paper
2022
Hybrid physics-ML & parameterization
New model or method
Physics-informed / physics-constrainedRNN / LSTM / ConvLSTMAlibaba (DAMO Academy)Nanjing University of Information Science & Technology (NUIST) Other
2022-08-18
022
Aug 2022
Yichen Yao, Xiaohui Zhong, Yongjun Zheng et al.
preprint
Alibaba (DAMO Academy), Nanjing University of Information Science & Technology (NUIST)
Physics-incorporated network enforces energy conservation between fluxes and heating rates for fast radiative transfer emulation; Bi-LSTM performs best among tested architectures.
Hybrid physics-ML & parameterization
Physics-Incorporated Framework for Emulating Atmospheric Radiative Transfer and the Related Network Study
In one sentence. Physics-incorporated network enforces energy conservation between fluxes and heating rates for fast radiative transfer emulation; Bi-LSTM performs best among tested architectures.
Labels
- Topic
- Hybrid physics-ML & parameterization
- Type
- New model or method
- Method
- Physics-informed / physics-constrained, RNN / LSTM / ConvLSTM
- Data
- NWP analysis or forecasts (IFS, GFS, ...), Other
- Status
- Research
- Identifiers
- DOI:10.1002/essoar.10512196.1 OpenAlex:W4302081191
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.