Preprints
https://doi.org/10.5194/hess-2023-158
https://doi.org/10.5194/hess-2023-158
31 Jul 2023
 | 31 Jul 2023
Status: this preprint was under review for the journal HESS but the revision was not accepted.

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

Yunfeng Liang, Dongpu Feng, and Zhaojun Sun

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).

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Yunfeng Liang, Dongpu Feng, and Zhaojun Sun

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • CC1: 'Comment on hess-2023-158', quanrong wang, 03 Sep 2023
    • AC1: 'Reply on CC1(Response to review queries and review suggestions from Quanrong Wang)', Zhaojun Sun, 07 Sep 2023
  • RC1: 'Comment on hess-2023-158', Anonymous Referee #1, 30 Sep 2023
    • AC2: 'Reply on RC1', Zhaojun Sun, 02 Oct 2023
  • RC2: 'Comment on hess-2023-158', Anonymous Referee #2, 08 Oct 2023
    • AC3: 'Reply on RC2', Zhaojun Sun, 10 Oct 2023

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • CC1: 'Comment on hess-2023-158', quanrong wang, 03 Sep 2023
    • AC1: 'Reply on CC1(Response to review queries and review suggestions from Quanrong Wang)', Zhaojun Sun, 07 Sep 2023
  • RC1: 'Comment on hess-2023-158', Anonymous Referee #1, 30 Sep 2023
    • AC2: 'Reply on RC1', Zhaojun Sun, 02 Oct 2023
  • RC2: 'Comment on hess-2023-158', Anonymous Referee #2, 08 Oct 2023
    • AC3: 'Reply on RC2', Zhaojun Sun, 10 Oct 2023
Yunfeng Liang, Dongpu Feng, and Zhaojun Sun
Yunfeng Liang, Dongpu Feng, and Zhaojun Sun

Viewed

Total article views: 650 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
473 142 35 650 60 23 23
  • HTML: 473
  • PDF: 142
  • XML: 35
  • Total: 650
  • Supplement: 60
  • BibTeX: 23
  • EndNote: 23
Views and downloads (calculated since 31 Jul 2023)
Cumulative views and downloads (calculated since 31 Jul 2023)

Viewed (geographical distribution)

Total article views: 608 (including HTML, PDF, and XML) Thereof 608 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 18 Jul 2024
Download
Short summary
During the testing period, the performance of the predicted ETo from the machine learning model trained and validated based on the public weather forecast 1 day before outperforms the performance of the predicted ETo from the machine learning model trained and validated based on the daily observed meteorological data. Wspd and SDun in the public weather forecast are the most important sources of daily ETo errors in the model predictions for the AR and SAR (SHZ) climate zone, respectively.