Physics‐Guided Deep Learning Model for Daily Groundwater Table Maps Estimation Using Passive Surface‐Wave Dispersion
Tallennettuna:
| Julkaisussa: | Water Resources Research vol. 61, no. 1 (Jan 1, 2025) |
|---|---|
| Päätekijä: | |
| Muut tekijät: | , , , , , , |
| Julkaistu: |
John Wiley & Sons, Inc.
|
| Aiheet: | |
| Linkit: | Citation/Abstract Full Text Full Text - PDF |
| Tagit: |
Ei tageja, Lisää ensimmäinen tagi!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3160336957 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 0043-1397 | ||
| 022 | |a 1944-7973 | ||
| 024 | 7 | |a 10.1029/2024WR037706 |2 doi | |
| 035 | |a 3160336957 | ||
| 045 | 0 | |b d20250101 | |
| 084 | |a 107315 |2 nlm | ||
| 100 | 1 | |a Cunha Teixeira, José |u CNRS, EPHE, UMR 7619 METIS, Sorbonne Université, Paris, France | |
| 245 | 1 | |a Physics‐Guided Deep Learning Model for Daily Groundwater Table Maps Estimation Using Passive Surface‐Wave Dispersion | |
| 260 | |b John Wiley & Sons, Inc. |c Jan 1, 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a Monitoring groundwater tables (GWTs) remains challenging due to limited spatial and temporal observations. This study introduces an innovative approach combining an artificial neural network, specifically a multilayer perceptron (MLP), with continuous passive Multichannel Analysis of Surface Waves (passive‐MASW) to construct GWT depth maps. The geologically well‐constrained study site includes two piezometers and a permanent 2D geophone array recording train‐induced surface waves. At each point of the array, dispersion curves (DCs), displaying Rayleigh‐wave phase velocities VR $\left({V}_{R}\right)$ over a frequency range of 5–50 Hz, were measured daily from December 2022 to September 2023, and latter resampled over wavelengths from 4 to 15 m, to focus on the expected GWT depths (1–5 m). Nine months of daily VR ${V}_{R}$ data near one piezometer, spanning both low and high water periods, were used to train the MLP model. GWT depths were then estimated across the geophone array, producing daily GWT maps. The model's performance was evaluated by comparing inferred GWT depths with observed measurements at the second piezometer. Results show a coefficient of determination (R2) of 80% at the training piezometer and of 68% at the test piezometer, and a remarkably low root‐mean‐square error (RMSE) of 0.03 m at both locations. These findings highlight the potential of deep learning to estimate GWT maps from seismic data with spatially limited piezometric information, offering a practical and efficient solution for monitoring groundwater dynamics across large spatial extents. | |
| 653 | |a Seismic waves | ||
| 653 | |a Observational learning | ||
| 653 | |a Resource management | ||
| 653 | |a Multilayer perceptrons | ||
| 653 | |a Artificial neural networks | ||
| 653 | |a Neural networks | ||
| 653 | |a Dispersion | ||
| 653 | |a Hazard assessment | ||
| 653 | |a Wave dispersion | ||
| 653 | |a Groundwater | ||
| 653 | |a Water monitoring | ||
| 653 | |a Environmental management | ||
| 653 | |a Water resources management | ||
| 653 | |a Groundwater table | ||
| 653 | |a Ambient noise | ||
| 653 | |a Seismic velocities | ||
| 653 | |a Wave data | ||
| 653 | |a Training | ||
| 653 | |a Root-mean-square errors | ||
| 653 | |a Seismological data | ||
| 653 | |a Wave phase | ||
| 653 | |a Piezometers | ||
| 653 | |a Water table | ||
| 653 | |a Wavelengths | ||
| 653 | |a Dispersion curve analysis | ||
| 653 | |a Water resources | ||
| 653 | |a Seismic activity | ||
| 653 | |a P-waves | ||
| 653 | |a Deep learning | ||
| 653 | |a Maps | ||
| 653 | |a Two dimensional analysis | ||
| 653 | |a Frequency ranges | ||
| 653 | |a Wave velocity | ||
| 653 | |a Surface waves | ||
| 653 | |a Physics | ||
| 653 | |a Noise monitoring | ||
| 653 | |a Depth | ||
| 653 | |a Groundwater levels | ||
| 653 | |a Environmental hazards | ||
| 653 | |a Sensor arrays | ||
| 653 | |a Estimation errors | ||
| 653 | |a Seismic data | ||
| 653 | |a Spatial discrimination learning | ||
| 653 | |a Estimation | ||
| 653 | |a Environmental | ||
| 700 | 1 | |a Bodet, Ludovic |u CNRS, EPHE, UMR 7619 METIS, Sorbonne Université, Paris, France | |
| 700 | 1 | |a Rivière, Agnès |u Geosciences Department, Mines Paris—PSL, PSL University, Paris, France | |
| 700 | 1 | |a Hallier, Amélie |u SNCF Réseau, Saint‐Denis, France | |
| 700 | 1 | |a Gesret, Alexandrine |u Geosciences Department, Mines Paris—PSL, PSL University, Paris, France | |
| 700 | 1 | |a Dangeard, Marine |u SNCF Réseau, Saint‐Denis, France | |
| 700 | 1 | |a Dhemaied, Amine |u SNCF Réseau, Saint‐Denis, France | |
| 700 | 1 | |a Boisson Gaboriau, Joséphine |u SNCF Réseau, Saint‐Denis, France | |
| 773 | 0 | |t Water Resources Research |g vol. 61, no. 1 (Jan 1, 2025) | |
| 786 | 0 | |d ProQuest |t ABI/INFORM Global | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3160336957/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text |u https://www.proquest.com/docview/3160336957/fulltext/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3160336957/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |