Machine learning for climate systems



How to model the world with data-hungry methods. How to think our way out of climate crisis/

ML for climate drivers

  • ESA - Trio of Sentinel satellites map methane super-emitters

    In a recent paper published in Remote Sensing of Environment (Schuit et al. 2023), researchers from SRON found that the Sentinel-3 satellites can retrieve methane enhancements from its shortwave infrared band measurements. Impressively, it can detect the largest methane leaks of at least 10 tonnes per hour, depending on factors like location and wind conditions, every single day.

    See also Pandey et al. (2023).

ML for climate solutions

Jeff Dean’s NeurIPS 2019 talk suggests ideas. His talk is an advertisement for tensorflow probability as a solution for machine learning for physics simulations for making nuclear fusion feasible etc.

References

Australian Information Industry Association. 2023. β€œTech and Sustainability.”
Pandey, Sudhanshu, Maarten van Nistelrooij, Joannes D. Maasakkers, Pratik Sutar, Sander Houweling, Daniel J. Varon, Paul Tol, David Gains, John Worden, and Ilse Aben. 2023. β€œDaily Detection and Quantification of Methane Leaks Using Sentinel-3: A Tiered Satellite Observation Approach with Sentinel-2 and Sentinel-5p.” Remote Sensing of Environment 296 (October): 113716.
Rolnick, David, Priya L. Donti, Lynn H. Kaack, Kelly Kochanski, Alexandre Lacoste, Kris Sankaran, Andrew Slavin Ross, et al. 2019. β€œTackling Climate Change with Machine Learning.” arXiv:1906.05433 [Cs, Stat], November.
Schiermeier, Quirin. 2018. β€œDroughts, Heatwaves and Floods: How to Tell When Climate Change Is to Blame.” Nature 560 (7716): 20–22.
Schuit, Berend J., Joannes D. Maasakkers, Pieter Bijl, Gourav Mahapatra, Anne-Wil van den Berg, Sudhanshu Pandey, Alba Lorente, et al. 2023. β€œAutomated detection and monitoring of methane super-emitters using satellite data.” Atmospheric Chemistry and Physics 23 (16): 9071–98.

No comments yet. Why not leave one?

GitHub-flavored Markdown & a sane subset of HTML is supported.