Grids and interpolates scattered spatial data using machine-learning style APIs and processing pipelines.
The Verde skill empowers Claude to perform sophisticated spatial data analysis, specifically focusing on gridding scattered point data onto regular surfaces. By leveraging a scikit-learn inspired API, it allows users to implement bi-harmonic splines, linear interpolation, and cubic methods while handling complex geospatial tasks like coordinate projections, block averaging for data reduction, and polynomial trend removal. This skill is indispensable for geoscientists and data analysts who need to transform irregular observations—such as GPS velocities, bathymetry, or elevation—into clean, analysis-ready grids with built-in cross-validation and reproducible pipelines.
Key Features
01Integrated polynomial trend fitting and removal for isolating regional signals.
02Built-in cross-validation tools for optimizing gridding parameters and model selection.
03Data decimation and reduction through block averaging (mean, median) to handle large datasets.
0412 GitHub stars
05Support for 2-component vector data gridding, ideal for GPS and flow velocity fields.
06Machine-learning style API for spatial interpolation including Spline, Linear, and Cubic models.
Use Cases
01Interpolating irregular geophysical measurements while validating accuracy through K-fold cross-validation.
02Creating multi-step processing pipelines that combine trend removal, reduction, and gridding.
03Converting scattered topographic or bathymetric survey points into regular elevation models.
