SubsurfaceGen generates realistic seismic data for ML-based FWI

Researchers have developed SubsurfaceGen, a GPU-accelerated tool for generating realistic, field-scale 3D velocity models and seismic data. This new system addresses limitations in existing datasets for machine learning approaches to full waveform inversion (FWI). The accompanying dataset includes 4,276 2D velocity slices and seismic data from 42 diverse geological settings, designed to improve ML-based FWI for applications like carbon sequestration and hydrocarbon exploration. AI

IMPACT Enables more realistic training data for ML models in subsurface imaging, potentially improving accuracy in energy exploration and hazard assessment.

RANK_REASON The cluster contains an academic paper detailing a new method and dataset for machine learning applications. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• full waveform inversion (FWI)
• OpenFWI
• SEAM
• SubsurfaceGen

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →