Developing reservoir operation strategy under the mechanism-data dual-driven framework: Coordinating the water demand characteristics of multi sectors

Zhiwen Peng, Aijun Guo, Jianxia Chang, Yimin Wang, Xuebin Wang, Chen Niu and Zhehao Li

Agricultural Water Management, 2025, vol. 318, issue C

Abstract: Reservoir operation is facing increasing challenges in balancing water demands across multiple sectors, making it crucial to develop effective operation strategy to improve the utilization efficiency of limited water resources. To address this, this study proposes a mechanism-data dual-driven framework for developing reservoir operation strategy. At the mechanistic level, considering the water demand characteristics of multi sectors, the localized AquaCrop-OSPy is coupled with the reservoir operation model to construct Model I. And the model aims to maximize agricultural yield. Simultaneously, Model II is established that the reservoir operates according to the standardized operation policy. At the data-driven level, based on diversified information, the light gradient boosting machine is used to extract reservoir operation strategy, and the shapley additive explanations (SHAP) is applied to analyze the decision-making mechanisms of the strategy. Using the Dongzhuang reservoir in the Yellow River Basin as an example. The results demonstrate that in long-term simulations, Model I can reduce water shortages in the ecological sector from 0.12 % to 0.04 %, in the domestic-industrial sector from 2.20 % to 0.64 %, and increases agricultural yield by 7.79 % compared to Model II. The extracted operation strategy extracted demonstrates significant overall benefits. Among them, agricultural yield is 2.60 % higher than Model II, but 4.82 % lower than Model I. SHAP analysis reveals that the end of month water level of the reservoir is influenced by the directional heterogeneity of multiple-factor. Among them, the water level at the beginning of month has the greatest impact, while the monthly precipitation has the least impact.

Keywords: Coordinating multi-sector water demands; Reservoir operation model; Reservoir operation strategy; Machine learning; Driver analysis (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0378377425004524
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:agiwat:v:318:y:2025:i:c:s0378377425004524

DOI: 10.1016/j.agwat.2025.109738

Access Statistics for this article

Agricultural Water Management is currently edited by B.E. Clothier, W. Dierickx, J. Oster and D. Wichelns

More articles in Agricultural Water Management from Elsevier
Bibliographic data for series maintained by Catherine Liu ().