基于扩散模型的不完整井与成像地震观测生成地质统计建模
Generative Geostatistical Modeling from Incomplete Well and Imaged Seismic Observations with Diffusion Models
AI总结:
本文提出利用扩散生成模型,仅基于不完整井和地震观测合成高保真地下速度模型,无需完整训练数据,并能提供不确定性估计,为全波形反演提供支持。
摘要:
在本研究中,我们提出了一种利用扩散生成模型合成地下速度模型的新方法。传统方法依赖大量高质量数据集,而这些数据集在地下应用中往往难以获取。我们的方法利用不完整的井和地震观测来生成高保真速度样本,无需完全采样的训练数据集。结果表明,我们的生成模型能够准确捕捉长程结构,与真实速度模型对齐,取得较高的结构相似性指数(SSIM)分数,并提供有意义的不确定性估计。该方法有助于实现真实的地下速度合成,为全波形反演提供有价值的输入,并增强基于地震的地下建模。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。