DataSheet1_Groundwater monitoring and specific yield estimation using time-lapse electrical resistivity imaging and machine learning.pdf

This paper presents an alternative method for monitoring groundwater levels and estimating specific yields of an unconfined aquifer under different seasonal conditions. The approach employs the Time-Lapse Electrical Resistivity Imaging (TL-ERI) method and machine learning-based time series clustering. A TL-ERI survey was conducted at ten sites (WS01-WS10 sites) throughout the dry and wet seasons, with five-time measurements collected for each site, in the Taichung-Nantou Basin along the Wu River, Central Taiwan. The obtained resistivity raw data was inverted and converted into normalized water content values using Archie’s law, followed by applying the Van Genuchten (VG) model for the Soil Water Characteristic Curve to estimate the Groundwater Level (GWL), and estimated the theoretical specific yield (Sy) by computing the difference between the saturated and residual water contents of the fitted VG model. In addition, the specific yield capacity (Sc), representing the nature of the storage capacity in the aquifer, was also calculated. The results showed that this approach was able to estimate those hydrogeological parameters. The spatial distribution of the GWL reveals that during the dry-wet seasons from February to July, there was a high GWL that extended from southeast to northwest. Conversely, during the wet-dry seasons from July to October, the high GWL shrank, which can be attributed to recharge variations from rainfall events. The determined spatial distribution of Sy and Sc fall within the range of 0.03–0.24 and 0.14–0.25, respectively. To quantitatively establish areas of similar groundwater level changes along with the VG model parameter variations during the study period, a Time series Clustering analysis (TSC) was performed by utilizing Hierarchical Agglomerative Clustering (HAC). The findings suggest that the WS03 site is a promising area for further investigation due to its highest Sc value with a slight change in groundwater levels during the dry and wet seasons. This study brings an advanced development of the geoelectrical method to estimate regional hydrogeological parameters in an area with limited available groundwater observation wells, in different seasonal conditions for groundwater management purposes.

本文提出了一种监测地下水水位和估算无压含水层在不同季节条件下特定产水量的替代方法。该方法采用时间推移电阻率成像（TL-ERI）技术和基于机器学习的时间序列聚类。在中央台湾乌溪流域的台中-南投盆地，对十个地点（WS01-WS10地点）在干季和湿季进行了TL-ERI调查，每个地点收集了五次测量数据。通过阿奇定律将获得的电阻率原始数据反演并转换为标准化含水率值，随后应用范·根滕（VG）模型对土壤水分特征曲线进行处理，以估算地下水位（GWL），并通过计算拟合VG模型的饱和含水率和残余含水率之差来估算理论特定产水率（Sy）。此外，还计算了代表含水层储存能力性质的特定产水率容量（Sc）。结果表明，该方法能够估算这些水文地质参数。地下水位的空间分布揭示了从二月到七月干湿季节期间，存在从东南向西北延伸的高地下水位。相反，从七月到十月的湿干季节期间，高地下水位缩小，这可以归因于降雨事件的补给变化。确定的Sy和Sc的空间分布分别位于0.03–0.24和0.14–0.25范围内。为了在研究期间定量建立具有类似地下水位变化以及VG模型参数变化的区域，利用层次聚类法（HAC）进行了时间序列聚类分析（TSC）。研究结果表明，WS03地点由于其Sc值最高，且在干湿季节期间地下水位略有变化，是一个值得进一步研究的潜在区域。本研究将地球物理方法的高级发展应用于估算有限地下水观测井的区域内区域水文地质参数，旨在不同季节条件下进行地下水管理。