General and regional cross-station assessment of machine learning models for estimating reference evapotranspiration


Acta Geophysica, vol.71, no.2, pp.927-947, 2023 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 71 Issue: 2
  • Publication Date: 2023
  • Doi Number: 10.1007/s11600-022-00939-9
  • Journal Name: Acta Geophysica
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.927-947
  • Keywords: Reference evapotranspiration, Cross-station assessment, Machine learning, Generalizability, Regional models, Gaussian processes, WATER-USE, ANN
  • Kayseri University Affiliated: No


© 2022, The Author(s) under exclusive licence to Institute of Geophysics, Polish Academy of Sciences & Polish Academy of Sciences.Significant research has been done on estimating reference evapotranspiration (ET) from limited climatic measurements using machine learning (ML) to facilitate the acquirement of ET values in areas with limited access to weather stations. However, the spatial generalizability of ET estimating ML models is still questionable, especially in regions with significant climatic variation like Turkey. Aiming at exploring this generalizability, this study compares two ET modeling approaches: (1) one general model covering all of Turkey, (2) seven regional models, one model for each of Turkey’s seven regions. In both approaches, ET was predicted using 16 input combinations and 3 ML methods: support vector regression (SVR), Gaussian process regression (GPR), and random forest (RF). A cross-station evaluation was used to evaluate the models. Results showed that the use of regional models created using SVR and GPR methods resulted in a reduction in root mean squared error (RMSE) in comparison with the general model approach. Models created using the RF method suffered from overfitting in the regional models’ approach. Furthermore, a randomization test showed that the reduction in RMSE when using these regional models was statistically significant. These results emphasize the importance of defining the spatial extent of ET estimating models to maintain their generalizability.