Spatial modeling using machine learning concepts.

This is a work in progress. Current functionality includes:

• Gaussian process modeling in 1D, 2D, and 3D, with anisotropy ellipsoid;
• Variational Gaussian process for classification and multivariate modeling;
• Support for compositional data;
• Support for directional data (structural geology measurements, scalar field gradients, etc.);
• Support for classification with boundary data (points lying in the boundary between two rock types);
• Deep learning for non-stationary modeling;
• Exports results to PyVista format;
• Back-end powered by TensorFlow.

Clone the repo and update the path to include the package's folder.

Dependencies:

• scikit-image
• pandas
• numpy
• tensorflow
• tensorflow-probability
• pyvista and plotly for 3D visualization

The following notebooks demonstrate the capabilities of the package (if one of them seems broken, it is probably going through an update).

• Walker Lake
• 2D classification with structural constraints
• Sunspot cycle prediction
• 3D classification
• Potential field modeling using only directional data
• Jura
• Compositional data
• Gold modeling with auxiliary variables

• Understanding inducing points
• VGP training step by step