用Transformer生成超大数字岩心，1024³分辨率也能在普通电脑跑。
PoreDiT: A Scalable Generative Model for Large-Scale Digital Rock Reconstruction
- 用3D Swin Transformer直接预测孔隙二值概率场，避开传统方法瓶颈。
- 生成1024³体素数字岩心，计算效率高且保持孔隙结构物理真实性。
- 适合做油气储层、碳封存等大尺度流体模拟的研究者使用。
本文提出PoreDiT，一种新型生成模型，用于在千兆体素尺度上高效重建数字岩心。针对数字岩心物理（DRP）中分辨率与视场（FOV）的权衡问题，以及传统深度学习架构带来的计算瓶颈，PoreDiT采用三维Swin Transformer，直接预测孔隙空间的二值概率场，而非灰度强度，从而保留对孔隙尺度流体流动和传输模拟至关重要的拓扑特征。该方法显著提升计算效率，可在消费级硬件上生成高达1024³体素的超大规模数字岩心样本。同时，其物理保真度与先前最先进方法相当，包括准确的孔隙度、孔隙尺度渗透率及欧拉特征数。该模型的高效可扩展性为大尺度水动力学模拟开辟新路径，为孔隙尺度流体力学、储层表征及碳封存研究提供实用解决方案。
原文摘要 · Abstract (English)
This manuscript presents PoreDiT, a novel generative model designed for high-efficiency digital rock reconstruction at gigavoxel scales. Addressing the significant challenges in digital rock physics (DRP), particularly the trade-off between resolution and field-of-view (FOV), and the computational bottlenecks associated with traditional deep learning architectures, PoreDiT leverages a three-dimensional (3D) Swin Transformer to break through these limitations. By directly predicting the binary probability field of pore spaces instead of grayscale intensities, the model preserves key topological features critical for pore-scale fluid flow and transport simulations. This approach enhances computational efficiency, enabling the generation of ultra-large-scale ($1024^3$ voxels) digital rock samples on consumer-grade hardware. Furthermore, PoreDiT achieves physical fidelity comparable to previous state-of-the-art methods, including accurate porosity, pore-scale permeability, and Euler characteristics. The model's ability to scale efficiently opens new avenues for large-domain hydrodynamic simulations and provides practical solutions for researchers in pore-scale fluid mechanics, reservoir characterization, and carbon sequestration.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。