基于机器学习的深圳湾水质预报  

Machine Learning-based Water Quality Forecasting for Shenzhen Bay

作　　者：熊剑智 熊睿 鲁海燕 郑一 XIONG Jianzhi;XIONG Rui;LU Haiyan;ZHENG Yi(Eco-Environmental Monitoring and Research Center,Pearl River Valley and South China Sea Ecology and Environment Administration,Ministry of Ecology and Environment,Guangzhou 510611,China;School of Environmental Science and Engineering,Southern University of Science and Technology,Shenzhen 518055,China;The Open Research Fund of Key Laboratory of Water Security Guarantee in Guangdong-Hong Kong-Marco Greater Bay Area of Ministry of Water Resources,Guangzhou 510611,China)

机构地区：[1]生态环境部珠江流域南海海域生态环境监督管理局生态环境监测与科学研究中心,广东广州510611 [2]南方科技大学环境科学与工程学院,广东深圳518055 [3]水利部粤港澳大湾区水安全保障重点实验室,广东广州510611

出　　处：《人民珠江》2024年第7期10-18,共9页Pearl River

基　　金：水利部粤港澳大湾区水安全保障重点实验室开放基金资助项目(WSGBA-KJ202304)。

摘　　要：基于深圳湾浮标在线监测系统采集的高频监测数据,测试人工神经网络(Artificial Neural Network,ANN)、支持向量回归(Support Vector Regression,SVR)和随机森林(Rendom Forest,RF)等机器学习方法,对溶解氧(DO)、叶绿素a(Chl.a)、总氮(TN)和总磷(TP)等水质参数进行短期预报。研究结果表明:利用高频原位水质监测数据,机器学习可实现深圳湾24 h内水质的准确预报,其中,ANN最适合DO、Chl.a和TN的预报,24 h内预报结果的纳什系数(NSE)值均大于0.60,而RF模型最适合TP的预报,24 h内的NSE值均大于0.76。研究结论为粤港澳大湾区的水污染精准防治提供了方法支撑。Based on high-frequency monitoring data collected by the buoy online monitoring system in Shenzhen Bay,machine learning methods including artificial neural networks(ANN),support vector regression(SVR),and random forest(RF)are employed to conduct short-term forecasting of water quality parameters such as dissolved oxygen(DO),chlorophyll-a(Chl.a),total nitrogen(TN),and total phosphorus(TP).The research findings indicate that utilizing high-frequency in-situ water quality monitoring data enables accurate prediction of water quality in Shenzhen Bay within 24 hours.Specifically,ANN is found to be the most suitable for forecasting DO,Chl.a,and TN,with nash-sutcliffe efficiency(NSE)values greater than 0.60 for the 24-hour forecast period.Meanwhile,the RF model is found to be the most suitable for TP forecasting,with NSE values greater than 0.76 within 24 hours.The findings of this study have important implications for the precise prevention and control of water pollution in the Guangdong-Hong Kong-Macao Greater Bay Area.

关 键 词：水质预报 机器学习 深圳湾 

分 类 号：TV21[水利工程—水文学及水资源]