Presenters-0677: Difference between revisions
From CSDMS
Created page with "{{Presenters temp |CSDMS meeting event title=CSDMS 2025: Exploring Earth's Surface with Models, Data & AI |CSDMS meeting event year=2025 |CSDMS meeting presentation type=Invited oral presentation |CSDMS meeting first name=Yalan |CSDMS meeting last name=Song |CSDMS meeting institute=Penn State University |Country member=United States |CSDMS meeting state=Pennsylvania |CSDMS meeting email address=songyalan1@gmail.com |CSDMS meeting title presentation=High-Resolution Differ..." |
No edit summary |
||
| Line 13: | Line 13: | ||
{{Presenters presentation | {{Presenters presentation | ||
|CSDMS meeting abstract presentation=Continental and global water models have long been trapped in slow growth and inadequate predictive power, as they are not able to effectively assimilate information from big data. While Artificial Intelligence (AI) models greatly improve performance, purely data-driven approaches do not provide strong enough interpretability and generalization. One promising avenue is “differentiable” modeling that seamlessly connects neural networks with physical modules and trains them together to deliver real-world benefits in operational systems. Differentiable modeling (DM) can efficiently learn from big data to reach state-of-the-art accuracy while preserving interpretability and physical constraints, promising superior generalization ability, predictions of untrained intermediate variables, and the potential for knowledge discovery. Here we demonstrate the practical relevance of a high-resolution, multiscale water model for operational continental-scale and global-scale water resources assessment. (https://bit.ly/3NnqDNB). Not only does it achieve significant improvements in streamflow simulation compared to the established national- and global water models, but it also produces much more reliable depictions of interannual changes in large river streamflow, freshwater inputs to estuaries, and groundwater recharge. As a related topic, we also showcase the value of foundation AI for global environmental change and its benefits for resource management. | |CSDMS meeting abstract presentation=Continental and global water models have long been trapped in slow growth and inadequate predictive power, as they are not able to effectively assimilate information from big data. While Artificial Intelligence (AI) models greatly improve performance, purely data-driven approaches do not provide strong enough interpretability and generalization. One promising avenue is “differentiable” modeling that seamlessly connects neural networks with physical modules and trains them together to deliver real-world benefits in operational systems. Differentiable modeling (DM) can efficiently learn from big data to reach state-of-the-art accuracy while preserving interpretability and physical constraints, promising superior generalization ability, predictions of untrained intermediate variables, and the potential for knowledge discovery. Here we demonstrate the practical relevance of a high-resolution, multiscale water model for operational continental-scale and global-scale water resources assessment. (https://bit.ly/3NnqDNB). Not only does it achieve significant improvements in streamflow simulation compared to the established national- and global water models, but it also produces much more reliable depictions of interannual changes in large river streamflow, freshwater inputs to estuaries, and groundwater recharge. As a related topic, we also showcase the value of foundation AI for global environmental change and its benefits for resource management. | ||
|CSDMS meeting youtube code= | |CSDMS meeting youtube code=xEwbeh90UHk | ||
|CSDMS meeting participants=0 | |CSDMS meeting participants=0 | ||
}} | }} | ||
Revision as of 08:36, 22 May 2025
CSDMS 2025: Exploring Earth's Surface with Models, Data & AI
High-Resolution Differentiable Models for Operational National and Global Water Modeling and Assessment
Abstract
Continental and global water models have long been trapped in slow growth and inadequate predictive power, as they are not able to effectively assimilate information from big data. While Artificial Intelligence (AI) models greatly improve performance, purely data-driven approaches do not provide strong enough interpretability and generalization. One promising avenue is “differentiable” modeling that seamlessly connects neural networks with physical modules and trains them together to deliver real-world benefits in operational systems. Differentiable modeling (DM) can efficiently learn from big data to reach state-of-the-art accuracy while preserving interpretability and physical constraints, promising superior generalization ability, predictions of untrained intermediate variables, and the potential for knowledge discovery. Here we demonstrate the practical relevance of a high-resolution, multiscale water model for operational continental-scale and global-scale water resources assessment. (https://bit.ly/3NnqDNB). Not only does it achieve significant improvements in streamflow simulation compared to the established national- and global water models, but it also produces much more reliable depictions of interannual changes in large river streamflow, freshwater inputs to estuaries, and groundwater recharge. As a related topic, we also showcase the value of foundation AI for global environmental change and its benefits for resource management.
Please acknowledge the original contributors when you are using this material. If there are any copyright issues, please let us know (CSDMSweb@colorado.edu) and we will respond as soon as possible.
Of interest for:
