Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387442910> ?p ?o ?g. }
Showing items 1 to 43 of
43
with 100 items per page.
- W4387442910 abstract "<strong class=journal-contentHeaderColor>Abstract.</strong> Real-time accurate prediction of daily reference evapotranspiration (ET<sub>o</sub>) 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 ET<sub>o</sub> 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 ET<sub>o</sub> is not ideal. In this study, based on Food and Agriculture Organization (FAO) 56 Penman–Monteith (PM) equations, four machine learning models (multilayer perceptron (MLP<sub>o</sub>), extreme gradient boosting (XGBoost<sub>o</sub>), light gradient boosting machine (LightGBM<sub>o</sub>), and gradient boosting with categorical features support (CatBoost1<sub>o</sub>)) were trained and validated with daily observed meteorological data from 1995–2015 and 2016–2019, respectively, and five machine learning models (MLP<sub>p</sub>, XGBoost<sub>p</sub>, LightGBM<sub>p</sub>, CatBoost1<sub>p</sub>, 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 ET<sub>o</sub> performance of nine machine learning models (MLP<sub>o</sub>, XGBoost<sub>o</sub>, LightGBM<sub>o</sub>, CatBoost1<sub>o</sub>, MLP<sub>p</sub>, XGBoost<sub>p</sub>, LightGBM<sub>p</sub>, CatBoost1<sub>p</sub>, 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 XGBoost<sub>p</sub>, LightGBM<sub>p</sub>, and MLP<sub>p</sub>, the top three models for the SAR climate zone were MLP<sub>p</sub>, XGBoost<sub>p</sub>, and LightGBM<sub>p</sub>, and the top three models for the SHZ climate zone were XGBoost<sub>p</sub>, MLP<sub>p</sub>, and LightGBM<sub>p</sub>. In addition, the prediction performance for daily ET<sub>o</sub> is found to be highest in winter and lowest in summer in all three climate zones. <em>Wspd</em> from public weather forecasts was the most important source of daily ET<sub>o</sub> error in model predictions for the AR climate zone, followed by <em>SDun</em>, <em>T<sub>max</sub></em>, and <em>T<sub>min</sub></em>, while <em>SDun</em> from public weather forecasts was the most important source of daily ET<sub>o</sub> error in model predictions for the SAR (SHZ) climate zone, followed by <em>Wspd</em>, <em>T<sub>max</sub></em>, and <em>T<sub>min</sub></em> (<em>T<sub>max</sub></em>, <em>Wspd</em>, and <em>T<sub>min</sub></em>)." @default.
- W4387442910 created "2023-10-10" @default.
- W4387442910 date "2023-10-08" @default.
- W4387442910 modified "2023-10-10" @default.
- W4387442910 title "Comment on hess-2023-158" @default.
- W4387442910 doi "https://doi.org/10.5194/hess-2023-158-rc2" @default.
- W4387442910 hasPublicationYear "2023" @default.
- W4387442910 type Work @default.
- W4387442910 citedByCount "0" @default.
- W4387442910 crossrefType "peer-review" @default.
- W4387442910 hasBestOaLocation W43874429101 @default.
- W4387442910 hasConcept C119857082 @default.
- W4387442910 hasConcept C154945302 @default.
- W4387442910 hasConcept C169258074 @default.
- W4387442910 hasConcept C179717631 @default.
- W4387442910 hasConcept C41008148 @default.
- W4387442910 hasConcept C46686674 @default.
- W4387442910 hasConcept C50644808 @default.
- W4387442910 hasConcept C70153297 @default.
- W4387442910 hasConceptScore W4387442910C119857082 @default.
- W4387442910 hasConceptScore W4387442910C154945302 @default.
- W4387442910 hasConceptScore W4387442910C169258074 @default.
- W4387442910 hasConceptScore W4387442910C179717631 @default.
- W4387442910 hasConceptScore W4387442910C41008148 @default.
- W4387442910 hasConceptScore W4387442910C46686674 @default.
- W4387442910 hasConceptScore W4387442910C50644808 @default.
- W4387442910 hasConceptScore W4387442910C70153297 @default.
- W4387442910 hasLocation W43874429101 @default.
- W4387442910 hasOpenAccess W4387442910 @default.
- W4387442910 hasPrimaryLocation W43874429101 @default.
- W4387442910 hasRelatedWork W1985505753 @default.
- W4387442910 hasRelatedWork W2766514146 @default.
- W4387442910 hasRelatedWork W2885516856 @default.
- W4387442910 hasRelatedWork W2885778889 @default.
- W4387442910 hasRelatedWork W2967733078 @default.
- W4387442910 hasRelatedWork W3094138326 @default.
- W4387442910 hasRelatedWork W3137904399 @default.
- W4387442910 hasRelatedWork W4289703016 @default.
- W4387442910 hasRelatedWork W4310224730 @default.
- W4387442910 hasRelatedWork W4310492845 @default.
- W4387442910 isParatext "false" @default.
- W4387442910 isRetracted "false" @default.
- W4387442910 workType "peer-review" @default.