Water resource optimal allocation method based on artificial intelligence algorithm

Abstract

The invention discloses a water resource optimal allocation method based on an artificial intelligence algorithm. The method comprises the following steps that collected hydrometeorology, land utilization types, DEM and hydrogeology are used as input data of a surface water and underground water simulation model, actual measurement data are used for calibrating and verifying related parameters, related model parameters are determined, and a surface water-underground water coupling simulation model is constructed; according to the invention, future climate scene data is combined to predict thewater resource supply and demand of the future area, the water resource supply and demand serves as an input value of the multi-objective planning model, the built multi-objective optimization model is solved through NSGA-II, a reasonable water resource optimal configuration scheme under the future climate change scene is finally obtained, and the method has very important practical significance and practicability.

Description

technical field [0001] The invention relates to the technical field of water resource optimal configuration, in particular to a water resource optimal configuration method based on an artificial intelligence algorithm. Background technique [0002] After entering the 21st century, the contradiction between the growing demand for water resources and the shortage of available water resources is particularly prominent. The lack of available water resources has hindered the process of urbanization and social economic development, and has multiple impacts such as global climate change. Under such circumstances, the sustainable use and management of water resources has become a major problem in today's society; at the same time, due to the uncertainty of the impact of future climate change on regional water resources, based on the combined use of multiple water sources to solve the problem of regional water resources under the influence of future climate change The shortage proble...

AI Technical Summary

Problems solved by technology

[0002] After entering the 21st century, the contradiction between the growing demand for water resources and the shortage of available water resources is particularly prominent. The lack of available water resources has hindered the process of urbanization and social economic development, and has multiple impacts such as global climate change. Under such circumstances, the sustainable use and management of water resources has become a major problem in today's society; at the same time, due to the uncertainty of the impact of future climate change on regional water resources, based on the combined use of multiple water sources to solve the problem of regional water resources under the influence of future climate change Shortages are a huge challenge

[0003] Generally speaking, there are mathematical programming methods, simulation techniques, etc. for the optimal dispatching of water resources. In addition, because the actual water demand forecast and water supply forecast involve various factors, the single use of some mathematical methods can only reflect the Therefore, the predicted results will be different from the actual water consumption

The traditional water resources optimal allocation technology is mainly based on the analysis of historical data, using statistical analysis or empirical methods to predict the amount of water available and the water demand of various departments, which lacks precision and rarely considers the impact of future climate change on water resource allocation. Impact

[0004] In addition, the water resource system is a complex and uncertain dynamic system; natural processes such as rainfall and runoff lead to random uncertainties in the amount of water resources, and traditional water resource systems rarely study climate change under uncertain conditions impact on the allocation of water resources; at the same time, the existing multi-objective programming models mostly use the weight method, which is transformed into a single-objective model for solution, and the determination of the weight is highly subjective

Images