Reliable Evapotranspiration Predictions with a Probabilistic Machine Learning Framework

Abstract

Evapotranspiration is often expressed in terms of reference crop evapotranspiration (ETo), actual evapotranspiration (ETa), or surface water evaporation (Esw), and their reliable predictions are critical for groundwater, irrigation, and aquatic ecosystem management in semi-arid regions. We demonstrated that a newly developed probabilistic machine learning (ML) model, using a hybridized “boosting” framework, can simultaneously predict the daily ETo, Esw, & ETa from local hydroclimate data with high accuracy. The probabilistic approach exhibited great potential to overcome data uncertainties, in which 100% of the ETo, 89.9% of the Esw, and 93% of the ETa test data at three watersheds were within the models’ 95% prediction intervals. The modeling results revealed that the hybrid boosting framework can be used as a reliable computational tool to predict ETo while bypassing net solar radiation calculations, estimate Esw while overcoming uncertainties associated with pan evaporation & pan coefficients, and predict ETa while offsetting high capital & operational costs of EC towers. In addition, using the Shapley analysis built on a coalition game theory, we identified the order of importance and interactions between the hydroclimatic variables to enhance the models’ transparency and trustworthiness.

Combination of Limited Meteorological Data for Predicting Reference Crop Evapotranspiration Using Artificial Neural Network Method

“…Although lysimeters are commonly used to directly measure ET, they are poorly spread over the world due to their high cost and time-consuming management [16,17]. Therefore, ET is generally estimated by various empirical models that assess either potential evapotranspiration (ET p ) or reference crop evapotranspiration (ET o ) [18,19]. The factor ET o is the highest rate of evapotranspiration that a well-watered vegetative grass surface can produce [5,20,21].…”

Evaluation of the RF-Based Downscaled SMAP and SMOS Products Using Multi-Source Data over an Alpine Mountains Basin, Northwest China

“…The quality of the model was evaluated with the testing set after obtaining the optimal model with the minimum RMSE as the standard. Additionally, the SHAP methodology [55][56][57][58] was used here to interpret the relationships of the input surface variables with the model predictions.…”

Machine Learning for Bayesian Experimental Design in the Subsurface

“…Shen et al (2022) applied NGBoost for probabilistic runoff predictions, and remarked its "suitable performance," although their approach was hindered by model limitations and complexity of the actual runoff process. Başağaoğlu et al (2021) developed and hybrid NGBoost-XGBoost (extreme gradient boosting, Chen and Guestrin 2016) to predict evapotranspiration. One downside of NGBoost is that it can only be used to predict a single variable at a time.…”