Data Analytics and Machine Learning Innovation for Climate and Earth Surface Processes

Earth observations and climate model outputs are witnessing an unprecedented increase in data volume, opening up new opportunities to advance physical understanding, improve earth system modeling, and increase predictive ability of weather, climate and earth surface processes at a range of scales. Mining these data for new knowledge presents also new challenges and opportunities to the data science community instigating the development or adaptation of tools from mathematics, statistics, and computer science for the problems at hand. Topics of special interest include identifying causal sources of predictability, quantifying and attributing climate variability and change, improving micro-scale parameterizations in climate models, and deciphering landscape response to change. This session will bring together ocean and atmospheric scientists, hydrologists, geomorphologists, and data scientists to critically debate challenges and opportunities in the era of big data and the wave of machine learning for advancing climate and earth system modeling.

Type
Oral

Primary Convener
Efi Foufoula-Georgiou
University of California Irvine

Conveners
James Tremper Randerson
University of California Irvine

Jean Braun
Helmholtz Centre Potsdam GFZ German Research Centre for Geosciences

Alejandro Tejedor
Max Planck Institute for the Physics of Complex Systems
University of California Irvine

Chairs
Efi Foufoula-Georgiou
University of California Irvine

James Tremper Randerson
University of California Irvine

Alejandro Tejedor
Saint Anthony Falls Laboratory

[PaulPukite]

At 1:09 the symbolic regression tool Eureqa that Schmidt developed is no longer available.