基于图卷积STG-LSTM的京杭运河水质时空预测研究

Research on the Temporal and Spatial Prediction of the Water Quality of Beijing-Hangzhou Canal Based on Graph Convolution STG-LSTM

快速精准预测河流水质是城市水管理战略的重要任务,而河流水质因子具有时序性、不稳定性和非线性等特点且受多种因素影响,会造成时空维度上分布差异。针对现有水质因子预测方法大多是单监测站点的时间序列预测,无法描述河流水质因子的空间分布,提出一种基于时空图卷积融合长短记忆神经网络的河流水质时空预测模型(STG-LSTM)。以各监测站点地理位置和水质因子历史观测值为依据,构建时空图来表征各监测站点间的时空相关性。将时空图输入到STG-LSTM模型中,采用图卷积(GCN)提取河流水质数据空间依赖关系,并融合长短时记忆神经网络(LSTM)来获取水质因子数据的时空关联性,实现对未来一段时间运河河段不同位置水质状态的时空预测。用京杭运河常州段上8个监测站点4种不同水质因子数据集进行验证,从预测精度和训练时间两方面,将模型和其他6种预测模型进行比较,并对模型进行可靠性测试。实验结果表明,STG-LSTM模型能以较短的训练时间得到较高的预测精度,实现了对河流不同位置水质的快速精准预测,为城市水管理提供技术支撑。

Rapid and accurate prediction of river water quality is an important task of urban water management strategy.However,River wa‐ter quality factors have the characteristics of time series,instability,and nonlinearity,and are affected by many factors,which will cause dif‐ferences in spatial and temporal dimensions.Most of the existing water quality factor forecasting methods are time series forecasting at a sin‐gle monitoring station,which cannot describe the spatial distribution of river water quality factors.In this paper,we proposes a spatiotempo‐ral prediction model of river water quality(STG-LSTM)on account of spatio-temporal graph convolution and long-short-term memory neu‐ral network.Based on the historical observation values of the geographic location and water quality factors of each monitoring station,con‐struct a time-space map to characterize the time-space correlation between each monitoring station.Input the space-time diagram into the STG-LSTM model,using graph convolution(GCN)to obtain the spatial dependence of river water quality factor data and fusing the long and short-term memory neural network(LSTM)to obtain the spatio-temporal correlation of the water quality factor data,we realized the future period temporal and spaltial prediction of water quality at different locations in the canal section.The data sets of four different water quality factors at eight monitoring stations on the Changzhou section of the Beijing-Hangzhou Canal were used for verification.The model was com‐pared with six other prediction models in terms of prediction accuracy and training time,and the reliability of the model was tested.The ex‐perimental results show that STG-LSTM can obtain high prediction accuracy with a short training time and realize rapid and accurate predic‐tion of water quality at different locations of the river.Most but not the least,they provide technical support for urban water management.