Primary Convener:
Yalan Song, Pennsylvania State University Main Campus

Convener:
Wei Zhi, Hohai University
Allison Goodwell, Prairie Research Institute at University of Illinois at Urbana-Champaign
Shuyu Chang, The Pennsylvania State University
Jonathan Frame, University of Alabama
Tadd Bindas, ERT
Rebecca Herman, Columbia University of New York
Mohammed Ombadi, University of Michigan Ann Arbor
Frederick Cheng, Colorado State University

Chair:
Rebecca Herman, Columbia University of New York
Mohammed Ombadi, University of Michigan Ann Arbor
Frederick Cheng, Colorado State University
Tadd Bindas, ERT
Wei Zhi, Hohai University
Shuyu Chang, The Pennsylvania State University

This session explores the integration of big data and machine learning with physics in geosciences, addressing both the challenges and opportunities of applying AI/ML in the field. While the proliferation of 'Big Data' offers unprecedented opportunities, the hydrology community faces the challenge of developing and refining physical theories that complement and keep pace with the predictive capabilities of AI/ML (Nearing et al., 2021). We focus on: (1) development and harmonization of large-scale datasets, (2) reconciling observations with theory, (3) integrating/discovering theory through AI/ML, (4) diagnosing or detecting model misspecification/errors, (5) causal methods developments, applications, or counterfactual approaches that study environmental systems and how they respond to climate change or perturbations, and (6) physically-based or machine learning model studies with a focus on causality, explainability, functional performance, or process representations. We highlight the submissions from early-career researchers at all stages to foster collaboration, innovation, and in-depth discussions within the community.

Index Terms
0555 Neural networks, fuzzy logic, machine learning
1847 Modeling
1873 Uncertainty assessment
4475 Scaling: spatial and temporal

Cross-Listed:
NG - Nonlinear Geophysics
B - Biogeosciences

Suggested Itineraries:
Machine Learning and AI

Neighborhoods:
3. Earth Covering