Input data for gclien-isa

# Input data for gclien-isa: static features and XGBoost bias-correction models This archive contains the input data needed to run **gclien-isa**. gclien-isa downscales0.5° meteorology (WFDE5 v2.1 or ISIMIP3b) to a 0.05° global grid. It then applies anXGBoost bias correction and computes air temperature and WBGT. This archive contains: - `gridX/`: static feature files on the global 0.05° grid (NetCDF)- `xgb_models/`: trained XGBoost models used for the bias correction (JSON). The dew point model is not used by the current version of the software. The meteorological forcing (WFDE5 v2.1 or ISIMIP3b) is not included. - Software: https://github.com/nies-gsia/gclien-isa ## Status As of November 2, 2026, the algorithms, code and data in this archive have not beenpeer-reviewed. They should be regarded as preliminary and may change in later versions. ## Usage Extract the archive into the `input/` directory of the gclien-isa repository, so that`input/gridX/` and `input/xgb_models/` exist. See the software README for details. ## Data sources The static features were calculated from the datasets listed in [References](#references).The XGBoost models were trained using these features and station observations from the NOAAIntegrated Surface Database (ISD). Please also cite these datasets when you use this archive. Contains modified Copernicus Climate Change Service information 2026. Neither the EuropeanCommission nor ECMWF is responsible for any use that may be made of the Copernicusinformation or data it contains. ## Licence This archive is licensed under the Creative Commons Attribution 4.0 International licence(CC BY 4.0): https://creativecommons.org/licenses/by/4.0/ ## Disclaimer The data are provided "as is", without warranty of any kind, express or implied, includingbut not limited to the warranties of accuracy, completeness, merchantability and fitness fora particular purpose. In no event shall the authors or the National Institute forEnvironmental Studies (NIES) be liable for any claim, damages or other liability arising from the use of the data. ## References - Amante, C. and Eakins, B. W. (2009). ETOPO1 1 Arc-Minute Global Relief Model: Procedures, Data Sources and Analysis. NOAA Technical Memorandum NESDIS NGDC-24. https://doi.org/10.7289/V5C8276M- Copernicus Climate Change Service (2020). Near surface meteorological variables from 1979 to 2019 derived from bias-corrected reanalysis, version 2.1. C3S Climate Data Store. https://doi.org/10.24381/cds.20d54e34- Cucchi, M., Weedon, G. P., Amici, A., Bellouin, N., Lange, S., Müller Schmied, H., Hersbach, H. and Buontempo, C. (2020). WFDE5: bias-adjusted ERA5 reanalysis data for impact studies. Earth System Science Data, 12, 2097–2120. https://doi.org/10.5194/essd-12-2097-2020- Dong, Y., Varquez, A. C. G. and Kanda, M. (2017). Global anthropogenic heat flux database with high spatial resolution. Atmospheric Environment, 150, 276–294. https://doi.org/10.1016/j.atmosenv.2016.11.040- Friedl, M. and Sulla-Menashe, D. (2022). MODIS/Terra+Aqua Land Cover Type Yearly L3 Global 0.05Deg CMG V061 [Data set]. NASA EOSDIS Land Processes Distributed Active Archive Center. https://doi.org/10.5067/MODIS/MCD12C1.061- NOAA National Centers for Environmental Information (2001). Global Surface Hourly (Integrated Surface Dataset). NOAA National Centers for Environmental Information. https://www.ncei.noaa.gov/products/land-based-station/integrated-surface-database- Smith, A., Lott, N. and Vose, R. (2011). The Integrated Surface Database: Recent developments and partnerships. Bulletin of the American Meteorological Society, 92, 704–708. https://doi.org/10.1175/2011BAMS3015.1