paper
2026
Hybrid physics-ML & parameterization
Explainability, uncertainty & physics New model or method
Classical ML (trees, GP, linear, kernels)Columbia University (LEAP, Lamont-Doherty)Lawrence Berkeley National Laboratory / NERSCNASA Other
2026-07-30
051
Jul 2026
Jennifer Nicole Paige, Peter Caldwell, Hassan Beydoun et al.
preprint
Columbia University (LEAP, Lamont-Doherty), Lawrence Berkeley National Laboratory / NERSC, NASA
A Gaussian process surrogate calibrates SCREAM cloud parameters from a 153-member ensemble, cutting bias by more than 20% in 2-day simulations.
Hybrid physics-ML & parameterization
Machine Learning for Optimized Tuning of the Simple Cloud-Resolving Earth Atmosphere Model (SCREAM)
In one sentence. A Gaussian process surrogate calibrates SCREAM cloud parameters from a 153-member ensemble, cutting bias by more than 20% in 2-day simulations.
Labels
- Topic
- Hybrid physics-ML & parameterization, Explainability, uncertainty & physics
- Type
- New model or method
- Method
- Classical ML (trees, GP, linear, kernels)
- Domain
- Global
- Data
- km-scale or high-res simulation
- Status
- Research
- Identifiers
- DOI:10.22541/essoar.15006793/v1 OpenAlex:W7171787501
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.