A Hybridized NGBoost-XGBoost Framework for Robust Evaporation and Evapotranspiration Prediction

Abstract

Abstract. We analyze the relationship between potential evapotranspiration (ETo), actual evapotranspiration (ETa), and surface water evaporation (Esw) in the semi-arid south-central Texas, using hourly climate data, daily lake evaporation measurements, and daily actual evapotranspiration measurements from an eddy covariance (EC) tower. The deterministic analysis reveals that ETo set the upper bound for ETa, but the lower bound for Esw in the study area. Unprecedentedly, we demonstrate that a newly developed probabilistic machine learning (ML) model, using a hybridized NGBoost-XGBoost framework, can accurately predict the daily ETo, Esw, & ETa from local climate data. The probabilistic approach exhibits great potential in overcoming data uncertainties, in which 99 % of the ETo, 90 % of the Esw, and 91 % of the ETa test data at three watersheds were within the model's 95 % prediction interval. The probabilistic ML model results suggest that the proposed framework can serve as a robust and computationally more efficient tool than the hourly Penman-Monteith equation to predict the ETo while avoiding computationally-involved net solar radiation calculations. Additionally, the performance analysis of the probabilistic ML model indicates that it can be successfully implemented in practice to overcome the uncertainties associated with pan evaporation & pan coefficients in Esw estimates, and to offset the high capital & operational costs of EC towers used for Ea measurements. Finally, we demonstrate, for the first time, a coalition game theory approach to identify the order of importance, dependencies & interactions of climatic variables on the ML-based ETo, Esw, and ETa predictions. New knowledge gained through the game theory approach is beneficial to strategically locate weather stations for enhanced evapo(transpi)ration predictions, and plan out sustainability and resilience efforts, as part of water management and habitat conservation plans.

Application of Probabilistic Machine Learning to the prediction of Remotely Sensed Vegetation Health

“…NGBoost has already been used successfully to predict Evaporation and Evapotranspiration (Başagaoglu et al, 2020), air temperature (Peng et al, 2020), short-term solar irradiance (Zelikman et al, 2020) and, short-term prediction model of wind power (Li et al, 2020).…”