These files contain main source codes and datasets for the neural network (NN) radiation emulator (Song and Roh, 2021) as well as the compound parameterization (CP) of the NN emulator (Song et al., 2021). Song, H.-J., & Roh, S. (2021). Improved weather forecasting using neural network emulation for radiation parameterization. Journal of Advances in Modeling Earth Systems, 13, e2021MS002609, https://doi.org/10.1029/2021MS002609. Song, H.-J., Roh, S., & Park, H. (2021). Compound parameterization to improve the accuracy of radiation emulator in a numerical weather prediction model. Geophysical Research Letters, 48, e2021GL095043, https://doi.org/10.1029/2021GL095043. Also, you can download the "tr.tar: training sets for NN radiation emulator and CP" and "met.tar: WPS metgrid files based on ERA5 reanalysis data". Monthly separated datasets are available in other Zenodo pages. See readme (in src.zip) for more information. tr.tar (339GB): https://drive.google.com/file/d/1BIIzU6KdSKj6i1pFdgCayTiwrHuQUApo/view?usp=sharing met.tar (289GB): https://drive.google.com/file/d/14z9jVHDSAn8xr7yaWXhHH4S6Ctmreeio/view?usp=sharing January (31GB): https://doi.org/10.5281/zenodo.5528570 Februray (31GB): https://doi.org/10.5281/zenodo.5528591 March (31GB): https://doi.org/10.5281/zenodo.5529238 April (31GB): https://doi.org/10.5281/zenodo.5529244 May (31GB): https://doi.org/10.5281/zenodo.5529254 June (31GB): https://doi.org/10.5281/zenodo.5529256 July (31GB): https://doi.org/10.5281/zenodo.5529262 August (31GB): https://doi.org/10.5281/zenodo.5529268 September (31GB): https://doi.org/10.5281/zenodo.5529272 October (31GB): https://doi.org/10.5281/zenodo.5529274 November (31GB): https://doi.org/10.5281/zenodo.5529276 December (31GB): https://doi.org/10.5281/zenodo.5529280