A minimalistic approach for evapotranspiration estimation using the Prophet model |
| |
Authors: | A. T. M. Sakiur Rahman Takahiro Hosono Ozgur Kisi Boateng Dennis A. H. M. Rahmatullah Imon |
| |
Affiliation: | 1. Department of Earth and Environmental Science, Faculty of Science, Kumamoto University , Kumamoto, Japan shakigeo@gmail.comhttps://orcid.org/0000-0003-1900-4506;3. Faculty of Advanced Science and Technology, Kumamoto University , Kumamoto, Japan;4. International Research Organization for Advanced Science and Technology, Kumamoto University , Kumamoto, Japan https://orcid.org/0000-0001-7200-7912;5. School of Technology, Ilia State University , Tbilisi, Georgia;6. Institute of Research and Development, Duy Tan University, Da Nang 550000, Vietnamhttps://orcid.org/0000-0001-7847-5872;7. Department of Earth and Environmental Science, Faculty of Science, Kumamoto University , Kumamoto, Japan;8. Department of Mathematical Sciences, Ball State University , Muncie, Indiana, USA |
| |
Abstract: | ABSTRACT This study aimed to evaluate the potential of the recently introduced Prophet model for estimating reference evapotranspiration (ETo). A comparative study was conducted for benchmarking the model results with support vector regression (SVR) and temperature-based empirical models (Thornthwaite and Hargreaves) in southern Japan. The performance of the Prophet, SVR and temperature-based empirical models was evaluated by Nash–Sutcliffe efficiency (NSE) and coefficient of determination (R2). The results indicate that temperature-based Prophet and SVR models have greater accuracy than the empirical models. The Prophet model with sole input of relative humidity, sunshine hours or windspeed showed acceptable accuracy (NSE > 0.80; R2 > 0.80), while SVR models with similar inputs showed greater errors. Accuracy improved with increasing number of input parameters, giving excellent performance (NSE > 0.95; R2 > 0.95) with all input parameters. Hence, the Prophet model is a new promising approach for modelling ETo with limited input variables. |
| |
Keywords: | machine learning Prophet model support vector regression evapotranspiration minimalistic approach |
|
|