paper-with-me

Papers

Generative Geostatistical Modeling from Incomplete Well and Imaged Seismic Observations with Diffusion Models

2024-05-16 · Huseyin Tuna Erdinc, Rafael Orozco, Felix J. Herrmann

In this study, we introduce a novel approach to synthesizing subsurface velocity models using diffusion generative models. Conventional methods rely on extensive, high-quality datasets, which are often inaccessible in subsurface applications. Our method leverages incomplete well and seismic observations to produce high-fidelity velocity samples without requiring fully sampled training datasets. The results demonstrate that our generative model accurately captures long-range structures, aligns with ground-truth velocity models, achieves high Structural Similarity Index (SSIM) scores, and provides meaningful uncertainty estimations. This approach facilitates realistic subsurface velocity synthesis, offering valuable inputs for full-waveform inversion and enhancing seismic-based subsurface modeling.

📄 PDF Abstract BibTeX arXiv:2406.05136

Code (0)

등록된 구현이 없습니다.

Tasks

SSIM

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Physics-informed semantic inpainting: Application to geostatistical modeling

2019-09-19 · Qiang Zheng, Lingzao Zeng, Zhendan Cao, George Em. Karniadakis

A fundamental problem in geostatistical modeling is to infer the heterogeneous geological field based on limited measurements and some prior spatial statistics. Semantic inpainting, a technique for image processing using…

Generative Adversarial Network

Leveraging generative adversarial networks with spatially adaptive denormalization for multivariate stochastic seismic data inversion

2025-12-02 · Roberto Miele, Leonardo Azevedo arxiv

Probabilistic seismic inverse modeling often requires the prediction of both spatially correlated geological heterogeneities (e.g., facies) and continuous parameters (e.g., rock and elastic properties). Generative advers…

SAGE: Subsurface AI-driven Geostatistical Extraction with proxy posterior

2026-03-31 · Huseyin Tuna Erdinc, Ipsita Bhar, Rafael Orozco, Thales Souza 외 arxiv

Recent advances in generative networks have enabled new approaches to subsurface velocity model synthesis, offering a compelling alternative to traditional methods such as Full Waveform Inversion. However, these approach…

DeepFlow: History Matching in the Space of Deep Generative Models

2019-05-14 · Lukas Mosser, Olivier Dubrule, Martin J. Blunt

The calibration of a reservoir model with observed transient data of fluid pressures and rates is a key task in obtaining a predictive model of the flow and transport behaviour of the earth's subsurface. The model calibr…

Generative Adversarial Network

Mitigation of Spatial Nonstationarity with Vision Transformers

2022-12-09 · Lei Liu, Javier E. Santos, Maša Prodanović, Michael J. Pyrcz

Spatial nonstationarity, the location variance of features' statistical distributions, is ubiquitous in many natural settings. For example, in geological reservoirs rock matrix porosity varies vertically due to geomechan…

Deep Learning