Multimodal Interaction and Residual Fusion for Cross-Well Acoustic-Impedance Reconstruction
- 1School of Overseas Education, Changzhou University, Changzhou 213164, China
Abstract
Cross-well acoustic-impedance reconstruction combines seismic observations with retained auxiliary logs whose relationships change between wells. We introduce Multimodal Interaction and Residual Fusion (MIRF), which expresses multimodal fusion as an additive correction to a source-supervised seismic estimate. Three residual heads propose updates, a conditional router determines their composition, and an admission coefficient controls the applied magnitude. Separate anchor supervision retains a seismic reference for examining the effect of auxiliary-log correction. Using the original processed-log protocol on Penobscot L-30 to B-41 transfer, ten matched seeds reduce mean root mean squared error (RMSE) from 1905.5 to 1489.6 kRayl and mean absolute error from 1659.5 to 1178.4 kRayl relative to the standalone seismic CNN. MIRF also has the lowest mean RMSE among four matched neural fusion alternatives in this direction. Bidirectional comparisons, ablations, and depth-resolved profiles locate the benefits in reduced broad reconstruction bias and show how component effects change with transfer direction.
Related
- Direction-Aware Masked Pretraining on 3D Seismic Data with Transfer to Cross-Area Acoustic Impedance Inversion
- Reconstruction of landslide events in urban setting using LLM-based Agentic AI with multimodal data
- Bayesian Joint Velocity and Impedance Inversion via Diffusion Models Conditioned on Common Image Gathers
- Characterization of Coal Fly Ash by Electrical Impedance Spectroscopy, Magnetic Susceptibility and Mössbauer Phase Composition.
- Multi-frequency seismo-acoustic measurements of synthetic ice with fluid inclusions: implications for seismic and through-ice acoustic estimation of sea-ice thickness
BibTeX
@article{rui2026multimodal,
title = {{Multimodal Interaction and Residual Fusion for Cross-Well Acoustic-Impedance Reconstruction}},
author = {Xue Rui and Weina Zhang and Jing Ren and Chenyang Zhu and Yunxin Xie},
journal = {Applied Sciences},
year = {2026},
month = oct,
doi = {10.3390/app162010311},
url = {https://doi.org/10.3390/app162010311},
note = {CC BY},
}
RIS
TY - JOUR
TI - Multimodal Interaction and Residual Fusion for Cross-Well Acoustic-Impedance Reconstruction
AU - Xue Rui
AU - Weina Zhang
AU - Jing Ren
AU - Chenyang Zhu
AU - Yunxin Xie
PY - 2026
DA - 2026/10/26
JO - Applied Sciences
DO - 10.3390/app162010311
UR - https://doi.org/10.3390/app162010311
AB - Cross-well acoustic-impedance reconstruction combines seismic observations with retained auxiliary logs whose relationships change between wells. We introduce Multimodal Interaction and Residual Fusion (MIRF), which expresses multimodal fusion as an additive correction to a source-supervised seismic estimate. Three residual heads propose updates, a conditional router determines their composition, and an admission coefficient controls the applied magnitude. Separate anchor supervision retains a seismic reference for examining the effect of auxiliary-log correction. Using the original processed-log protocol on Penobscot L-30 to B-41 transfer, ten matched seeds reduce mean root mean squared error (RMSE) from 1905.5 to 1489.6 kRayl and mean absolute error from 1659.5 to 1178.4 kRayl relative to the standalone seismic CNN. MIRF also has the lowest mean RMSE among four matched neural fusion alternatives in this direction. Bidirectional comparisons, ablations, and depth-resolved profiles locate the benefits in reduced broad reconstruction bias and show how component effects change with transfer direction.
SN - 2076-3417
ER -