-
- NG21B-0386: A Physics-Informed Auto-Learning Framework under Partial Observations, with Applications to Developing Stochastic Conceptual Models
-
Board 0386‚ Hall EFG (Poster Hall)NOLA CC
Author(s):Generic 'disconnected' Message
Yinling Zhang, University of Wisconsin Madison (First Author, Presenting Author)
Nan Chen, University of Wisconsin-Madison
Xianghui Fang, Fudan University
Jérome Vialard, LOCEAN-IPSL, CNRS-IRD-MNHN-Sorbonne Université
This study develops a physics-informed auto-learning approach to improve the modeling and understanding of El Niño–Southern Oscillation (ENSO), a major climate phenomenon influencing global weather and climate. The auto-learning framework explores the causality between key processes to systematically produce stochastic conceptual models with different climate factors that simulate the diversity of observed ENSO events. The key finding is that the minimal model for characterizing the ENSO diversity (with the least number of climate factors) is a four-variable model capturing thermocline depth, sea surface temperatures, and wind bursts that can reproduce intensity and spatial pattern variation. This advancement provides an interpretable tool to identify the minimum sufficient processes governing ENSO behavior for improved predictability.
Scientific DisciplineSuggested ItinerariesNeighborhoodType
Enter Note
Go to previous page in this tab
Session
