摘要
区域用水量影响要素及其关联规则识别对于合理预测用水需求和优化配置水资源具有重要意义。本文基于珠三角地区历年水资源开发利用数据和经济社会发展统计数据,利用随机森林(RF,random forest)和人工神经网络(ANN,artificial neural network)两种机器学习模型,并综合采用SHAP(shapley additive explanations)和部分依赖图(PDP,partial dependence plots)方法,系统识别了珠三角地区用水量影响要素及其与用水量的关联规则,揭示了各影响要素贡献度的时空变化特征。结果表明:用水量影响要素按重要度排序依次是GDP、人口规模、耕地面积、人均水资源量、农田实灌单位面积平均用水量、城镇人均生活用水量;ANN模型和RF模型决定系数平均值分别在0.94和0.92以上;用水量影响要素空间上呈现中心城市以人口为主导、周边地区以耕地面积为主导的特点;珠三角地区用水量对于人口规模和耕地面积变化的响应最为明显。研究可为珠三角地区未来用水需求预测以及水资源空间均衡配置提供科学依据与技术支撑。
Identifying the factors that influence regional water use and the corresponding regulations is crucial for accurately predicting water demand and optimizing the allocation of water resources.This study collected historical data on water resource exploitation and socio-economic statistics in the Pearl River Delta(PRD)region.Two machine learning models,namely Random Forest(RF)and Artificial Neural Network (ANN), were employed to systematically identify the factors affecting water use andto uncover the associated rules in the PRD region. In addition, Shapley Additive Explanations (SHAP)and Partial Dependence Plots (PDP) were applied to enhance the interpretability of the modelingoutcomes. The results indicate that the factors influencing water use, in order of importance, are GDP,population size, cultivated land area, per capita water resources, water consumption for actualirrigation per unit of farmland, and urban per capita domestic water use. The average determinationcoefficients of ANN and RF models are above 0.94 and 0.92, respectively. Regarding water usefactors, population is the dominant influence in the central cities, while cultivated land is the principalfactor in the surrounding areas. Water use in the PRD region shows the most significant response to thechanges in population size and cultivated land area. This research provides a scientific basis andtechnical support for the future prediction of water demand and the balanced allocation of waterresources in the PRD region.
作者
郑炎辉
徐小迪
李俊辉
林树彦
何艳虎
ZHENG Yanhui;XU Xiaodi;LI Junhui;LIN Shuyan;HE Yanhu(College of Ecological Environment and Resources,Guangdong University of Technology,Guangzhou 510006,China;Guangdong Key Laboratory of River Basin Water Environment Management and Water Ecological Restoration,Guangzhou 510006,China;Guangzhou Fengzeyuan Water Technology Co.,Ltd.,Guangzhou 510663,China;School of Environmental Science and Engineering,Southern University of Science and Technology,Shenzhen 518055,China)
出处
《中山大学学报(自然科学版)(中英文)》
北大核心
2025年第2期22-32,共11页
Acta Scientiarum Naturalium Universitatis Sunyatseni
基金
国家自然科学基金(52209025,51979043)
2024年省级水资源节约与保护专项项目
水利部粤港澳大湾区水安全保障重点实验室开放基金(WSGBA-KJ202302)。
