摘要
洪涝数值模型是当前城市内涝风险分析和预报预警的主要技术手段,然而数值模型的计算速度较慢,难以满足日常防汛应急的需求。如何将人工智能技术,引入到训练样本及标注数据较少的城市积水内涝快速预测中,是个重点关注且亟待解决的问题。针对这个问题,本文将具有良好计算精度数值模型与具有较高计算效率的BP人工神经网络模型相结合,提出了一种快速预测城市内涝风险的新方法。本方法以城市洪涝模型的模拟结果作为数据驱动,构建各积水点的BP神经网络预测模型。结果表明,该方法预测精度高,计算速度快,可以满足日常防汛应急的需要,为人工智能技术在防洪减灾方向的应用提供了新的思路。
Numerical simulation model is the main technical method to analyze and simulate urban flooding,forecast and early warning.However,the computational efficiency of numerical mode cannot meet the needs of urban rainstorm risks.How to introduce artificial intelligence technology into the rapid prediction of urban flooding with less training samples and labeled data is a key concern and urgent problem to be solved.To solve this problem,this paper proposes a new method for rapid prediction of urban flooding by combining the numerical model with good calculation accuracy and the artificial neural network model with high computational efficiency.Based on the simulation results of numerical model as training samples,the neural network prediction model is constructed to simulate the process of urban flooding.The results show that this method has high prediction accuracy and fast calculation speed,which can meet the needs of daily flood control and emergency response,and provides a new idea for the application of artificial intelligence technology in flood control and disaster reduction.
作者
刘媛媛
刘业森
郑敬伟
柴福鑫
李敏
穆杰
LIU Yuanyuan;LIU Yesen;ZHENG Jingwei;CHAI Fuxin;LI Min;MU Jie(China Institute of Water Resources and Hydropower Research,Beijing 100038,China;Research Center on Flood and Drought Disaster Reduction of the Ministry of Water Resources,Beijing 100038,China)
出处
《水利学报》
EI
CSCD
北大核心
2022年第3期284-295,共12页
Journal of Hydraulic Engineering
基金
国家自然科学基金项目(52009147)。
关键词
人工智能
BP神经网络
洪涝模型
城市内涝
快速预测
artificial intelligence technology
BP neural network
numerical simulation
urban waterlogging
rapid prediction
