ICLR 2023 Workshop: Tackling Climate Change with Machine Learning

Many in the ML community wish to take action on climate change, but are unsure of the pathways through which they can have the most impact. This workshop highlights work that demonstrates that, while no silver bullet, ML can be an invaluable tool in reducing greenhouse gas emissions and in helping society adapt to the effects of climate change. Climate change is a complex problem, for which action takes many forms – from theoretical advances to deployment of new technology. Many of these actions represent high-impact opportunities for real-world change, and are simultaneously interesting academic research problems.

This workshop is part of a series (NeurIPS 2022, NeurIPS 2021, ICML 2021, NeurIPS 2020, ICLR 2020, NeurIPS 2019, and ICML 2019).

Climate change disproportionally affects people and environments in low- and middle-income countries. For this iteration of the workshop, we aim to explore the connection between global perspectives and local challenges in the context of employing machine learning to tackle climate change. As this is the first time one of the top machine learning conferences is being hosted in-person outside the Global North, we want to take this opportunity to shine a light on work that employs, analyzes, or critiques ML methods and their use for climate change mitigation and adaptation in low- and middle-income countries.

About ICLR

This workshop is part of the International Conference on Learning Representations (ICLR), one of the premier conferences on machine learning. For information on how to attend the ICLR conference, please see here https://iclr.cc/Conferences/2023. The workshop is open to the public; it is not necessary to submit to the workshop in order to attend.

About the Workshop

• Date: May 4, 2023
• Location: Kigali, Rwanda and virtual
• Contact: climatechangeai.iclr2023@gmail.com

Schedule

Call for Submissions

We invite submissions of short papers using machine learning to address problems in climate mitigation, adaptation, or modeling, including but not limited to the following topics:

• Agriculture and food
• Behavioural and social science
• Buildings
• Carbon capture and sequestration
• Cities and urban planning
• Climate finance and economics
• Climate justice
• Climate science and climate modeling
• Disaster management and relief
• Earth observations and monitoring
• Earth science
• Ecosystems and biodiversity
• Extreme weather
• Forestry and other land use
• Health
• Heavy industry and manufacturing
• Local and indigenous knowledge systems
• Materials science and discovery
• Oceans and marine systems
• Power and energy systems
• Public policy
• Societal adaptation and resilience
• Supply chains
• Transportation

All machine learning techniques are welcome, from kernel methods to deep learning. Each submission should make clear why the application has (or could have) a pathway to positive impacts regarding climate change. This year, we especially invite work that addresses, contextualizes and critiques the deployment of machine learning for tackling climate change in low- and middle income countries. We highly encourage submissions which make their data publicly available. Accepted submissions will be invited to give poster presentations, of which some will be selected for spotlight talks.

The workshop does not publish proceedings, and submissions are non-archival. Submission to this workshop does not preclude future publication. Previously published work may be submitted under certain circumstances (see the FAQ).

All papers and proposals submissions must be through the submission website. Submissions will be reviewed double-blind; do your best to anonymize your submission, and do not include identifying information for authors in the PDF. Authors are required to use the workshop style template (based on the ICLR style files), available for LaTeX.

All tutorial submissions must be through the submission website.

Please see the Tips for Submissions and FAQ, and contact climatechangeai.iclr2023@gmail.com with questions.

Submission Tracks

There are three tracks for submissions: (i) Papers, (ii) Proposals and (iii) Tutorials. Submissions are limited to 4 pages for the Papers track, and 3 pages for the Proposals track, in PDF format (see examples from previous workshops here). References do not count towards this total. Supplementary appendices are allowed but will be read at the discretion of the reviewers. All submissions must explain why the proposed work has (or could have) positive impacts regarding climate change.

PAPERS Track

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

Submissions for the Papers track should describe projects relevant to climate change that involve machine learning. These may include (but are not limited to) academic research; deployed results from startups, industry, public institutions, etc.; and climate-relevant datasets.

Submissions 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 a machine learning perspective if they are applied in a novel setting. Details of methodology need not be revealed if they are proprietary, though transparency is highly encouraged.

Submissions creating novel datasets are welcome. Datasets should be properly documented with regards to their provenance and contents and designed to permit machine learning research (e.g. formatted with clear benchmarks for evaluation).

PROPOSALS Track

Early-stage work and detailed descriptions of ideas for future work.

Submissions for the Proposals track should describe detailed ideas for how machine learning can be used to solve climate-relevant problems. While less constrained than the Papers track, Proposals will be subject to a very high standard of review. Ideas should be justified as extensively as possible, including motivation for why the problem being solved is important in tackling climate change, discussion of why current methods are inadequate, explanation of the proposed method, and discussion of the pathway to climate impact. Preliminary results are optional.

TUTORIALS Track

Interactive notebooks for insightful step-by-step walkthroughs

Submissions for the Tutorials track should introduce or demonstrate the use of machine learning methods and tools (e.g. libraries, packages, services, datasets, or frameworks) to address climate-relevant challenges. Tutorial proposals (due Jan 20) should take the form of an abstract and include a clear and concise description of what users can expect to learn from the tutorial. For accepted proposals, the initial draft of the tutorial submissions (due Feb 24) and final tutorial submissions (due March 31) should be in the form of executable notebooks and follow the CCAI Tutorial Template. Authors must submit the notebook in a self-contained runnable environment (e.g. Colab, Binder) to allow users and reviewers to easily access and run the tutorial notebook.

Tutorial proposal submissions will be reviewed based on their potential impact and usability by the climate and AI research community. Submissions will also be assessed based on the originality of the problem space; for this, kindly review our list of CCAI tutorials to minimize substantial overlap with existing tutorials. Notebook submissions will be assessed based on clarity, accessibility, and code quality. Lastly, we ask authors to emphasize the real-world impact of the ML models in the tutorial by answering questions such as: Who will be using the models/outputs and how will they be used? What decisions will be made based on these models? How will this impact existing systems/the environment/affected communities on the ground?

For more information on the tutorial proposal guidelines, kindly check this document.

Tips for Submissions

• For examples of typical formatting and content, see submissions from our previous workshops at NeurIPS 2022, NeurIPS 2021, ICML 2021, NeurIPS 2020, ICLR 2020, NeurIPS 2019, and ICML 2019.
• Be explicit: Describe how your proposed approach addresses climate change, demonstrating an understanding of the application area.
• Frame your work: The specific problem and/or data proposed should be contextualized in terms of prior work.
• Address the impact: Describe the practical implications of your method in addressing the problem you identify, as well as any relevant societal impacts or potential side-effects. We recommend reading our further guidelines on this aspect here.
• Explain the ML: Readers may not be familiar with the exact techniques you are using or may desire further detail.
• Justify the ML: Describe why the ML method involved is needed, and why it is a good match for the problem.
• Avoid jargon: Jargon is sometimes unavoidable but should be minimized. Ideal submissions will be accessible both to an ML audience and to experts in other relevant fields, without the need for field-specific knowledge. Feel free to direct readers to accessible overviews or review articles for background, where it is impossible to include context directly.

Addressing Impact

Tackling climate change requires translating ideas into action. The guidelines below will help you clearly present the importance of your work to a broad audience, hopefully including relevant decision-makers in industry, government, nonprofits, and other areas.

• Illustrate the link: Many types of work, from highly theoretical to deeply applied, can have clear pathways to climate impact. Some links may be direct, such as improving solar forecasting to increase utilization within existing electric grids. Others may take several steps to explain, such as improving computer vision techniques for classifying clouds, which could help climate scientists seeking to understand fundamental climate dynamics.
• Consider your target audience: Try to convey with relative specificity why and to whom solving the problem at hand will be useful. If studying extreme weather prediction, consider how you would communicate your key findings to a government disaster response agency. If analyzing a supply chain optimization pilot program, what are the main takeaways for industries who might adopt this technology? To ensure your work will be impactful, where possible we recommend co-developing projects with relevant stakeholders or reaching out to them early in the process for feedback. We encourage you to use this opportunity to do so!
• Outline key metrics: Quantitative or qualitative assessments of how well your results (or for proposals, anticipated results) compare to existing methods are encouraged. Try to give a sense of the importance of your problem and your findings. We encourage you to convey why the particular metrics you choose are relevant from a climate change perspective. For instance, if you are evaluating your machine learning model on the basis of accuracy, how does improved accuracy on a machine learning model translate to climate impact, and why is accuracy the best metric to use in this context?
• Be clear and concise: The discussion of impact does not need to be lengthy, just clear.
• Convey the big picture: Ultimately, the goal of Climate Change AI is to “empower work that meaningfully addresses the climate crisis.” Try to make sure that from the beginning, you contextualize your method and its impacts in terms of this objective.

Interactive Q&A

If you have further questions on how to participate in the workshop, you can ask those directly via the interactive Q&A session hosted on our community platform. You can also always contact us via email at climatechangeai.iclr2023@gmail.com. For recordings of informational webinars of previous editions of our workshop, please see here.

Organizers

Sasha Luccioni (Huggingface)
Konstantin Klemmer (Microsoft)
Simone Nsutezo Fobi (Microsoft)
Rasika Bhalerao (Northeastern University)
Utkarsha Agwan (UC Berkeley)
Marcus Voss (Birds on Mars, TU Berlin)
Olalekan Akintande (University of Ibadan)
Yoshua Bengio (Mila, Université de Montréal)

Tutorials Track Organizers

Shafat Rahman (Climate Change AI)
Isabelle Tingzon (Climate Change AI)
Melanie Hanna (DataRobot)

Mentors

Heather Couture (Pixel Scientia Labs)
Juan Francisco Venegas Gutierrez (Universidad Austral de Chile)
Fatma Tarlaci (OpenTeams)
Elie Alhajjar (USMA)
Sadid Hasan (Microsoft)
Alberto Costa Nogueira Junior (IBM Research)
Andrii Krutsylo (Polish Academy of Sciences)
Ying-Jung Chen Deweese (Descartes Labs)
Bharathan Balaji (Amazon)
James Doss-Gollin (Rice University)
Bertrand Le Saux (European Space Agency)
Sara Khalid (University of Oxford)
Yongli Zhu Texas (A&M University)
Ahmed Ragab (Natural Resources Canada/Polytechnique Montreal)
Anuroop Sriram (Meta AI )
Karagiannis Xenofon (Earth-i)
Dr Varvara Vetrova (University of Canterbury)
Jesse Nyokabi Quaise (Energy Africa)
Lamis Amer (University of Miami)
Dennis Wilson (ISAE-Supaero, University of Toulouse)
Komal Pradeep Dhoka (SICSR)

Program Committee

Alan Fortuny (Adidas)
Alberto Chapchap (GS Cap)
Alexander Pondaven (Imperial College London)
Alexandra Puchko (Kettle RE)
Alona Zharova (Humboldt University of Berlin)
Amarsagar Reddy Ramapuram Matavalam (Arizona State University)
amirmohammad naeini (York University)
Andreas Maier (Pattern Recognition Lab, FAU Erlangen-Nuremberg)
Aneesh Rangnekar (Memorial Sloan Kettering Cancer Center)
Anna Kwa (Allen Institute for Artificial Intelligence)
Antoine Blanchard (Verisk)
Ashwin Ramesh Babu (Hewlett Packard Enterprise Labs)
Bartosz Pieliński (University of Warsaw)
Bedartha Goswami (University of Tübingen)
Bertrand Le Saux (European Space Agency (ESA))
Brian Hutchinson (Western Washington University)
Chace Ashcraft (JHU/APL)
Charles Anderson (Colorado State University)
Christian Lessig (Otto-von-Guericke-Universitat Magdeburg)
Clayton Sanford (Columbia)
Damon Matthews (Concordia University)
Damon Wischik (Univeristy of Cambridge)
Dan Lu (Oak Ridge National Laboratory)
Danica Vukadinovic Greetham (Capgemini Engineering)
Daniel Salles Civitarese (IBM Research, Brazil)
Dario Augusto Borges Oliveira (Technische Universität München)
David Russell (Carnegie Mellon University)
Difan Zhang (PNNL)
Donghu Guo (Imperial College London)
DONNA VAKALIS (University of Toronto)
Eleanor Casas (Naval Postgraduate School)
Elham Kheradmand (University of Montreal)
Fred Otieno (IBM)
Frederik Gerzer (Recogni)
Gege Wen (Stanford University)
Hamid Alizadeh Pahlavan (Rice University)
Hao Sheng (Stanford University)
Hari Prasanna Das (UC Berkeley)
Henry Addison (University of Bristol)
Hovig Bayandorian ()
Isabelle Tingzon (Climate Change AI)
Jan Drgona (Pacific Northwest National Laboratory)
Jonathan Fürst (NEC Laboratories Europe)
Jorge Montalvo Arvizu (Solario)
Joris Guerin (LAAS-CNRS)
Joseph Early (University of Southampton)
Joyjit Chatterjee (University of Hull)
Julian de Hoog (The University of Melbourne)
Kaiser Olga (UNIversity)
Kate Duffy (BAER Institute / NASA)
Ken C. L. Wong (IBM Research – Almaden Research Center)
Kritika Gadpayle (CSTEP)
Kyle Bradbury (Duke University)
KYONGSIK YUN (California Institute of Technology)
Lucas Spangher (UC Berkeley)
Lukas Kondmann (German Aerospace Center)
Mahdi Torabi Rad (Beyond Limits)
Manmeet Singh (The University of Texas at Austin)
Marc Rußwurm (École Polytechnique Fédérale de Lausanne)
Marcel Hussing (University of Pennsylvania)
Maria João Sousa (IDMEC, Instituto Superior Técnico, Universidade de Lisboa)
Mark Roth (Oregon State University)
Markus Leippold (University of Zurich)
Markus Zechner (Stanford University)
Massimo Bollasina (University of Edinburgh)
Matias Quintana (National University of Singapore)
Matteo Turchetta (ETH Zurich)
Matthias Hertel (KIT)
Mayank Jain (University College Dublin)
Melanie Hanna (Climate Change AI)
Milan Jain (PNNL)
Mohamed Elhabashy (MIT)
Muhammad Kasim (University of Oxford)
Nahian Ahmed (Oregon State University)
Niccolo Dalmasso (J.P. Morgan Chase)
Nicole Ludwig (University of Tübingen)
Noman Bashir (University of Massachusetts Amherst)
Norhan Bayomi (MIT Environmental Solutions Initiative)
Paul Griffiths (National Centre for Atmospheric Science, Cambridge University)
Peer Nowack (Karlsruhe Institute of Technology)
Peetak Mitra (Excarta)
Philip Popien (Floodbase)
Qiao Kang (Memorial University)
Raghul Parthipan (University of Cambridge)
Rambod Mojgani (Rice University)
Redouane Lguensat (IPSL)
Rishikesh Ranade (Ansys Inc)
Robin Dunn (Novartis)
Rodrigo Rene Rai Munoz Abujder (Johns Hopkins Applied Physics Laboratory)
Ruben Cartuyvels (KU Leuven)
Sam Silva (The University of Southern California)
Samarth Vadia (LMU Munich)
Sara El Mekkaoui (EMI Engineering School)
Sebastian Ruf (Northeastern University)
Shahine Bouabid (University of Oxford)
Shannon Lloyd (Concordia University)
Shiheng Duan (Lawrence Livermore National Laboratory)
Shruti Kulkarni (Indian Institute of Science)
Simiao Ren
Siming Bayer (Pattern Recognition Lab, Friedrich-Alexander University)
Simon Letzgus (Technische Universität Berlin)
So Takao (UCL)
Subhashis Hazarika (Palo Alto Research Center)
Sudipan Saha (Indian Institute of Technology Delhi)
Swati Sharma (Microsoft Research)
Tarek Alskaif (Wageningen University)
Themis Sapsis (MIT)
Thomas Walther (Utrecht University)
Tianle Yuan (NASA)
Tongxin Li (The Chinese University of Hong Kong (Shenzhen))
Veruska Muccione (University of Zurich)
Victoria Preston (WHOI)
Vili Hätönen (Emblica)
Yanru Zhang (University of Electronic Science and Technology of China)
Yimeng Min (Cornell University)
Ying-Jung Deweese (Descartes Labs / Georgia Insititute of Technology)
Zhecheng Wang (Stanford University)
Zikri Bayraktar (Schlumberger Doll Research)
Zoltan Nagy (The University of Texas at Austin)
David Rolnick (McGill University, Mila)
Evan Sherwin (Stanford University, Energy and Resources Engineering)
Hari Prasanna Das (UC Berkeley)
Katarzyna B. Tokarska (ETH Zurich)
Kevin McCloskey (Google)
Kris Sankaran (University of Wisconsin-Madison)
Maria João Sousa (IDMEC, Instituto Superior Técnico, Universidade de Lisboa)
Meareg Hailemariam (Addis Ababa University)
Olivia Mendivil Ramos (CSHL)
Peetak Mitra (Palo Alto Research Center)
Priya Donti (Climate Change AI)
Shafat Rahman (Climate Change AI)

Mentorship Program

We are hosting a mentorship program to facilitate exchange between potential workshop submitters and experts working in topic areas relevant to the workshop. The goal of this program is to foster cross-disciplinary collaborations and ultimately increase the quality and potential impact of submitted work.

Expectations:

Mentors are expected to guide mentees during the CCAI mentorship program as they prepare submissions for this workshop.

Examples of mentor-mentee interactions may include:

• In-depth discussion of relevant related work in the area of the Paper or Proposal, to ensure submissions are well-framed and contextualized in terms of prior work.
• Iterating on the core idea of a Proposal to ensure that the climate change application is well-posed and the ML techniques used are well-suited.
• Giving feedback on the writing or presentation of a Paper or Proposal to bring it to the right level of maturity for submission.

Mentees are expected to initiate contact with their assigned mentor and put in the work and effort necessary to prepare a Paper or Proposal submission by Feb 10.

We suggest that after the mentor-mentee matching is made, a first (physical or digital) meeting should take place within the first week (Jan 10-17) to discuss the Paper or Proposal and set expectations for the mentorship period. Subsequent interactions can take place either through meetings or via email discussions, following the expectations set during the initial meeting, culminating in a final version of a Paper or Proposal submitted via the CMT portal by Feb 10.

Mentors and mentees must abide by the following Code of Conduct: https://www.climatechange.ai/code_of_conduct.

Application

Applications are due by Jan 10. We will post a link with the mentor / mentee application forms shortly.

• Application to be a mentee: https://forms.gle/kpuJVemDveiu7YgN9
• Application to be a mentor: https://forms.gle/6rrgxnyW6igXKt219

Sponsors

If you want to support this workshop as a sponsor, please reach out to climatechangeai.iclr2023@gmail.com and access our request for sponsorship here.

Frequently Asked Questions

Mentorship Program FAQ

Q: Are mentors allowed to be authors on the paper for which they provided mentorship?
A: Yes, mentors can be co-authors but not reviewers.

Q: What happens if the mentor/mentee does not fulfill their duties, or if major issues come up?
A: Please email us at climatechangeai.iclr2023@gmail.com and we will do our best to help resolve the situation. Potential breaches of the Code of Conduct will be responded to promptly as detailed therein.

Q: What happens if I apply to be a mentee but do not get paired with a mentor?
A: While we will do our best, we cannot guarantee pairings for everyone. Even if you do not get paired with a mentor, we encourage you to submit a Paper or Proposal to the workshop, and our reviewers will provide you with guidance and feedback on how to improve it.

Q: What happens if my submission does not get accepted to the workshop?
A: While the mentorship program is meant to give early-career researchers and students the opportunity to improve the quality of their work, sometimes submissions will need further polishing and elaboration before being ready for presentation at a CCAI workshop. If this is the case, we invite you to take into account the comments made by the reviewers and to resubmit again to a subsequent CCAI workshop.

Q: I cannot guarantee that I can commit at least 4 hours to the program over the time period. Should I still apply as a mentor?
A: No. While the 4 hour time commitment is a suggestion, we do believe that it is necessary to ensure that all mentees receive the help and guidance they need.

Q: I do not have a background in machine learning; can I still apply to be a mentor/mentee?
A: Yes! We welcome applications from domains that are complementary to machine learning to solve the problems that we are targeting.

Q: What happens if my mentor/mentee wants to continue meeting after the workshop?
A: We welcome and encourage continued interactions after the official mentorship period. That said, neither the mentor nor the mentee should feel obligated to maintain contact.

Submission FAQ

Q: How can I keep up to date on this kind of stuff?
A: Sign up for our mailing list!

Q: I’m not in machine learning. Can I still submit?
A: Yes, absolutely! We welcome submissions from many fields. Do bear in mind, however, that the majority of attendees of the workshop will have a machine learning background; therefore, other fields should be introduced sufficiently to provide context for the work.

Q: What if my submission is accepted but I can’t attend the workshop?
A: You may ask someone else to present your work in your stead.

Q: It’s hard for me to fit my submission on 3 or 4 pages. What should I do?
A: Feel free to include appendices with additional material (these should be part of the same PDF 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 CMT website to make submissions.

Q: The submission website is asking for my name. Is this a problem for anonymization?
A: You should fill out your name and other info when asked on the submission website; CMT will keep your submission anonymous to reviewers.

Q: Do submissions for the Proposals track need to have experimental validation?
A: No, although some initial experiments or citation of published results would strengthen your submission.

Q: The submission website never sent me a confirmation email. Is this a problem?
A: No, the CMT system does not send automatic confirmation emails after a submission, though the submission should show up on the CMT page once submitted. If in any doubt regarding the submission process, please contact the organizers. Also please avoid making multiple submissions of the same article to CMT.

Q: Can I submit previously published work to this workshop?
A: Yes, though under limited circumstances. In particular, work that has previously been published at non-machine learning venues may be eligible for submission; however, work that has been published in conferences on machine learning or related fields is likely not eligible. If your work was previously accepted to a Climate Change AI workshop, this work should have changed or matured substantively to be eligible for resubmission. Please contact climatechangeai.iclr2023@gmail.com with any questions.

Q: Can I submit work to this workshop if I am also submitting to another ICLR 2023 workshop?
A: Yes. We cannot, however, guarantee that you will not be expected to present the material at a time that conflicts with the other workshop.