Geophysical Research Letters· 2025Q1
Imaging Hyporheic Exchange by Integrating Deep Learning and Physics‐Informed Inversion of Time‐Lapse Self‐Potential Data
- 24citations
- Q1SCImago
- 2025year
Short summary
A novel framework combines physics-informed inversion with a Vision Transformer (ViT) deep learning model to image dynamic hyporheic exchange zones from time-lapse self-potential (SP) data.
AI-generated from the title and abstract; the full text is not read.
Key points
- A hybrid framework integrates physics-informed inversion and a Vision Transformer (ViT) deep learning model for SP data analysis.
- The ViT model is trained on dipole moment tomography grids derived from numerical inversion of time-lapse SP data.
- The approach maps surface SP sequences to 2D source distributions, capturing both transient and persistent subsurface flow features.
- This method enhances interpretability, generalization, and temporal awareness in SP analysis for hyporheic exchange imaging.
AI-generated from the title and abstract; the full text is not read.
Abstract
Abstract Self‐potential (SP) monitoring is increasingly used for subsurface flow characterization due to its sensitivity to hydrogeological and geochemical processes. However, SP inversion remains challenging due to its ill‐posed nature, sparse data coverage, and strong transient noise. This study proposes a hybrid framework to image hyporheic exchange using a time‐lapse SP data set monitored from a streamflow site in Oak Ridge, Tennessee. Dipole moment tomography grids generated from the physics‐informed numerical inversion is first used to train a Vision Transformer (ViT) model that maps surface SP sequences to 2D source distributions. While the numerical method is more responsive to transient signals, the ViT model better captures persistent spatial structures. Their complementary outputs are jointly analyzed in the spatiotemporal domain to isolate dynamic hyporheic exchange zones and distinguish transient from steady state subsurface flow features. This approach integrates physical inversion and deep learning to enhance interpretability, generalization, and temporal awareness in SP analysis.
The authors' abstract, as published at the source. Geophysical Research Letters, 2025 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
GeophysicsEarth and Planetary Sciences