Prediction Model for Reference Crop Evapotranspiration Based on the Back-propagation Algorithm with Limited Factors

• Published in: Water resources management Vol. 37; no. 3; pp. 1207 - 1222
• Main Authors: Zhao, Long, Xing, Liwen, Wang, Yuhang, Cui, Ningbo, Zhou, Hanmi, Shi, Yi, Chen, Sudan, Zhao, Xinbo, Li, Zhe
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Netherlands 01.02.2023; Springer Nature B.V
• Subjects: Accuracy; Air temperature; Algorithms; Ant colony optimization; Artificial neural networks; Atmospheric models; atmospheric pressure; Atmospheric Sciences; Back propagation; Back propagation networks; birds; China; Civil Engineering; Computer applications; Decision making; Earth and Environmental Science; Earth Sciences; Environment; Evapotranspiration; Geotechnical Engineering & Applied Earth Sciences; Heuristic methods; Hydrogeology; Hydrology/Water Resources; Irrigation; Irrigation water; Machine learning; Model accuracy; Neural networks; Prediction models; Relative humidity; Resource management; solar radiation; supply balance; swarms; system optimization; water management; Water resources; Water resources management; Water supply; Weather stations; Wind speed; China; Reference evapotranspiration; Back-propagation neural network; Hybrid optimization algorithm; Weather forecast; K-fold
• ISSN: 0920-4741; 1573-1650
• DOI: 10.1007/s11269-022-03423-7

The precise estimation of reference crop evapotranspiration (ET O ) is vital for regional and irrigation water resource management. It is also beneficial to the rational allocation of regional water resources and alleviates the disparity between water supply and demand. This study accurately estimates the ET O of 14 meteorological stations in southern China. Five neural network models (extreme learning machine [ELM], back-propagation neural network [BP], ant colony optimization [ACO]-BP, bird swarm algorithm [BSA]-BP, and cat swarm optimization [CSO]-BP) were introduced to predict ET O with limited factors using different methods. The results demonstrated that models involving T (average, maximum, and minimum air temperature), sunshine duration (n), and relative humidity (RH) exhibited the highest accuracy of all studied combinations; the role of T, n, RH, wind speed (U 2 ) and average atmospheric pressure (AP) regarding ET O gradually decreased. These three biological heuristic algorithms (ACO, BSA, and CSO) each significantly enhanced the capability of the BP model. The accuracy and computational cost of the CSO-BP model are better than those built by other algorithms. Therefore, it is strongly recommended to use the CSO-BP model for ET O estimation in southern China. This result serves as a reference for a more accurate estimation of ET O for future irrigation decision-making and water resource management in southern China.