Effect of Land Surface Temperature of MODIS Sensor in Estimating Daily Reference Evapotranspiration in Two Different Climates

Abstract

Estimating reference evapotranspiration (ET0) is a fundamental requirement of agricultural water management. However, the lack of necessary meteorological data makes it difficult to estimate ET0 using the FAO-Penman-Monteith equation wider areas. Therefore, this research examines the estimation of daily reference evapotranspiration using MODIS Land Surface Temperature (LST) from satellite imagery in two climates of Tabriz and Rasht. ET0 has been estimated using two random forests (RF) and random forests optimized with genetic (GA-RF) algorithms. The parameters used in both stations include the combination of daily land surface temperature (LSTday), nightly land surface temperature (LSTnight) and average land surface temperature at night, and day (LSTmean). The obtained results indicated that LSTmean has an excellent ability to estimate ET0 in both stations. In Tabriz station with a semi-arid climate, GA-RF-7 model with RMSE=0.516 and in Rasht station with a very humid climate, the GA-RF-5 model with RMSE=0.868, have the best performance among the studied models. Moreover, the evaluations revealed that the temperature of the earth's surface at night is as important as the temperature of the earth's surface during the day, and by combining these two parameters, satisfactory results may be obtained.

Keywords

• fao-penman-monteith
• genetic algorithm
• random forest
• remote sensing