白龙江引调水工程受水区需水预测研究
Water Demand Prediction Research in the Water Receiving Area of the Bailongjiang Water Diversion Project
DOI: 10.12677/jwrr.2025.144038, PDF,    科研立项经费支持
作者: 王军德, 刘德地*, 程玉菲：甘肃省水利科学研究院，甘肃 兰州；武汉大学水资源工程与调度全国重点实验室，湖北 武汉；张波森*：武汉大学水资源工程与调度全国重点实验室，湖北 武汉；包志为：甘肃省水利科学研究院，甘肃 兰州
关键词: 需水预测；定额法；LSTM模型；白龙江引调水工程；Water Demand Forecasting； Quota Method； LSTM Model； Bailongjiang Water Diversion Project
摘要: 白龙江引调水工程是为解决甘肃省天水、平凉、庆阳地区水资源短缺危机而规划建设的大型水利工程，对提高区域水安全保障水平具有重要作用。对受水区进行合理准确的需水预测，能有效提高引调水工程水资源配置效率。本文进行了调水工程受水区的需水预测研究，利用LSTM模型建立了从全球WFaS用水数据到统计调查历史用水数据之间的映射关系，从而将未来受水区上的WFaS用水预测数据转化为受水区的需水数据，并与定额法预测的需水数据进行对比。该方法有效克服了统计调查历史用水数据样本不足以及WFaS数据在区域范围内精度不高的问题，为引调水工程受水区的需水预测提供了一种新思路。
Abstract: The Bailongjiang Water Diversion Project is a large-scale water conservancy project planned and con-structed to address the water resources shortage crisis in Tianshui, Pingliang, and Qingyang areas of Gansu Province, playing a crucial role in enhancing regional water security. Accurate and appropriate water demand forecasting for the water-receiving areas can effectively improve the efficiency of water resources allocation for the diversion project. This paper conducts a study on water demand forecasting for the water-receiving areas of the diversion project. It establishes a mapping relationship between global WFaS water use data and historical water use data from statistical surveys using an LSTM model. This allows for the conversion of future WFaS water use forecast data in the water-receiving areas into water demand data for those areas, which is then compared with water demand data predicted by the quota method. This approach effectively overcomes the issues of insufficient samples in historical water use data from statistical surveys and the low accuracy of WFaS data at the regional level, offering a new perspective for water demand forecasting in the water-receiving areas of water diversion projects.
文章引用：王军德, 张波森, 刘德地, 程玉菲, 包志为. 白龙江引调水工程受水区需水预测研究[J]. 水资源研究, 2025, 14(4): 350-362. https://doi.org/10.12677/jwrr.2025.144038

参考文献

[1] 黄军, 胡卫权, 陈媛媛, 等. 水资源论证区域评估关键技术研究与应用实践[J/OL]. 水利发展研究, 2024: 1-8.
https://link.cnki.net/urlid/11.4655.TV.20241022.1101.008, 2025-08-05.
[2] 孙芳欣, 杜崇, 刘岩. 多种数学模型下的绥滨县需水预测研究[J]. 黑龙江水利科技, 2024, 52(11): 25-29.
[3] 蔡素芳, 梅亚东. 需水预测研究综述[C]//中国水利学会水资源专业委员会, 中国水利水电科学研究院, 大连理工大学. 变化环境下的水资源响应与可持续利用——中国水利学会水资源专业委员会2009学术年会论文集. 2009: 227-232.
[4] 邓奎, 李龙国. 灰色回归模型在农业用水量预测中的应用[J]. 杨凌职业技术学院学报, 2011, 10(1): 48-50.
[5] MA, J., CHEN, Y., HAO, X., et al. Study on real-time water demand prediction of winter wheat—Summer corn based on convolutional neural network—Informer combined modeling. Sustainability, 2024, 16(9): 3699. [Google Scholar] [CrossRef] 
[6] WU, W., KANG, Y. Ensemble empirical mode decomposition granger causality test dynamic graph attention transformer network: Integrating transformer and graph neural network models for multi-sensor cross-temporal granularity water demand forecasting. Applied Sciences-Basel, 2024, 14(8): 3428. [Google Scholar] [CrossRef] 
[7] LIU, C., LIU, Z., YUAN, J., et al. Urban water demand prediction based on attention mechanism graph convolutional network-long short-term memory. Water, 2024, 16(6): 831. [Google Scholar] [CrossRef] 
[8] CHEN, L., GAN, X., YI, B., et al. Domestic water demand prediction based on system dynamics combined with social-hydrology methods. Hydrology Research, 2022, 53(8): 1107-1128. [Google Scholar] [CrossRef] 
[9] WANG, X., ZHANG, J., SHAHID, S., et al. Domestic water demand forecasting in the Yellow River basin under changing environment. International Journal of Climate Change Strategies and Management, 2018, 10(3): 379-388. [Google Scholar] [CrossRef] 
[10] LIU, X., QIN, M. and XIANG, X. Forecasting on China’s water demand by industry in 2021. IOP Conference Series: Earth and Environmental Science, 2021, 772(1): 012097. [Google Scholar] [CrossRef] 
[11] 潘梦娜. 改进BP神经网络模型在锦州地区农业灌溉用水预测中应用[J]. 水与水技术, 2025: 124-128.
[12] WADA, Y., FLOERKE, M., HANASAKI, N., et al. Modeling global water use for the 21st century: The water futures and solutions (WFaS) initiative and its approaches. Geoscientific Model Development, 2016, 9(1): 175-222. [Google Scholar] [CrossRef] 
[13] WADA, Y., WISSER, D. and BIERKENS, M. F. P. Global modeling of withdrawal, allocation and consumptive use of surface water and groundwater resources. Earth System Dynamics, 2014, 5(1): 15-40. [Google Scholar] [CrossRef] 
[14] ZHOU, F., BO, Y., CIAIS, P., et al. Deceleration of China’s human water use and its key drivers. Proceedings of the National Academy of Sciences of the United States of America, 2020, 117(14): 7702-7711. [Google Scholar] [CrossRef] [PubMed]
[15] 郑铁刚, 吴茂喜, 张迪, 等. 基于改进长短期记忆网络模型的水库库区水温模拟[J]. 农业工程学报, 2025, 41(3): 144-153.