Rockphypy - An Extensive Python Library for Rock Physics Modeling

Abstract

we present rockphypy: a comprehensive and streamlined Python library that offers access to a vast array of rock physics models and workflows ranging from basic to sophisticated. The library is designed to be easily embedded in interdisciplinary fields such as deep neural networks and probabilistic frameworks, leveraging the rich resources of Python. Currently, rockphypy implements ten modules with over 100 methods, accessible through a straightforward and user-friendly API that facilitates various modeling tasks in rock physics. Its modular design allows easy extension to incorporate new features and functionalities. In addition to the versatility of the library, we have shown that rockphypy also greatly simplifies practical tasks that require many different rock physics models, enabling fast experimentation and iteration of research and practical programs. Check the documentation https://rockphypy.readthedocs.io/en/latest/index.html# for more information.

Jiaxin Yu

My research encompasses both theoretical investigations in the domains of rock and subsurface studies, as well as the practical application of AI technologies to geoscientific endeavors. On the theoretical front, my research interests are primarily centered around rock physics, granular medium theory, and poroelasticity. From an applied perspective, my focus lies in leveraging artificial intelligence for rock mineral identification, employing Graph Neural Networks (GNNs) for simulating granular mediums, and contributing to open-source initiatives dedicated to rock physics and computational geoscience projects