Skip to the content.

AI for Earth Sciences

Earth sciences or geosciences encompasses understanding the physical characteristics of our planet, including its lithosphere, hydrosphere, atmosphere and biosphere, applying all fields of natural and computational sciences. As Earth sciences enters the era of increasing volumes and variety of geo-scientific data from sensors, as well as high performance computing simulations, machine learning methods are poised to augment and in some cases replace traditional methods. Interest in the application of machine learning, deep learning, reinforcement learning, computer vision and robotics to the geosciences is growing rapidly at major Earth science and machine learning conferences.

Our workshop seeks to bring cutting edge geoscientific and planetary challenges to the fore for the machine learning and deep learning communities. We seek machine learning interest from major areas encompassed by Earth sciences which include, atmospheric physics, hydrologic sciences, cryosphere science, oceanography, geology, planetary sciences, space weather, geo-health (i.e. water, land and air pollution), volcanism, seismology and biogeosciences.

!!Latest Updates!!

Due to concerns about COVID-19, #ICLR2020 will cancel its physical conference this year, and instead host a fully virtual conference: We will send specific details to accepted workshop participants soon, but it is expected that these will be quite similar to the virtual format of the main conference.

Seeking Partnerships & Sponsors
We are interested in hearing from philanthropies, companies, governments, entrepreneurs and volunteers interested in supporting AI for Earth Sciences workshop, attendees, datasets, competitions, related research and development activities.

Topics of Interest

We call for papers demonstrating novel machine learning techniques in remote sensing for meteorology and geosciences, generative Earth system modeling, and transfer learning from geophysics and numerical simulations and uncertainty in Earth science learning representations.

We also seek theoretical developments in interpretable machine learning in meteorology and geoscientific models, hybrid models with Earth science knowledge guided machine learning, representation learning from graphs and manifolds in spatiotemporal models and dimensionality reduction in Earth sciences.

In addition, we seek Earth science applications from vision, robotics and reinforcement learning. New labelled Earth science datasets and visualizations with machine learning is also of particular interest.

Submission Instructions

There are two tracks for workshop submission:

1) Full Paper submission: 3-6 pages excluding references and supplementary materials. Papers are encouraged to use ICLR Format. We also welcome dataset labeling papers submitted as a 3 page proposal as described in AI4Earth

2) Abstract-Only submission: 300 word limit (AGU/EGU style abstract)

Submissions may be made on Microsoft CMT. If new to Microsoft CMT, register a username and password at and submit to our workshop which is listed as AI4ESICLR2020. E-mail us at ai4earthscience[at]gmail[dot]com if you have issues with the submission process. Post-acceptance, ICLR workshop registration is needed for attendance if you are not awarded a travel grant, but one need not register to attend the entire conference.

Important Dates

21 Jan 2020 - ICLR Registration opens
14 Feb 2020 - Full Paper Extended Deadline
14 Feb 2020 - Abstract-Only Deadline

(Rolling evaluation period)
25 Feb 2020 - Acceptance Notifications
26 April 2020 - Workshop Date

Deadlines are at 11:59 PST (California time) of date listed.


This full day workshop will include keynotes, invited talks, regular talks, spotlight talks, selective remote talks for individuals with travel restrictions, and a panel discussion with a mix of keynote speakers and organisers with audience Q/A. Posters will be available throughout the day and in a dedicated viewing session.

Organizing Committee

S. Karthik Mukkavilli, Postdoc at Mila
Aaron Courville, Associate Professor at Mila and Université de Montréal
Kelly Kochanski, PhD Candidate at CU Boulder
Johanna Hansen, PhD Candidate at McGill University

Steering Committee

Vipin Kumar, Chaired Professor at Minnesota in Computer Science and Engineering
Gregory Dudek, Chaired Professor at McGill School of Computer Science
Pierre Gentine, Associate Professor of Earth and Environmental Engineering, Columbia University
Mary C Hill, Professor of Geology at University of Kansas
Trooper Sanders, CEO at Benefits Data Trust
Chad Frischmann, VP & Research Director at Drawdown
Paul D. Miller, aka DJ Spooky

Program Committee

Atalay Ayele (Addis Ababa University)
Auroop Ganguly (Northeastern)
Philippe Tissot (Texas A & M)
Amy McGovern (University of Oklahoma)
David Gagne (NCAR)
Ashley Pilipiszyn (Stanford and OpenAI)
David Meger (McGill)
Karthik Kashinath (Berkeley Lab)
Christiane Jablonowski (University of Michigan)
Daniel Fuka (Virginia Tech)
Julien Brajard (NERSC/Sorbonne University)
Udit Bhatia (IIT Gandhinagar)
Redouane Lguensat (CNES/Universite Grenoble Alpes)
Victor Schmidt (Mila)
Tom Beucler (UC Irvine)
Aven-Satre Meloy (Oxford)
Agnieszka Słowik (Cambridge)

Contact Us

Send inquiries to ai4earthscience[at]gmail[dot]com