Estimating daily reference evapotranspiration using a novel hybrid deep learning model

被引:18
作者
Xing, Liwen [1 ,2 ]
Cui, Ningbo [1 ,2 ,6 ]
Guo, Li [1 ,2 ]
Du, Taisheng [3 ]
Gong, Daozhi [4 ]
Zhan, Cun [1 ,2 ]
Zhao, Long [5 ]
Wu, Zongjun [1 ,2 ]
机构
[1] Sichuan Univ, State Key Lab Hydraul & Mt River Engn, Chengdu 610065, Peoples R China
[2] Sichuan Univ, Coll Water Resource & Hydropower, Chengdu 610065, Peoples R China
[3] China Agr Univ, Ctr Agr Water Res China, Beijing 100091, Peoples R China
[4] Chinese Acad Agr Sci, Inst Environm & Sustainable Dev Agr, State Engn Lab Efficient Water Use Crops & Disaste, Beijing 100081, Peoples R China
[5] Henan Univ Sci & Technol, Coll Agr Equipment Engn, Luoyang 471000, Peoples R China
[6] Sichuan Univ, Coll Water Resource & Hydropower, Chengdu 610065, Peoples R China
基金
中国国家自然科学基金;
关键词
Empirical model; Hybrid deep learning model; Deep Belief Network; Long Short-Term Memory; K-fold cross validation; LIMITED METEOROLOGICAL DATA; GRADIENT DESCENT ALGORITHM; NEURAL-NETWORK; LATENT EVAPORATION; PREDICTION; MACHINE; EQUATIONS; SVM; ELM; ANN;
D O I
10.1016/j.jhydrol.2022.128567
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Reference evapotranspiration (ET0) is usually employed for estimating actual crop ET together with crop co-efficients (Kc). However, it is necessary to explore an alternative model to estimate ET0 concisely because of numerous limitations in the Penman-Monteith method. To improve the ET0 estimation accuracy using limited meteorological data, this study developed a novel hybrid deep learning model (D-LSTM) based on the meteo-rological data during 1961-2020 observed at fifty stations on the Loess Plateau, which used the Deep Belief Network (DBN) module to extract features from meteorological data and the Long Short-Term Memory (LSTM) module to expand time features and process data information with sequential features, respectively. Based on the comparative evaluation of ET0 estimation accuracy between the D-LSTM, DBN, LSTM, and nine empirical models, the results drawn from this study demonstrated that the D-LSTM model manifested the best performance as RH-based, Rn-based, and T-based ET0 estimating models. For local strategy, the value of R2, NSE, RMSE, MAPE, and GPI ranging 0.941 +/- 0.020, 0.940 +/- 0.032, 0.436 +/- 0.457 mm d-1, 0.150 +/- 0.016, and 1.611 +/- 0.180 for D-LSTM1 (RH-based), 0.944 +/- 0.030, 0.943 +/- 0.037, 0.423 +/- 0.313 mm d-1, 0.119 +/- 0.013, and 1.917 +/- 0.155 for D-LSTM2 (Rn-based), and 0.902 +/- 0.091, 0.891 +/- 0.094, 0.558 +/- 0.319 mm d-1, 0.181 +/- 0.058, and 1.440 +/- 0.550 for D-LSTM3 (T-based). For external strategy, the average value of R2, NSE, RMSE, MAPE, and GPI were 0.874, 0.872, 0.651 mm d-1, 0.159, and 1.837 for D-LSTM1, 0.894, 0.892, 0.591 mm d-1, 0.138, and 2.000 for D-LSTM2, and 0.839, 0.827, 0.768 mm d-1, 0.212, and 1.482 for D-LSTM3. Following, the LSTM performed better than DBN for local strategy, but vice versa for external strategy. Despite DL models outperforming RH-based and Rn-based empirical models, H-S outperformed the DBN3 for local strategy, and was superior to LSTM3 for external strategy. Under limited meteorological data, the Rn-based ET0 estimating models are superior to RH-based and T-based models, and RH-based achieved better accuracy than T-based for DL models, but vice versa for empirical models. There is significant spatial variability in the accuracy of daily ET0 models, but the high precision of the D-LSTM was stable on the Loess Plateau. Overall, the D-LSTM model, which combines the advantages of DBN and LSTM, is the most recommended ET0 model using incomplete meteoro-logical data on the Loess Plateau, which is very helpful for farmers or irrigation system operators to improve their irrigation scheduling.
引用
收藏
页数:15
相关论文
共 81 条
[1]   Extreme Learning Machines: A new approach for prediction of reference evapotranspiration [J].
Abdullah, Shafika Sultan ;
Malek, M. A. ;
Abdullah, Namiq Sultan ;
Kisi, Ozgur ;
Yap, Keem Siah .
JOURNAL OF HYDROLOGY, 2015, 527 :184-195
[2]  
Alkan C.M., 2021, GEOMECHANIK TUNNELBA, V188, P1, DOI DOI 10.1002/GEOT.201900054
[3]  
Allen R. G., 1998, FAO Irrigation and Drainage Paper
[5]   ESTIMATION OF LATENT EVAPORATION FROM SIMPLE WEATHER OBSERVATIONS [J].
BAIER, W ;
ROBERTSON, GW .
CANADIAN JOURNAL OF PLANT SCIENCE, 1965, 45 (03) :276-+
[6]   Integrating Models and Fusing Data in a Deep Ensemble Learning Method for Predicting Epidemic Diseases Outbreak [J].
Ben Yahia, Nesrine ;
Kandara, Mohamed Dhiaeddine ;
BenSaoud, Narjes Bellamine .
BIG DATA RESEARCH, 2022, 27
[7]   Evaluation of 32 Simple Equations against the Penman-Monteith Method to Estimate the Reference Evapotranspiration in the Hexi Corridor, Northwest China [J].
Celestin, Sindikubwabo ;
Qi, Feng ;
Li, Ruolin ;
Yu, Tengfei ;
Cheng, Wenju .
WATER, 2020, 12 (10)
[8]   A hybrid deep learning framework with physical process description for simulation of evapotranspiration [J].
Chen, Han ;
Huang, Jinhui Jeanne ;
Dash, Sonam Sandeep ;
Wei, Yizhao ;
Li, Han .
JOURNAL OF HYDROLOGY, 2022, 606
[9]   Design of Deep Belief Networks for Short-Term Prediction of Drought Index Using Data in the Huaihe River Basin [J].
Chen, Junfei ;
Jin, Qiongji ;
Chao, Jing .
MATHEMATICAL PROBLEMS IN ENGINEERING, 2012, 2012
[10]   Estimating daily reference evapotranspiration based on limited meteorological data using deep learning and classical machine learning methods [J].
Chen, Zhijun ;
Zhu, Zhenchuang ;
Jiang, Hao ;
Sun, Shijun .
JOURNAL OF HYDROLOGY, 2020, 591