gempy-project/gempy

GemPy is an open-source, Python-based 3-D structural geological modeling software, which allows the implicit (i.e. automatic) creation of complex geological models from interface and orientation data. It also offers support for stochastic modeling to address parameter and model uncertainties.

What it solves

GemPy is designed to solve the challenge of creating complex 3D geological models. It allows users to construct representations of folded structures, fault networks, and unconformities, which are typically difficult to map in three dimensions from limited surface or borehole data.

How it works

The library uses an implicit representation approach to generate 3D models. It leverages PyTorch for its engine and provides tools for model setup, serialization, and visualization (via gempy_viewer). It can handle complex geometries like pinch-outs and recumbent folds through mathematical representations of geological surfaces.

Who it’s for

Geologists, geophysicists, and earth scientists who need to create reproducible, open-source 3D structural models of the subsurface for research or industry applications.

Highlights

  • Implicit Modeling: Uses a powerful implicit representation approach to construct 3D geological structures.
  • Comprehensive Geometry Support: Capable of modeling folds, faults, and unconformities.
  • Crossection Visualization: Includes tools for 2D and 3D visualization and cross-section generation.
  • PyTorch Integration: The latest version (v3) incorporates PyTorch support for its underlying engine.
  • Open Source: A fully open-source Python library with a wide array of tutorials and case studies.

Related

  • Project
    facebookresearch/pytorch3d

    A PyTorch-based library for 3D Computer Vision research providing differentiable rendering and efficient tools for manipulating 3D meshes and point clouds.

  • Project
    ucam-eo/geotessera

    A Python library for accessing and working with Tessera geospatial foundation model embeddings, providing tools to download, export, and visualize 128-channel representation maps of the Earth.

  • Project
    azavea/raster-vision

    A Python library and low-code framework for building computer vision models on satellite, aerial, and drone imagery using PyTorch.

  • Project
    NVIDIA/cuEquivariance

    An NVIDIA Python library for building high-performance geometric neural networks that respect 3D symmetries using optimized CUDA kernels and segmented polynomials.

  • Project
    a-r-j/graphein

    A Python library for converting biomolecular structures and interaction networks into geometric graph representations for use in deep learning.