Deep-reinforcement-learning-based water diversion strategy  

作　　者：Qingsong Jiang Jincheng Li Yanxin Sun Jilin Huang Rui Zou Wenjing Ma Huaicheng Guo Zhiyun Wang Yong Liu 

机构地区：[1]State Environmental Protection Key Laboratory of All Materials Flux in River Ecosystems,College of Environmental Sciences and Engineering,Peking University,Beijing,100871,PR China [2]Rays Computational Intelligence Lab,Beijing Inteliway Environmental Ltd.,Beijing,100085,PR China [3]Yunnan Key Laboratory of Pollution Process and Management of Plateau Lake-Watershed,Yunnan Research Academy of Eco-environmental Sciences,Kunming,650034,PR Chin

出　　处：《Environmental Science and Ecotechnology》2024年第1期68-79,共12页环境科学与生态技术（英文）

基　　金：supported by the National Social Science Foundation of China(21AZD060),China;the National Natural Science Foundation of China(51721006),China;the High-Performance Computing Platform of Peking University,China.

摘　　要：Water diversion is a common strategy to enhance water quality in eutrophic lakes by increasing available water resources and accelerating nutrient circulation.Its effectiveness depends on changes in the source water and lake conditions.However,the challenge of optimizing water diversion remains because it is difficult to simultaneously improve lake water quality and minimize the amount of diverted water.Here,we propose a new approach called dynamic water diversion optimization(DWDO),which combines a comprehensive water quality model with a deep reinforcement learning algorithm.We applied DWDO to a region of Lake Dianchi,the largest eutrophic freshwater lake in China and validated it.Our results demonstrate that DWDO significantly reduced total nitrogen and total phosphorus concentrations in the lake by 7%and 6%,respectively,compared to previous operations.Additionally,annual water diversion decreased by an impressive 75%.Through interpretable machine learning,we identified the impact of meteorological indicators and the water quality of both the source water and the lake on optimal water diversion.We found that a single input variable could either increase or decrease water diversion,depending on its specific value,while multiple factors collectively influenced real-time adjustment of water diversion.Moreover,using well-designed hyperparameters,DWDO proved robust under different uncertainties in model parameters.The training time of the model is theoretically shorter than traditional simulation-optimization algorithms,highlighting its potential to support more effective decisionmaking in water quality management.

关 键 词：Dynamic water diversion optimization Deep reinforcement learning Process-based model Explainable decision-making Parameter uncertainty 

分 类 号：TU991[建筑科学—市政工程]