Following his Navy career, Greene joined Virginia Tech serving in a variety of roles including Associate Director for Strategic Development of the Institute for Critical Technology and Applied Science. He has led or supported initiatives for a broad spectrum of research activities to include unmanned systems, data analytics, wireless communications, weapon systems, computation and space science. He was the founding executive director of the Mid Atlantic Aviation Partnership, Virginia Tech’s FAA sponsored UAS Test Site. Greene has a bachelor’s degree in general science from the United States Naval Academy and a master’s degree in national security affairs (Strategic Planning) from the Naval Postgraduate School.
  • Andrés Alonso Robisco joined Banco de España in 2019 as senior economist in the Financial Innovation Division where he analyses the latest trends in financial innovation. Specifically, he studies the impact of machine learning on credit risk modelling, and different topics related to climate finance innovation. Previously he had been working in the Single Resolution Board (SRB), an agency of the European Commission, and Instituto de Credito Oficial (ICO), the financial agency of the Kingdom of Spain. He holds a MSc in Quantitative Finance by AFI and he is PhD candidate in Economics by Universidad Autonoma de Madrid. His work has been published in journals like International Review of Financial Analysis and Financial Innovation.
  • Dr. Jim Spohrer is a student of service science and open-source, trusted AI. He is a retired industry executive (Apple, IBM), who is a member of the Board of Directors of the non-profit International Society of Service Innovation Professionals (ISSIP). At IBM, he served as Director for Open Source AI/Data, Global University Programs, IBM Almaden Service Research, and CTO IBM Venture Capital Relations Group. At Apple, he achieved Distinguished Engineer Scientist Technologist (DEST) for authoring and learning platforms. After MIT (BS/Physics), he developed speech recognition systems at Verbex (Exxon), then Yale (PhD/Computer Science AI). With over ninety publications and nine patents, awards include AMA ServSIG Christopher Lovelock Career Contributions to the Service Discipline, Evert Gummesson Service Research, Vargo-Lusch Service-Dominant Logic, Daniel Berg Service Systems, and PICMET Fellow for advancing service science. In 2021, Jim was appointed a UIDP Senior Fellow (University-Industry Demonstration Partnership).
Reception

Friday, November 18

Time (ET) Event
Day 2 Welcome
Pamela K. Isom: Climate Innovations and the Role of AI and Cyber" (Keynote)
Details: (click to expand) Description: Mrs. Pamela K. Isom will share her personal perspectives and knowledge on the climate crisis and the roles AI and Cybersecurity must play towards economic prosperity and global security. During her talk, Isom will highlight examples of climate discoveries and explore AI patterns for sustainment. Some examples:
  • Fluid leak detection
  • Thwarting attacks on power and utility assets
  • Biosphere and biotechnologies
Speaker Bio: Mrs. Pamela K. Isom serves as FWG’s Chief Innovation Officer, bringing over 25 years of professional services experience in public and private sectors to FWG Solutions and clients. As a senior executive and team leader, she leads business focused transformations through the application of responsible innovations. Mrs. Isom previously served as Executive Director at the US Department of Energy where she was Director of the Artificial Intelligence & Technology Office and prior to that, Deputy Chief Information Officer. In total, she provided 7 years of Federal service guiding agencies through research, intellectual property management, governance, and application integration practices for the betterment of citizens. Her cross-industry experiences in manufacturing, e-commerce, financial services, energy and government have led to numerous recognitions for innovative outcomes including a Fed100 award. Mrs. Isom holds a Master’s in Information Systems Management from Walden University. She is the author of a book, has published in scientific journals, has been awarded several patents, and she is a small business entrepreneur.
Aryan Jain: Employing Deep Learning to Quantify Power Plant Greenhouse Gas Emissions via Remote Sensing Data (Contributed Paper)
Yeji Choi: Intermediate and Future Frame Prediction of Geostationary Satellite Imagery With Warp and Refine Network (Contributed Paper)
Break
Junjie Xu: From Ideas to Deployment - A Joint Industry-University Research Effort on Tackling Carbon Storage Challenges with AI (Contributed Paper)
Aron Brenner: Graph Representation Learning for Energy Demand Data: Application to Joint Energy System Planning under Emissions Constraints (Contributed Paper)
Huseyin Tuna Erdinc: De-risking Carbon Capture and Sequestration with Explainable CO2 Leakage Detection in Time-lapse Seismic Monitoring Images (Contributed Paper)
Aditya Grover: Rethinking Machine Learning for Climate Science: A Dataset Perspective (Contributed Paper)
Tianyu Zhang & Stephan Zheng: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N (Contributed Paper)
Lunch
Ranveer Chandra: FarmVibes.AI: Democratizing Digital Tools for Sustainable Agriculture" (Keynote)
Details: (click to expand) Speaker Bio: Dr. Ranveer Chandra is the Managing Director for Research for Industry, and the CTO of Agri-Food at Microsoft. He also leads the Networking Research Group at Microsoft Research, Redmond. Previously, Ranveer was the Chief Scientist of Microsoft Azure Global. His research has shipped as part of multiple Microsoft products, including VirtualWiFi in Windows 7 onwards, low power Wi-Fi in Windows 8, Energy Profiler in Visual Studio, Software Defined Batteries in Windows 10, and the Wireless Controller Protocol in XBOX One. His research also led to a new product, called Azure FarmBeats. Ranveer has published more than 100 papers, and holds over 150 patents granted by the USPTO. His research has been cited by the popular press, such as the Economist, MIT Technology Review, BBC, Scientific American, New York Times, WSJ, among others. He is a Fellow of the IEEE, and has won several awards, including best paper awards at ACM CoNext 2008, ACM SIGCOMM 2009, IEEE RTSS 2014, USENIX ATC 2015, Runtime Verification 2016 (RV’16), ACM COMPASS 2019, and ACM MobiCom 2019, the Microsoft Research Graduate Fellowship, the Microsoft Gold Star Award, the MIT Technology Review’s Top Innovators Under 35, TR35 (2010) and Fellow in Communications, World Technology Network (2012). He was recently recognized by the Newsweek magazine as America’s 50 most Disruptive Innovators (2021). Ranveer has an undergraduate degree from IIT Kharagpur, India and a PhD from Cornell University.
Nicolas Webersinke: ClimateBert: A Pretrained Language Model for Climate-Related Text (Contributed Paper)
Md Saiful Islam & Adiba Proma: KnowUREnvironment: An Automated Knowledge Graph for Climate Change and Environmental Issues (Contributed Paper)
Break
Lightning Talks
Tarun Narayanan & Ajay Krishnan, "Curator: Creating Large-Scale Curated Labelled Datasets using Self-Supervised Learning"
John Aitken & Denali Rao, "AI-Based Text Analysis for Evaluating Food Waste Policies"
Nitpreet Bamra, "Towards Generating Large Synthetic Phytoplankton Datasets for Efficient Monitoring of Harmful Algal Blooms"
Xin Zhou: Using Natural Language Processing for Automating the Identification of Climate Action Interlinkages within the Sustainable Development Goals (Contributed Paper)
Panel: What governance and actions are necessary to align AI with climate change goals, the UN Sustainable Development Goals, and associated ESG frameworks?
Details: (click to expand) Panelists: Dr. Lance Eliot (Stanford Fellow, Techbrium Incorporated), Serge Conesa (Immersion4), Dr. Bosen Liu (ITU, UNESCO), Allison Rogers (Aspen Institute, Second Nature), John C. Havens (IEEE Standards Association)
Moderator: Pierre-Adrien Hanania (Capgemini)

Panelist bios:
  • Dr. Lance Eliot is a globally recognized expert in AI & Law+Ethics and serves as a Stanford Fellow at Stanford University in joint affiliation with the Stanford Law School and the Stanford Computer Science Department via the Center for Legal Informatics. He is also the CEO and founder of Techbrium Incorporated and has been a highly successful entrepreneur having founded, run, and sold several AI high-tech startups. Dr. Eliot has been a keynote speaker at the AI World conference and other major industry events. His popular columns have amassed over 6.8+ million views including for Forbes. He serves on vital AI governance committees for the World Economic Forum (WEF), ITU United Nations, NIST, IEEE, and other international entities. His keen AI trends insights and expertise have been featured in Bloomberg Law, The AI Journal, Lawyer Monthly, MIT Computational Law Journal, Attorney At Law Magazine, The Global Legal Post, Jurist, The Daily Legal Journal, Law Society Gazette, Law360, Legal Business World, and numerous other legal and business industry publications.
  • Serge Conesa brings over 30 years of experience in data communications and the IT networking industry, holding Executive key positions in both sales and marketing management with from Fortune 500 companies and over 20 start-ups. His experience ranges from working in the business of internationally expanding major telecommunications and civil infrastructure businesses coordinating all the key elements of a new business: including time, money, resources and technology throughout multiple geographies and cultures. His vision will help corporate and government customers assess, optimize, and manage the life cycle of resources utilization for enhanced efficiency and reduced energy consumption. At the highest levels of governments, energy independence is recognized as key to maintain a nation’s economic and political security. His work is giving now the ability to respond to the call from the White House, not only in addressing, but also in helping to solve the nation’s need for energy independence in a climate of greater demand and diminishing resources, and to replace the current inefficient industrial model of resources management with a new highly efficient model.
  • Dr. Bosen Lily Liu is an Expert Group Leader for the “Focus Group on Environmental Efficiency for Artificial Intelligence and other Emerging Technologies (FG-AI4EE)” at International Telecommunication Union (ITU), the United Nations specialized agency for information and communication technologies. Since 2020, she has lead a team of 28 experts and successfully launched the Technical Report on “Guidelines on the implementation of eco-friendly criterias for AI and other emerging technologies.” Before joining AI4EE, she has served as an expert for the United for Smart Sustainable Cities (U4SSC) Initiative at ITU in 2018. In parallel to Bosen's contribution at ITU, she is currently working for UNESCO as a Lead on the Transforming Education agenda. Prior to this role, she has worked for UNESCO since 2020 as a Policy Analyst on higher education with a focus on innovation, in 2018 as the technical focal point of UNESCO to Namibia’s Ministry of Education to provide support on Namibia’s National ICT Policy revision and Implementation Plan, and in 2015 as a publication intern at UNESCO HQ on Open Educational Resources and Mobile Learning.
  • Allison Rogers currently serves as the Climate Policy Advisor for the Aspen Tech Policy Hub, a Bay Area policy incubator focused on training a new generation of science and tech policy entrepreneurs. The Aspen Tech Policy Hub is a division of Aspen Digital, which empowers policymakers, civic organizations, companies, and the public to be responsible stewards of technology and media in the service of an informed, just, and equitable world. Allison also serves as an America Is All In Fellow with Second Nature, a leading organization committed to accelerating climate action in, and through, higher education. She previously served as the Executive Director for the Green the Capitol Office within the U.S. House of Representatives, where she and her team were tasked by Speaker of the House Nancy Pelosi with making the U.S. Capitol a model of sustainability for the nation. Allison received her LL.M. in Energy Law (with a Certificate in Climate Law) and J.D. from Vermont Law School, M.A. in National Security and Strategic Studies from the U.S. Naval War College, Ed.M. from the Harvard Graduate School of Education, and A.B. from Harvard College. She spent a semester abroad at McGill University Faculty of Law, where she studied AI governance and other areas of international law.
  • John C. Havens is Lead of the Sustainability Practice of the IEEE Standards Association where he drives the strategy, coordination, and vision for The IEEE SA Planet Positive 2030 Program. He is also Executive Director of The IEEE Global Initiative on Ethics of Autonomous and Intelligent Systems which was responsible for the creation and iteration of a body of work known as Ethically Aligned Design: A Vision for Prioritizing Human Well- being with Autonomous and Intelligent Systems that was utilized by the United Nations, the OECD, IBM and dozens of organizations to create their AI principles, policies, and technology. Previously, John was an EVP of Social Media at PR Firm, Porter Novelli, led Business Development at BlogTalkRadio, and was a professional actor for over 15 years. John has written for Mashable and The Guardian and is author of the books, Heartificial Intelligence: Embracing Our Humanity To Maximize Machines and Hacking Happiness: Why Your Personal Data Counts and How Tracking it Can Change the World. For more information, follow John on LinkedIn or @johnchavens on twitter. John currently has over ninety citations on Research Gate and dozens of articles for outlets such as The Guardian, Quartz, IEEE Spectrum and Mashable.
  • Pierre-Adrien Hanania: As member of the Business & Technology Solutions Team Public Sector of Capgemini, I provide strategy and technology consultancy services on different aspects of digital transformation. Doing this, I always aim at embracing the full potential of Europeanization, addressing common digital challenges on a European level in order to provide the best solution possible. Furthermore, I advise our clients as Global Offer Leader AI in Public Sector, analyzing industry trends and accompanying Public Sector clients in their journey to a sustainable, meaningful and ethical AI. As former political analyst, I use my previous experiences I had in several European think tanks in order to detect the synergies between industry trends and the political frame.
Workshop Discussion & Readout Prep
Cross-Symposium Plenary Session

Saturday, November 19

Time (ET) Event
Group Breakout Discussion: The Way Forward on Aligning AI with Climate Action
Details: (click to expand) Join us for a group breakout discussion to brainstorm concrete steps and the way forward on aligning AI with climate action.

Moderator: Dr. Priya Donti (Climate Change AI)
Break
Group Breakout Discussion Ctd. & Sharing of Next Steps

Accepted Works

Title Authors
(1) AI-Based Text Analysis for Evaluating Food Waste Policies John Aitken (The MITRE Corporation), Denali Rao (The MITRE Corporation), Balca Alaybek (The MITRE Corporation), Amber Sprenger (The MITRE Corporation), Grace Mika (The MITRE Corporation), Rob Hartman (The MITRE Corporation) and Laura Leets (The MITRE Corporation)
(2) Data-Driven Reduced-Order Model for Atmospheric CO2 Dispersion Pedro Roberto Barbosa Rocha (IBM Research), Marcos Sebastião de Paula Gomes (Pontifical Catholic University of Rio de Janeiro), João Lucas de Sousa Almeida (IBM Research), Allan Moreira Carvalho (IBM Research) and Alberto Costa Nogueira Junior (IBM Research)
(3) KnowUREnvironment: An Automated Knowledge Graph for Climate Change and Environmental Issues Md Saiful Islam (University of Rochester), Adiba Proma (University of Rochester), Yilin Zhou (University of Rochester), Syeda Nahida Akter (Carnegie Mellon University), Caleb Wohn (University of Rochester) and Ehsan Hoque (University of Rochester)
(4) Towards Generating Large Synthetic Phytoplankton Datasets for Efficient Monitoring of Harmful Algal Blooms Nitpreet Bamra (University of Waterloo), Vikram Voleti (Mila, University of Montreal), Alexander Wong (University of Waterloo) and Jason Deglint (University of Waterloo)
(5) Generating physically-consistent high-resolution climate data with hard-constrained neural networks Paula Harder (Fraunhofer Institute ITWM, Mila Quebec AI Institute), Qidong Yang (Mila Quebec AI Institute, New York University), Venkatesh Ramesh (Mila Quebec AI Institute, University of Montreal), Alex Hernandez-Garcia (Mila Quebec AI Institute, University of Montreal), Prasanna Sattigeri (IBM Research), Campbell D. Watson (IBM Research), Daniela Szwarcman (IBM Research) and David Rolnick (Mila Quebec AI Institute, McGill University).
(6) Discovering Transition Pathways Towards Coviability with Machine Learning Laure Berti-Equille (IRD) and Rafael Raimundo (UFPB)
(7) Wildfire Forecasting with Satellite Images and Deep Generative Model Thai-Nam Hoang (University of Wisconsin - Madison), Sang Truong (Stanford University) and Chris Schmidt (University of Wisconsin - Madison)
(8) From Ideas to Deployment - A Joint Industry-University Research Effort on Tackling Carbon Storage Challenges with AI Junjie Xu (Tsinghua University), Jiesi Lei (Tsinghua University), Yang Li (Tsinghua University), Junfan Ren (College of Petroleum Engineering, China University of Petroleum (Beijing), Beijing, China), Jian Qiu (Product and Solution & Website Business Unit, Alibaba Cloud, Hangzhou, Zhejiang, China), Biao Luo (Product and Solution & Website Business Unit, Alibaba Cloud, Hangzhou, Zhejiang, China), Lei Xiao (Product and Solution & Website Business Unit, Alibaba Cloud, Hangzhou, Zhejiang, China) and Wenwen Zhou (Product and Solution & Website Business Unit, Alibaba Cloud, Hangzhou, Zhejiang, China)
(9) NADBenchmarks - a compilation of Benchmark Datasets for Machine Learning Tasks related to Natural Disasters Adiba Proma (University of Rochester), Md Saiful Islam (University of Rochester), Stela Ciko (University of Rochester), Raiyan Abdul Baten (University of Rochester) and Ehsan Hoque (University of Rochester)
(10) Contrastive Learning for Climate Model Bias Correction and Super-Resolution Tristan Ballard (Sust Global) and Gopal Erinjippurath (Sust Global)
(11) Employing Deep Learning to Quantify Power Plant Greenhouse Gas Emissions via Remote Sensing Data Aryan Jain (Amador Valley High School)
(12) ClimateBert: A Pretrained Language Model for Climate-Related Text Nicolas Webersinke (FAU Erlangen-Nürnberg), Mathias Kraus (FAU Erlangen-Nürnberg), Julia Anna Bingler (ETH Zurich) and Markus Leippold (UZH Zurich)
(13) Curator: Creating Large-Scale Curated Labelled Datasets using Self-Supervised Learning Tarun Narayanan (SpaceML), Ajay Krishnan (SpaceML), Anirudh Koul (Pinterest, SpaceML, FDL) and Siddha Ganju (NVIDIA, SpaceML, FDL)
(14) De-risking Carbon Capture and Sequestration with Explainable CO2 Leakage Detection in Time-lapse Seismic Monitoring Images Huseyin Tuna Erdinc (Georgia Institute of Technology), Abhinav Prakash Gahlot (Georgia Institute of Technology), Ziyi Yin (Georgia Institute of Technology), Mathias Louboutin (Georgia Institute of Technology) and Felix J. Herrmann (Georgia Institute of Technology)
(15) Predicting Wildfire Risk Under Novel 21st-Century Climate Conditions Matthew Cooper (Sust Global).
(16) Probabilistic Machine Learning in Polar Earth and Climate Science: A Review of Applications and Opportunities Kim Bente (The University of Sydney), Judy Kay (The University of Sydney) and Roman Marchant (Commonwealth Scientific and Industrial Research Organisation (CSIRO))
(17) Rethinking Machine Learning for Climate Science: A Dataset Perspective Aditya Grover (UCLA)
(18) Graph Representation Learning for Energy Demand Data: Application to Joint Energy System Planning under Emissions Constraints Aron Brenner (MIT), Rahman Khorramfar (MIT), Dharik Mallapragada (MIT) and Saurabh Amin (MIT)
(19) Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N Tianyu Zhang (Université de Montréal, MILA), Andrew Williams (Université de Montréal, MILA), Soham Phade (Salesforce Research), Sunil Srinivasa (Salesforce Research), Yang Zhang (MILA), Prateek Gupta (MILA, University of Oxford, The Alan Turing Institute), Yoshua Bengio (Université de Montréal, MILA, CIFAR) and Stephan Zheng (Salesforce Research)
(20) Self-Supervised Representations of Geo-located Weather Time Series - an Evaluation and Analysis Arjun Ashok (IBM Research), Devyani Lambhate (IBM Research) and Jitendra Singh (IBM Research)
(21) Predicting Daily Ozone Air Pollution With Transformers Sebastian Hickman (University of Cambridge), Paul Griffiths (University of Cambridge), Peer Nowack (University of East Anglia) and Alex Archibald (University of Cambridge)
(22) The Impact of TCFD Reporting - A New Application of Zero-Shot Analysis to Climate-Related Financial Disclosures Alix Auzepy (Justus-Liebig-Universität Gießen), Elena Tönjes (Justus-Liebig-Universität Gießen) and Christoph Funk (Justus-Liebig-Universität Gießen)
(23) Using Natural Language Processing for Automating the Identification of Climate Action Interlinkages within the Sustainable Development Goals Xin Zhou (Institute for Global Environmental Strategies (IGES)), Kshitij Jain (Google Inc.), Mustafa Moinuddin (Institute for Global Environmental Strategies (IGES)) and Patrick McSharry (Carnegie Mellon University Africa; Oxford Man Institute of Quantitative Finance, Oxford University)
(24) Imputation of Missing Streamflow Data at Multiple Gauging Stations in Benin Republic Rendani Mbuvha (Queen Mary University of London), Julien Yise Peniel Adounkpe (International Water Management Institute (IWMI)), Wilson Tsakane Mongwe (University of Johannesburg), Mandela Houngnibo (Agence Nationale de la Météorologie du Benin Meteo Benin), Nathaniel Newlands (Summerland Research and Development Centre, Agriculture and Agri-Food Canada) and Tshilidzi Marwala (University of Johannesburg)
(25) Intermediate and Future Frame Prediction of Geostationary Satellite Imagery With Warp and Refine Network Minseok Seo (SI Analytics), Yeji Choi (SI Analytics), Hyungon Ryu (NVIDIA), Heesun Park (National Institute of Meteorological Science), Hyungkun Bae (SI Analytics), Hyesook Lee (National Institute of Meteorological Science) and Wanseok Seo (NVIDIA)
(26) Machine Learning Methods in Climate Finance: A Systematic Review Andres Alonso-Robisco (Banco de España), Jose Manuel Carbo (Banco de España) and Jose Manuel Marques (Banco de España)

Organizers

Feras A. Batarseh (Virginia Tech)
Priya L. Donti (Climate Change AI, MIT) - Co-Chair
Ján Drgoňa (PNNL)
Kristen Fletcher (Naval Postgraduate School)
Pierre-Adrien Hanania (Capgemini)
Melissa Hatton (Capgemini Government Solutions) - Co-Chair
Srinivasan Keshav (University of Cambridge)
Bran Knowles (Lancaster University)
Raphaela Kotsch (University of Zurich)
Sean McGinnis (Virginia Tech)
Peetak Mitra (PARC)
Alex Philp (Mitre)
Jim Spohrer (ISSIP)
Frank Stein (Virginia Tech) - Co-Chair
Meghna Tare (UT Arlington)
Svitlana Volkov (PNNL)
Gege Wen (Stanford)

Call for Submissions

We invite submissions of position, review, and research papers in two formats: short papers (2-4 pages) and full papers (6-8 pages). Submissions are due on Jul 29 by 23:59 AOE (Anywhere on Earth).

Topics may include, but are not limited to:

All submissions must make clear their connection to these topics and/or the broader theme of the workshop. Extended versions of articles in submission at other venues are acceptable as long as they do not violate the dual-submission policy of the other venue.

All submissions must be made through the EasyChair submission website (select “The Role of AI in Responding to Climate Challenges” track), and should be formatted according to the AAAI style template. All submissions will undergo single-blind peer review (that is, submissions should not be anonymized). Authors will have the option to publish their work in an open access proceedings site.

Please also see the FAQ, and contact climatechange.aaaifss2022@gmail.com with questions.

Submission Types

We invite submissions of position, review, and research papers (more details below).

We invite both short papers (2-4 pages) and full papers (6-8 pages). All figures, tables, and graphics must be contained within these page limits; however, references may extend onto additional pages. Supplementary appendices are allowed but will be read at the discretion of the reviewers.

Research Papers

Work that is in progress, published, and/or deployed.

Research Papers should describe projects relevant to the intersection of climate change and AI. These may include (but are not limited to) academic research; deployed results from startups, industry, public institutions, etc.; and climate-relevant datasets. In addition to describing the projects themselves, Research Papers should also include discussion of lessons learned, best practices, and areas whether further research and innovation is required.

Submissions applying AI to address a climate-relevant problem should provide experimental or theoretical validation of the method presented, as well as specifying what gap the method fills. Authors should clearly illustrate a pathway to climate impact, i.e., identify the way in which this work fits into broader efforts to address climate change. Algorithms need not be novel from an AI perspective, but should be applied in a climate-relevant setting. Details of methodology need not be revealed if they are proprietary, though transparency is highly encouraged.

Submissions presenting novel climate-relevant datasets are welcomed. Datasets should be designed to permit AI and machine learning research (e.g., formatted with clear benchmarks for evaluation). In this case, baseline experimental results on the dataset are preferred, but not required.

Review Papers

Overviews of relevant topics or fields.

Review Papers should provide overviews of topics or fields at the intersection of climate change and AI (e.g., pertaining to the topics listed in the call for submissions).

Submissions of this form should synthesize existing literature, and additionally provide insights on gaps, salient considerations, and future directions to be considered by symposium attendees and the broader community.

Position Papers

Opinions or critiques on relevant topics or directions.

Position Papers should provide opinions or critiques on topics or directions at the intersection of climate change and AI (e.g., pertaining to the topics listed in the call for submissions).

Submissions of this form should present important frameworks or considerations for work at the intersection of climate change and AI, and should be well-grounded in existing literature and/or practice.

Frequently Asked Questions

Q: I didn’t submit a paper to the symposium. Can I still attend?
A: Yes! Please register via the AAAI website.

Q: What is the COVID policy of the event?
A: We take COVID-19 very seriously, and will at minimum strictly adhere to all guidelines provided by AAAI. Please see more information above.

Q: I am interested in the topics of the symposium, but I cannot attend in person. Can I still participate?
A: Yes, registered attendees will be able to participate through Zoom. Because we are using hotel facilities, the quality of the virtual experience is out of our control. We recommend in-person participation to get the most benefit from this interactive symposium.

Q: How can I keep up to date on these issues?
A: We encourage you to sign up for the Climate Change AI newsletter to receive information about opportunities and events at the intersection of climate change and AI.

Submissions FAQ

Q: I’m not an AI researcher or practitioner. Can I still submit?
A: Yes, absolutely! We welcome submissions from a diverse set of stakeholders.

Q: What if my submission is accepted but I can’t attend the symposium in person?
A: A co-author or colleague can present for you, or you may be able to present via Zoom.

Q: Do I need to use the AAAI style files for my submission?
A: Yes, they are required.

Q: It’s hard for me to fit my submission within the page limits. What should I do?
A: Feel free to include appendices with additional material (these should be part of the same file as the main submission). Do not, however, put essential material in an appendix, as it will be read at the discretion of the reviewers.

Q: Can I send submissions directly by email?
A: No, please use the EasyChair website to make submissions, and select the track on “The Role of AI in Responding to Climate Challenges” when creating your submission. If you are having trouble with the EasyChair website, please contact: climatechange.aaaifss2022@gmail.com.

Q: Can I submit previously published work to this symposium?
A: Yes, though under limited circumstances. In particular, extended versions of articles in submission at other venues are acceptable as long as they do not violate the dual-submission policy of the other venue. Please contact climatechange.aaaifss2022@gmail.com with any questions.

Q: Can I submit work to this symposium if I am also submitting to another 2022 AAAI Fall Symposium session?
A: Yes. We cannot, however, guarantee that your assigned presentation time will not conflict with the other symposium.

Q: How will my submission be published?
A: We plan to publish proceedings on arXiv after the symposium. Please note that inclusion in the proceedings is optional - we encourage you to submit to and present at the workshop, even if you do not want your work to appear in the proceedings.

Q: If my work appears in the proceedings, can I also publish this work elsewhere?
A: All submissions to this symposium are “non-archival” - that is, from our perspective, choosing to include your work in the proceedings does not preclude future publication in another venue. However, we recommend that you also check the policies of the venue to which you might plan to submit (e.g., whether they allow publication of work that was previously posted as a preprint).