Univrsity Of Tehran Press Water and Irrigation Management 2251-6298 13 4 2023 12 22 Evaluating Remote Sensing Technique and Machine Learning Algorithms in Estimating Sugarcane Evapotranspiration Evaluating Remote Sensing Technique and Machine Learning Algorithms in Estimating Sugarcane Evapotranspiration 965 982 94257 10.22059/jwim.2023.362473.1090 FA Mohammad Alavi Department of Irrigation and Drainage, Faculty of Water and Environmental Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran. 0009-0007-1613-9575 Mohammad Albaji Department of Irrigation and Drainage, Faculty of Water and Environmental Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran. 0000-0002-5483-5834 Mona Golabi Department of Irrigation and Drainage, Faculty of Water and Environmental Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran. 0000-0002-9199-2628 Abd Ali Naseri Department of Irrigation and Drainage, Faculty of Water and Environmental Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran. 0000-0002-5833-5802 Saeid Homayouni Centre Eau Terre Environnement, Institut National de la Recherche Scientifique (INRS), 490 Couronne St, Quebec, QC G1K 9A9, Canada. 0000-0002-0214-5356 Journal Article 2023 07 17 Estimating crop evapotranspiration (ET_c) in arid and semi-arid areas can be difficult due to the dynamic nature of this process across both time and space. In addition, obtaining on-site measurements for this variable can be very time-consuming and costly. This study aimed to develop a framework that accurately estimates the sugarcane crop evapotranspiration on a spatio-temporal scale. This was achieved using four machine learning (ML) algorithms (MLR, CART, SVR, and GBRT) combined with remote sensing (RS) data and meteorological variables. Also, to reduce the dependence on several meteorological parameters in conventional ET_c equations, the performance of eight different experimental temperature-based methods and four modified Hargreaves & Samani equations was evaluated compared to the standard FAO-Penman-Monteith method. For this purpose, weather data were collected from Hakim Farabi Sugarcane Agro-Industrial meteorological station for three years (2018-2021). Nine combinations of input variables (RS data and meteorological variables) were designed based on the IGR method and then evaluated by the ML algorithms. The results showed that the highest accuracy of ML algorithms based on R², RMSE, and MAE statistics was obtained in CART (0.99, 0.41, and 0.18) and GBRT algorithms (0.99, 0.65, and 0.26), respectively. Regarding temperature-based methods, Ivanov’s equation had the best performance with an R² of 0.91, while Baier and Robertson’s equation had the weakest performance with an R² of 0.78 when estimating ET_c. Overall, the combination of RS and ML algorithms effectively produced more precise and reliable ET_c values on both temporal and spatial scales. Estimating crop evapotranspiration (ET_c) in arid and semi-arid areas can be difficult due to the dynamic nature of this process across both time and space. In addition, obtaining on-site measurements for this variable can be very time-consuming and costly. This study aimed to develop a framework that accurately estimates the sugarcane crop evapotranspiration on a spatio-temporal scale. This was achieved using four machine learning (ML) algorithms (MLR, CART, SVR, and GBRT) combined with remote sensing (RS) data and meteorological variables. Also, to reduce the dependence on several meteorological parameters in conventional ET_c equations, the performance of eight different experimental temperature-based methods and four modified Hargreaves & Samani equations was evaluated compared to the standard FAO-Penman-Monteith method. For this purpose, weather data were collected from Hakim Farabi Sugarcane Agro-Industrial meteorological station for three years (2018-2021). Nine combinations of input variables (RS data and meteorological variables) were designed based on the IGR method and then evaluated by the ML algorithms. The results showed that the highest accuracy of ML algorithms based on R², RMSE, and MAE statistics was obtained in CART (0.99, 0.41, and 0.18) and GBRT algorithms (0.99, 0.65, and 0.26), respectively. Regarding temperature-based methods, Ivanov’s equation had the best performance with an R² of 0.91, while Baier and Robertson’s equation had the weakest performance with an R² of 0.78 when estimating ET_c. Overall, the combination of RS and ML algorithms effectively produced more precise and reliable ET_c values on both temporal and spatial scales. https://jwim.ut.ac.ir/article_94257_4eb142cc779f80936fe91bc9a2ea28f3.pdf