Predictability and feedbacks of the ocean-soil-plant-atmosphere water cycle: deep learning water conductance in Earth System Model
- Argonne National Lab. (ANL), Argonne, IL (United States)
- Univ. of Illinois, Chicago, IL (United States)
- Univ. of Chicago, IL (United States)
- Phymea Systems, Montpellier (France)
This white paper responds to Focal Area 2. We seek to build predictive models of leaf and surface conductance of water by implementing deep learning (DL) data assimilation techniques. These new models would then be implemented in existing Land Surface Models (LSMs) and Earth System models (ESMs), generating novel water cycle feedbacks. In doing so, we would improve predictability of expected changes in land precipitation, soil moisture, and vegetation dynamics in the long-term, and the role of land cover on the impacts and feedbacks of extreme weather events in the short-term
- Research Organization:
- Argonne National Lab. (ANL), Argonne, IL (United States); Univ. of Illinois, Chicago, IL (United States); Univ. of Chicago, IL (United States): Phymea Systems, Montpellier (France)
- Sponsoring Organization:
- USDOE Office of Science (SC), Biological and Environmental Research (BER)
- OSTI ID:
- 1769763
- Report Number(s):
- AI4ESP1112
- Country of Publication:
- United States
- Language:
- English
Similar Records
Integrated parameter and process learning for hydrologic and biogeochemical modules in Earth System Models
Computationally Tractable High-Fidelity Representation of Global Hydrology in ESMs via Machine Learning Approaches to Scale-Bridging
Hybridizing Machine Learning and Physically-based Earth System Models to Improve Prediction of Multivariate Extreme Events (AI Exploration of Wildland Fire Prediction)
Technical Report
·
Thu Apr 15 00:00:00 EDT 2021
·
OSTI ID:1769763
Computationally Tractable High-Fidelity Representation of Global Hydrology in ESMs via Machine Learning Approaches to Scale-Bridging
Technical Report
·
Thu Apr 15 00:00:00 EDT 2021
·
OSTI ID:1769763
+4 more
Hybridizing Machine Learning and Physically-based Earth System Models to Improve Prediction of Multivariate Extreme Events (AI Exploration of Wildland Fire Prediction)
Technical Report
·
Thu Apr 15 00:00:00 EDT 2021
·
OSTI ID:1769763