Hybrid physics-ML & parameterization
Neural Network Radiation Scheme
In one sentence. Releases code and training data for a neural network radiation scheme in the WRF model, developed with stochastic weight averaging for numerical weather prediction.
Abstract
These files contain main source codes and datasets for developing neural network radiation scheme for the WRF model. The Ideal and real case simulations were seperated. Reference: Song, H.-J., Roh, S., Lee, J., Nam, G., Yun, E., Yoon, J., & Kim, P. S. (2022). Benefits of stochastic weight averaging in developing neural network radiation scheme for numerical weather prediction. Journal of Advances in Modeling Earth Systems, 14, e2021MS002921. https://doi.org/10.1029/2021MS002921 Training and validation sets are given in following links: January: https://doi.org/10.5281/zenodo.5530472 February: https://doi.org/10.5281/zenodo.5634729 March: https://doi.org/10.5281/zenodo.5634731 April: https://doi.org/10.5281/zenodo.5634733 May: https://doi.org/10.5281/zenodo.5634735 June: https://doi.org/10.5281/zenodo.5634737 July: https://doi.org/10.5281/zenodo.5636127 August: https://doi.org/10.5281/zenodo.5636129 September: https://doi.org/10.5281/zenodo.5636131 October: https://doi.org/10.5281/zenodo.5636134 November: https://doi.org/10.5281/zenodo.5636136 December: https://doi.org/10.5281/zenodo.5636138
Labels
- Topic
- Hybrid physics-ML & parameterization
- Type
- New model or method
- Method
- Other
- Domain
- Regional
- Data
- Other
- Status
- Research
- Identifiers
- DOI:10.5281/zenodo.5638435 OpenAlex:W4226160182
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.