A short-term flood prediction based on spatial deep learning network: A case study for Xi County, China
A short-term flood prediction based on spatial deep learning network: A case study for Xi County, China
复制标题
DOI：
10.1016/j.jhydrol.2022.127535
复制
发表时间：
2022-02-07
影响因子：
6.4
通讯作者：
Pei, Qingqi
中科院分区：
文献类型：
--
作者：
Chen, Chen;Jiang, Jiange;Pei, Qingqi
洪水每年都会在世界各地造成重大损失。准确、及时的洪水预报可以极大地减少生命和财产损失。最近，许多机器学习模型已被用于洪水预测，表明它们的性能优于传统的统计模型。然而，现有模型忽略了洪水的空间特征，从而驱动洪水的产生和集中。本文根据经纬度将感兴趣区域划分为网格，并根据站点坐标将站点收集的降雨量和流量组合成张量。与一维时间序列不同，我们的输入特征是带有空间信息的二维时间序列。因此，将卷积神经网络（CNN）与长短期记忆网络（LSTM）相结合，我们提出了卷积LSTM（ConvLSTM）来提取水文信息的时空特征。该方法通过在中国河南省淮河沿岸的息县站收集的水文数据进行了验证。数值结果表明，到达时间相对误差在30%以内，洪峰流量相对误差在20%以内，满足2005年《中国水资源标准》洪水预报允许误差。实验还表明，ConvLSTM 在洪水到达时间和峰值流量方面优于最新模型，从而证明是一种有前途的替代方案。
Floods cause substantial damage across the world every year. Accurate and timely prediction of floods can significantly minimize the loss of life and property. Recently, numerous machine learning models have been used for flood prediction, showing that their performance is preferable to traditional statistical models. However, the existing models neglect the spatial features of floods, which drive flood generation and concentration. In this paper, the area of interest is divided into grids based on longitude and latitude, and the rainfall and discharge collected by stations are combined into tensors according to station coordinates. Different from one-dimensional time series, our input feature is a two-dimensional time series with spatial information. Hence, combining a Convolutional Neural Network (CNN) with a Long Short Term Memory Network (LSTM), we propose the convolution LSTM (ConvLSTM) to extract spatiotemporal features of hydrological information. The methodology is demonstrated using the hydrological data collected at the Xi County stations, located on the Huai River in Henan Province, China. Numerical results indicate that the relative error of arrival time is within 30%, and the relative error of peak discharge is within 20%, satisfying the 2005 Chinese Water Resource Standard on flood prediction permit error. The experiments also show that the ConvLSTM outperforms the recent models in terms of flood arrival time and peak discharge, thereby proving a promising alternative.