Infilling the missing values of groundwater level using time and space series: case of Nantong City, east coast of China

Abstract

Dynamic monitoring data of the groundwater level form an important basis to understand the current state of groundwater development and utilization, which is required to plan its sustainable exploitation. The dynamic data of groundwater level are typical space-time series data with the characteristics of nonlinear strong space-time correlation. However, because of the influences of human or natural factors, long-term monitoring data of the groundwater level are often incomplete to varying degrees. Consequently, the efficiency and accuracy of traditional data in-filling methods for the missing groundwater level data are low. Additionally, restoration methods based on spatio-temporal geostatistics and machine learning are not sufficiently comprehensive to consider spatio-temporal correlations, which results in low restoration accuracy. Therefore, this study was based on an analysis of the characteristics and the missing status of the groundwater level dynamic monitoring data of the pore confined aquifer III of Nantong City, east coast of China. Both the universal Kriging (UK) interpolation method and the support vector regression (SVR) method were used for spatial missing correction and temporal missing correction, respectively. A separable spatial-temporal missing correction coupling model of groundwater level monitoring data was constructed and named UK-SVR. The reliabilities and accuracies of UK-SVR, UK, SVR, and K-nearest neighbor were evaluated by a cross-validation algorithm. The results showed that UK-SVR achieved higher accuracy than other single data-infilling models.