Monitoring groundwater tables (GWTs) is challenging due to limited spatial and temporal observations. This study presents an innovative approach utilizing supervised deep learning, specifically a Multilayer Perceptron (MLP), and continuous passive-Multichannel Analysis of Surface Waves (passive-MASW) for constructing 2D GWT level maps. The study site, geologically well-constrained, features two 20-meter-deep piezometers and a permanent 2D geophone array capturing train-induced surface waves. For each point of the 2D array, dispersion curves (DCs), displaying Rayleigh-wave phase velocities (V_R) across a frequency range of 5 to 50 Hz, have been computed each day between December 2022 and September 2023. In the present study, these DCs are resampled in wavelengths ranging from 4 to 15~m in order to focus the monitoring on the expected GWT levels (between -1 and -5 m). Nine months of daily V_R data around one of the two piezometers is used to train the MLP model. GWT levels are then estimated across the entire geophone array, generating daily 2D GWT maps. Model’s performance is tested through cross-validation and comparisons with GWT level data at the second piezometer. Model’s efficiency is quantified with the root-mean-square error (RMSE) and the coefficient of determination (R²). The R² is estimated at 80% for data surrounding the training piezometer, and at 68% for data surrounding the test piezometer. Additionally, the RMSE is impressively low at 0.03 m at both piezometers. Results showcase the effectiveness of DL in estimating GWT level maps from passive-MASW data, offering a practical and efficient monitoring solution across broader spatial extents.

Estimating evolution of exchanges within the stream-aquifer interface is frequently tackled with the help of numerical models. Yet, the definition of boundary conditions is generally based on poorly constrained assumptions and restrained to the location of piezometers. We suggest here to stretch the modeling domain and build stronger constraints, both in space and time, by using a multi-method approach. On a hotspot of the Orgeval Critical Zone observatory (France), we show how a thorough interpretation of high-resolution geophysical images, combined with geotechnical data, helps describing the spatial heterogeneities of the shallow aquifer. It provides a detailed distribution of hydrofacies, valuable prior information about the associated hydrodynamic properties and makes it possible to expand the modeling window in space. We show how the local temporal dynamic of the water table can be captured with high resolution time-lapse seismic acquisitions. Time-lapse variations in seismic data are discriminated from noise or measurement errors to be interpreted, regarding hydrological observations, as temporal changes in the saturated-unsaturated zone continuum. Each seismic snapshot is then thoroughly inverted to actually image spatial water content variations and delineate the water table outside the limits defined by the piezometers. This posterior geophysical information is then suggested as initial and boundary conditions of the expanded hydrogeological modeling domain. We finally calibrate and provide plausible ranges of hydraulic parameters to reproduce the water table and improve the estimation of stream-aquifer exchanges.