Articles | Volume 19, issue 16
https://doi.org/10.5194/gmd-19-7961-2026
https://doi.org/10.5194/gmd-19-7961-2026
Development and technical paper
 | 
26 Aug 2026
Development and technical paper |  | 26 Aug 2026

LFD (v1.0): latent-compression-free generative diffusion with geological priors and geophysical regularization for implicit structural modeling

Zhixiang Guo, Xinming Wu, Yimin Dou, Hui Gao, and Guillaume Caumon

Model code and software

Code from "Latent-Compression-Free Generative Diffusion with Geological Priors and Geophysical Regularization for Implicit Structural Modeling" Zhixiang Guo et al. https://doi.org/10.5281/zenodo.20508635

Download
Short summary
We present a fast way to generate subsurface structure models from seismic surveys while honoring known horizons and faults. Instead of compressing the data into a hidden representation, our method works directly with the original model values and applies geological constraints during generation. Tests on synthetic and real surveys show more realistic structures and efficient prediction, producing a 512 by 512 model in 1.56 seconds on an NVIDIA H20 graphics processing unit.
Share