An Efficient Hybrid Model With Harris Hawks Optimization Algorithm for Predicting Oat Water
EAI Endorsed Transactions on AI and Robotics · 04.03.2026 · 5
DOI: 10.4108/airo.12011 ↗Kurz gefasst
Fachartikel in der Zeitschrift EAI Endorsed Transactions on AI and Robotics, online erschienen am 04.03.2026. Verfasst von He Jinbo und 11 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).
Abstract (Originalsprache)
Oats are a cold-tolerant and high-yielding cultivated forage crop, which have relatively high requirements for water management. To improve the forecasting accuracy of irrigation requirements for oats, this paper proposes a novel hybrid neural network architecture, whose parameters are refined using the Harris Hawk optimization algorithm. It directly addresses two prevalent shortcomings in current predictive models: the typically imprecise manual adjustment of hyperparameters, and the inadequate modeling of both spatial and temporal dependencies with the data. By integrating these methodological improvements, the proposed method aims to achieve more precise and robust forecasts. Firstly, the hybrid model integrates a temporal convolutional network, a bidirectional long short-term memory network, and a multi-head attention mechanism. This method leverages multi-head attention to enrich feature representation, thereby facilitating a more comprehensive capture of the temporal dynamics inherent in alpine oat water demand. Secondly, the Harris Hawk optimization method is introduced to optimize the model’s hyperparameters, effectively avoiding local optimum. Experimental results on the oat water demand and environmental dataset from 2019 to 2023 indicate that the hybrid model achieved a mean absolute error and root mean square error of 0.3432 and 0.4863, respectively, thus representing reductions of approximately 52.73% and 46.39%compared to the traditional Long Short-Term Memory (LSTM) model. The coefficient of determination increased by about 15.31%. Ablation study results demonstrate that the complete hybrid model achieved Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) of 0.3432 and 0.4863, respectively, which represent reductions of approximately 52.89% and 43.75% compared to the baseline model, the coefficient of determination improving by about 22.16%. Compared with other methods, this method has a distinct advantage in forecasting the precision of oat water demand, which offers technical and decision support for smart irrigation.
Zitieren
APA
Jinbo, H., Wang, Z., Huang, W., Zhou, F., Wang, A., Wu, X., Chen, P., He, T., Gan, J., Wei, P., Li, Z., & Wu, C. (2026). An Efficient Hybrid Model With Harris Hawks Optimization Algorithm for Predicting Oat Water. EAI Endorsed Transactions on AI and Robotics, 5. https://doi.org/10.4108/airo.12011
Vancouver
Jinbo H, Wang Z, Huang W, Zhou F, Wang A, Wu X, et al. An Efficient Hybrid Model With Harris Hawks Optimization Algorithm for Predicting Oat Water. EAI Endorsed Transactions on AI and Robotics. 2026;5. doi:10.4108/airo.12011
BibTeX
@article{Jinbo2026,
author = {Jinbo, He and Wang, Zirun and Huang, Wanzhen and Zhou, Fanting and Wang, Anqi and Wu, Xianjin and Chen, Pengzi and He, Tongli and Gan, Jianhong and Wei, Peiyang and Li, Zhibin and Wu, Chunjiang},
title = {An Efficient Hybrid Model With Harris Hawks Optimization Algorithm for Predicting Oat Water},
journal = {EAI Endorsed Transactions on AI and Robotics},
year = {2026},
volume = {5},
doi = {10.4108/airo.12011}
}
EUVIMED