تقرير
Generative Geostatistical Modeling from Incomplete Well and Imaged Seismic Observations with Diffusion Models
العنوان: | Generative Geostatistical Modeling from Incomplete Well and Imaged Seismic Observations with Diffusion Models |
---|---|
المؤلفون: | Erdinc, Huseyin Tuna, Orozco, Rafael, Herrmann, Felix J. |
سنة النشر: | 2024 |
المجموعة: | Computer Science Physics (Other) |
مصطلحات موضوعية: | Physics - Geophysics, Computer Science - Artificial Intelligence, Computer Science - Computer Vision and Pattern Recognition |
الوصف: | 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. |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2406.05136 |
رقم الأكسشن: | edsarx.2406.05136 |
قاعدة البيانات: | arXiv |
كن أول من يترك تعليقا!