Comparison of Simple Temporal and Climatological Baselines, Deterministic Spatial Interpolation, and Hybrid Machine-Learning Methods for Imputing Precipitation Data Using ERA5-Land Climate Data
Atmosphere · 26.07.2026 · 17 (8) · 727
DOI: 10.3390/atmos17080727 ↗Kurz gefasst
Fachartikel in der Zeitschrift Atmosphere, online erschienen am 26.07.2026. Verfasst von Yunus Tektaş und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Precipitation records from meteorological stations frequently contain gaps caused by sensor, power, or transmission failures, creating uncertainty in hydrological, agricultural, and water-resources applications. This study compared two simple baselines (station-specific monthly climatological mean and temporal linear interpolation), deterministic spatial interpolation, direct reanalysis-based replacement, and machine-learning methods for daily precipitation imputation. Daily precipitation from 14 stations in Eastern and Southeastern Türkiye during 1985–2014 was evaluated using an independent final-test set formed by stratified random masking of 15% of complete observations; the remaining 85% was used for calibration, SHapley Additive exPlanations (SHAP) analysis, cross-validation, and hyperparameter optimization. ERA5-Land variables were transferred to the stations, precipitation was calibrated by Empirical Quantile Mapping, and leakage-controlled Kriging estimates were incorporated as predictors in XGBoost, LightGBM, Random Forest, Support Vector Regression, and Multilayer Perceptron models. The station-month climatological mean (RMSE = 5.4820 mm; NSE = 0.0527) and temporal linear interpolation (RMSE = 5.7059 mm; NSE = −0.0262) performed substantially worse than optimized Kriging and IDW. The full-hybrid LightGBM model achieved the best performance (RMSE = 3.2001 mm; MAE = 0.9814 mm; Pearson r = 0.8317; NSE = 0.6772), whereas direct ERA5-EQM replacement was less accurate (RMSE = 5.2252 mm; NSE = 0.1394). Combining local observations, spatial information, and ERA5-Land covariates therefore improved daily precipitation imputation in the study region.
Zitieren
APA
Tektaş, Y., & Polat, N. (2026). Comparison of Simple Temporal and Climatological Baselines, Deterministic Spatial Interpolation, and Hybrid Machine-Learning Methods for Imputing Precipitation Data Using ERA5-Land Climate Data. Atmosphere, 17(8), 727. https://doi.org/10.3390/atmos17080727
Vancouver
Tektaş Y, Polat N. Comparison of Simple Temporal and Climatological Baselines, Deterministic Spatial Interpolation, and Hybrid Machine-Learning Methods for Imputing Precipitation Data Using ERA5-Land Climate Data. Atmosphere. 2026;17(8):727. doi:10.3390/atmos17080727
BibTeX
@article{Tekta2026,
author = {Tektaş, Yunus and Polat, Nizar},
title = {Comparison of Simple Temporal and Climatological Baselines, Deterministic Spatial Interpolation, and Hybrid Machine-Learning Methods for Imputing Precipitation Data Using ERA5-Land Climate Data},
journal = {Atmosphere},
year = {2026},
volume = {17},
number = {8},
pages = {727},
doi = {10.3390/atmos17080727}
}
EUVIMED