Lithological Mapping and Uncertainty Quantification
• Lithological Mapping Using Aeromagnetic and Gravity Data,
• Swin Transformer–Based U-Shaped Network,
• Theoretical Analysis of Uncertainty Sources.
Ding, L., Bellefleur, G., Boulanger, O., & Vo, P. (2026). Supervised Swin Transformer-based predictive lithological mapping and uncertainty quantification using aeromagnetic and gravity data. Journal of Geophysical Research: Machine Learning and Computation, 3, e2025JH000882. https://doi.org/10.1029/2025JH000882
Read the full article →Seismic Data Denoising with Deep Learning
• Sparse-domain, image-to-image seismic denoising,
• Swin-Transformer-enhanced UNet,
• Strong, dataset-agnostic performance gains.
Ding, L., Bellefleur, G., & Cheraghi, S., (2026). Seismic Data Denoising in Sparse Representation Domains with a Swin Transformer-Based UNet. Journal of Applied Geophysics, 255, 106534. https://doi.org/10.1016/j.jappgeo.2026.106534
Read the full article →