Random forest predictive model development with uncertainty analysis capability for the estimation of evapotranspiration in an arid oasis region

• Published in: Hydrology Research Vol. 51; no. 4; pp. 648 - 665
• Main Authors: Wu, Min, Feng, Qi, Wen, Xiaohu, Deo, Ravinesh C., Yin, Zhenliang, Yang, Linshan, Sheng, Danrui
• Format: Journal Article
• Language: English
• Published: London IWA Publishing 01.08.2020
• Subjects: Accuracy; Air temperature; Algorithms; arid areas; Arid regions; Artificial intelligence; Computer simulation; Evapotranspiration; Evapotranspiration estimates; Forest management; Irrigation; Machine learning; Meteorological data; Methods; monte carlo; Monte Carlo simulation; Neural networks; Oases; predict; Prediction models; random forest; Regression analysis; Relative humidity; Statistical methods; Support vector machines; Uncertainty; Uncertainty analysis; Variables; Wind speed; China
• ISSN: 0029-1277; 1998-9563; 2224-7955
• DOI: 10.2166/nh.2020.012

Abstract The study evaluates the potential utility of the random forest (RF) predictive model used to simulate daily reference evapotranspiration (ET0) in two stations located in the arid oasis area of northwestern China. To construct an accurate RF-based predictive model, ET0 is estimated by an appropriate combination of model inputs comprising maximum air temperature (Tmax), minimum air temperature (Tmin), sunshine durations (Sun), wind speed (U2), and relative humidity (Rh). The output of RF models are tested by ET0 calculated using Penman–Monteith FAO 56 (PMF-56) equation. Results showed that the RF model was considered as a better way to predict ET0 for the arid oasis area with limited data. Besides, Rh was the most influential factor on the behavior of ET0, except for air temperature in the proposed arid area. Moreover, the uncertainty analysis with a Monte Carlo method was carried out to verify the reliability of the results, and it was concluded that RF model had a lower uncertainty and can be used successfully in simulating ET0. The proposed study shows RF as a sound modeling approach for the prediction of ET0 in the arid areas where reliable weather data sets are available, but relatively limited.