Comparison of four machine learning models for forecasting daily reference evaporation based on public weather forecast data

Yunfeng Liang, Dongpu Feng, Zhaojun Sun

Preprint · 31 July 2023

In one sentence. Compares four ML models trained on public weather forecasts versus observations for one-day-ahead reference evapotranspiration; forecast-trained models perform better.

Abstract

Abstract. Real-time accurate prediction of daily reference evapotranspiration (ETo) is critical for real-time irrigation decisions and water resource management. Although many public weather forecast-based machine learning models have been successfully used for daily ETo prediction, these models are developed with long-term historical daily observed meteorological data. The use of training and testing samples from different data sources can lead to the selection of the best model, and the performance of the best model for predicting daily ETo is not ideal. In this study, based on Food and Agriculture Organization (FAO) 56 Penman–Monteith (PM) equations, four machine learning models (multilayer perceptron (MLPo), extreme gradient boosting (XGBoosto), light gradient boosting machine (LightGBMo), and gradient boosting with categorical features support (CatBoost1o)) were trained and validated with daily observed meteorological data from 1995–2015 and 2016–2019, respectively, and five machine learning models (MLPp, XGBoostp, LightGBMp, CatBoost1p, and CatBoost2) were trained and validated with daily public weather forecast data with a 1-day lead time (2014–2018 and 2019, respectively). Based on public weather forecast and daily observed meteorological data (2020–2021), the predicted daily ETo performance of nine machine learning models (MLPo, XGBoosto, LightGBMo, CatBoost1o, MLPp, XGBoostp, LightGBMp, CatBoost1p, and CatBoost2) was compared. The results show that for all three studied climate zones, the performance of the four models developed based on public weather forecast data with a 1-day advance is better than that of the four models developed based on daily observed meteorological data with corresponding input combinations, and the mean MAE and RMSE ranges for the four models (MLP, XGBoost, LightGBM, and CatBoost1) in the three studied climate zones were reduced by 2.93 %–11.67 % and 2.20 %–9.46 %, respectively, and the mean R range was improved by 1.31 %–5.31 %. The top three models for the AR climate zone were XGBoostp, LightGBMp, and MLPp, the top three models for the SAR climate zone were MLPp, XGBoostp, and LightGBMp, and the top three models for the SHZ climate zone were XGBoostp, MLPp, and LightGBMp. In addition, the prediction performance for daily ETo is found to be highest in winter and lowest in summer in all three climate zones. Wspd from public weather forecasts was the most important source of daily ETo error in model predictions for the AR climate zone, followed by SDun, Tmax, and Tmin, while SDun from public weather forecasts was the most important source of daily ETo error in model predictions for the SAR (SHZ) climate zone, followed by Wspd, Tmax, and Tmin (Tmax, Wspd, and Tmin).

Labels

Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.