MeteoSerbia1km is the first daily gridded meteorological dataset at a 1-km spatial resolution across Serbia for the 2000–2019 period. The dataset consists of five daily variables: maximum, minimum and mean temperature, mean sea level pressure, and total precipitation. Besides daily summaries, it contains monthly and annual summaries, daily, monthly, and annual long term means (LTM). Daily gridded data were interpolated using the Random Forest Spatial Interpolation methodology based on Random Forest and using nearest observations and distances to them as spatial covariates, together with environmental covariates. Complete script in R and datasets used for modelling, tuning, validation, and prediction of daily meteorological variables are available here. If you discover a bug, artifact or inconsistency in the MeteoSerbia1km maps, or if you have a question please use this channel. File naming convention of .zip files and containing MeteoSerbia1km files: Daily summaries per year: day_yyyy_proj.zip var_day_yyyymmdd_proj.tif Monthly summaries: mon_proj.zip var_mon_yyyymm_proj.tif Annual summaries: ann_proj.zip var_ann_yyyy_proj.tif Daily, monthly and annual LTM: ltm_proj.zip daily LTM: var_ltm_day_mmdd_proj.tif monthly LTM: var_ltm_mon_mm_proj.tif annual LTM: var_ltm_ann_proj.tif where: var is a daily meteorological variable name - tmax, tmin, tmean, slp, or prcp proj is a dataset projection - wgs84 or utm34 Units of the dataset values are temperature (Tmean, Tmax, and Tmin) - tenths of a degree in the Celsius scale (℃) SLP - tenths of a mbar PRCP - tenths of a mm All dataset values are stored as integers (INT32 data type) in order to reduce the size of the GeoTIFF files, i.e., temperature values should be divided by 10 to obtain degrees Celsius, and the same for SLP and PRCP to obtain millibars and millimeters.

This research was funded by CERES project, by the Science Fund of the Republic of Serbia – Program for Development of Projects in the Field of Artificial Intelligence, with grant number 6527073, and by BEACON Horizon 2020 Research and Innovation programme under Grant agreement No. 821964. The authors would like to acknowledge OGIMET service (https://www.ogimet.com/), NASA Goddard Space Flight Center (https://www.nasa.gov/goddard), ECA&D project (https://www.ecad.eu), and PIS Vojvodina (http://www.pisvojvodina.com/Shared%20Documents/AMS_pristup.aspx) for providing OGIMET, IMERG, E-OBS, and AMSV data. We would like to thank the R-sig-geo community for developing free and open tools for spatial modeling, and all researchers and developers of R packages that made MeteoSerbia1km data making possible.

{"references": ["Sekuli\u0107, A., Kilibarda, M., Heuvelink, G. B., Nikoli\u0107, M. & Bajat, B. Random Forest Spatial Interpolation.Remote. Sens. 12, 1687, https://doi.org/10.3390/rs12101687 (2020)."]}