Xinming Wu

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

Abstract. Diffusion models provide a promising way to model the distribution of implicit structural models, potentially improving generalization across surveys. However, existing diffusion Transformer pipelines scale poorly to high-dimensional geophysical data because noise- or v...

Deep Learning-based Seismic Reflectivity Estimation by Pre-training on Labeled Synthetic Data and Physics-guided Fine-tuning in Field Data

Summary Reflectivity estimation aims to enhance the resolution of seismic data, providing crucial support for the detailed inversion of reservoir parameters. We propose a method that combines supervised pre-training with synthetic data and physics-guided fine-tuning in field data...

Massive-scale unlabeled field and labeled synthetic seismic datasets of global shelf-edge clinothems

Summary Seismic stratigraphic interpretation of shelf-edge clinothems is essential for revealing tectonic evolution, paleoclimate change, depositional dynamic conditions, and hydrocarbon generation and accumulation during basin filling. However, traditional interpretation methods...