Regional water allocation is of great importance to regional coordinated development. Therefore, this paper constructs a data-driven model for regional water allocation analysis to address the existing problems of the imbalance between water supply and demand, irrational utilization of water resources and water scarcity. Firstly, a classification of regional water allocation case is constructed through cluster analysis to obtain similar regions with the same salient characteristics. Then, the regions in the same category are divided into regions to be predicted and other regions, and the similarity of water resources allocation between regions to be predicted and other regions is calculated. The Criteria Importance Through Intercriteria Correlation (CRITC) method is used to calculate the weighted values of each index and forecast water demands of regions to be predicted. Finally, an example analysis of water allocation of each city in Hubei province in 2020 was carried out, and the results indicated that when the water allocation of each city in Hubei province was divided into 4 categories, the water allocation characteristics of different cities are presented. The relative errors of the predicted water demand do not exceed 5%, which is highly accurate and can provide decision support for rational water allocation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.