Workshop description

This workshop aims to highlight work being done at the intersection of AI and the Earth and Space Sciences, with a special focus on model interpretability at the ICLR 2022 iteration of the workshop.

We showcase cutting-edge applications of machine learning to Earth and space science problems from diverse fields, including, but not limited to: atmospheric science, ecology and evolutionary biology, effects of environmental change on human health, geoscience, human-earth interaction, hydrology, sensors and sampling, and planetary science.

We also cultivate areas where Earth and planetary science is informing and inspiring new developments in AI, including theoretical developments in interpretable AI models, hybrid models with knowledge-guided AI, augmenting physics-based models with AI, representation learning from graphs and manifolds in spatiotemporal models, and dimensionality reduction. New Earth and planetary science datasets and visualizations that will enable faster integration of AI into the Earth and space sciences are also of particular interest. The workshop will highlight the following contributions in special sessions:

Please see the ICLR website for details on registering for this and other workshops at ICLR. The ICLR registration fee is 50 USD for students and 100 USD for non-students.

Information for the day of the workshop

General:

To watch the workshop: the event is live streamed via the ICLR workshop page Please do not join the Zoom room unless you are an author participating in the Q&A period for your session.

Asking questions during a Q&A or panel discussion: please ask via Rocket Chat or our workshop Slack channel. Session moderators will be continually looking for questions from the audience and relaying them to speakers.

Poster session: join the Gathertown poster room. Note: you will need to navigate either to the poster session (to see posters) or the breakout room (meet and chat with other workshop participants).

Breakout rooms: after each session, there will be a GatherTown breakout room where you can meet, chat, and network with other participants who attended your the session. We heartily encourage you to check out your session's breakout room after the Q&A.

For authors:

Exactly one author from each paper should be present at the Zoom Q&A session, which will be livestreamed. Please be sure to check-in well in advance (recommended 30-60 min ahead of time), to make sure your mic and video are working properly.

Important dates

AI4Earth Workshop at ICLR2022
Submission deadline: February 26 28, 2022 at 12:00 AM UTC (anywhere on earth) via CMT
Author notifications: March 26, 2022
Meeting: April 29, 2022

ICLR2022
Registration opens: February 2, 2022 at 2:00 PM UTC via ICLR website
Meeting: April 25 - 29, 2022

Submission instructions

We are accepting two forms of submissions: papers and posters. All submissions are due via CMT by Feb '22 12:00 AM UTC (anywhere on earth). Please anonymize your submissions as indicated in the ICLR submission instructions.

Paper submissions: To format your paper for submission please use the main conference LaTeX style files. The workshop has a strict maximum page limit of 5 pages for the main text and 3 pages for the supplemental text. Citations may use additional, unlimited pages.

Poster submissions: Please submit an abstract for consideration. While there is no page restriction on the abstract, concise submissions are encouraged. Explanatory figures are welcome.

Please note that ICLR policy states: "Workshops are not a venue for work that has been previously published in other conferences on machine learning. Work that is presented at the main ICLR conference should not appear in a workshop."

To see examples of successful past submissions see NeurIPS2020 and ICLR2020.

For questions, please contact us at ai4earthscience [at] gmail [dot] com or contact us on our slack