Assessment and Comparison of Six Machine Learning Models in Estimating Evapotranspiration over Croplands Using Remote Sensing and Meteorological Factors

Yan Liu,Lili Tang,Jiahua Zhang,Yun Bai,Sha Zhang

doi:10.3390/rs13193838

Abstract

Accurate estimates of evapotranspiration (ET) over croplands on a regional scale can provide useful information for agricultural management. The hybrid ET model that combines the physical framework, namely the Penman-Monteith equation and machine learning (ML) algorithms, have proven to be effective in ET estimates. However, few studies compared the performances in estimating ET between multiple hybrid model versions using different ML algorithms. In this study, we constructed six different hybrid ET models based on six classical ML algorithms, namely the K nearest neighbor algorithm, random forest, support vector machine, extreme gradient boosting algorithm, artificial neural network (ANN) and long short-term memory (LSTM), using observed data of 17 eddy covariance flux sites of cropland over the globe. Each hybrid model was assessed to estimate ET with ten different input data combinations. In each hybrid model, the ML algorithm was used to model the stomatal conductance (Gs), and then ET was estimated using the Penman-Monteith equation, along with the ML-based Gs. The results showed that all hybrid models can reasonably reproduce ET of cropland with the models using two or more remote sensing (RS) factors. The results also showed that although including RS factors can remarkably contribute to improving ET estimates, hybrid models except for LSTM using three or more RS factors were only marginally better than those using two RS factors. We also evidenced that the ANN-based model exhibits the optimal performance among all ML-based models in modeling daily ET, as indicated by the lower root-mean-square error (RMSE, 18.67–21.23 W m−2) and higher correlations coefficient (r, 0.90–0.94). ANN are more suitable for modeling Gs as compared to other ML algorithms under investigation, being able to provide methodological support for accurate estimation of cropland ET on a regional scale.

Highlights

Actual evapotranspiration (ET) is the total flux of water vapor transported by vegetation and the ground to the atmosphere
We find that the performance of the long short-term memory (LSTM)-based model in estimating ET time series is not as good as that of other machine learning (ML)-based models, as the r and Root mean square error (RMSE) values of the LSTM-based model are not statistically high
The results showed that the model using three input variables (R = 0.952–0.978, RMSE = 0.598–0.954 mm d−1 ) had better performance in estimating ET compared with the models using two input variables (R = 0.910–0.956, RMSE = 0.846–1.326 mm d−1 )

Summary

Introduction

Actual evapotranspiration (ET) is the total flux of water vapor transported by vegetation and the ground to the atmosphere. It plays an important role in terrestrial water and carbon cycles and energy balance [1]. Droughts have become increasingly prominent with the increase in temperature and the decrease in precipitation. The knowledge of ET, which is an important factor for determining the water consumption of cropland, can provide useful information for irrigation decision-making [2] and drought monitoring [3]. ET plays important roles in material and energy exchanges between soil, crop and atmosphere [4], and is closely related to crop yield and physiological activities. Accurate estimation of ET is of great significance for reducing yield

Objectives

Methods

Results

Discussion

Conclusion