Spherical DeepKriging

Code for DeepKriging on the Global Data (Jpn J Stat Data Sci, 2026): spherical spatial prediction with DeepKriging, MRTS-sphere / Wendland bases, and universal kriging. Implementation lives under spherical_deepkriging/.

Framework Overview: Spherical DeepKriging for Global Spatial Prediction

Install

From PyPI (project page) — typical use (Python ≥ 3.10):

pip install spherical-deepkriging

Optional extras, e.g. Jupyter / plotting / everything bundled in [all]:

pip install "spherical-deepkriging[jupyter,viz]"
pip install "spherical-deepkriging[all]"

From source (development) — conda-based env and repo scripts:

Needs Miniconda. On Windows, use WSL.

git clone https://github.com/STLABTW/spherical-deepkriging.git
cd spherical-deepkriging
make install-dev

make install-dev creates the conda environment and installs dependencies; make build-spherical-cpp builds the MRTS-sphere C++ extension. For tests and packaging tools in a plain venv: pip install -e ".[dev]".

Examples

• Smoke test: examples/toy/toy_sphere_deepkriging.ipynb
• Colab toy notebook: examples/toy/toy_sphere_deepkriging_colab.ipynb (also linked by the Colab badge above)
• Simulations: examples/simulation/
• Real data: examples/real_data/

See examples/README.md for run notes.

Available Basis Functions

Citation

@article{huang2026deepkrigingglobaldata,
      title={{DeepKriging on the global data}},
      author={Hao-Yun Huang and Wen-Ting Wang and Ping-Hsun Chiang and Wei-Ying Wu},
      journal={Japanese Journal of Statistics and Data Science},
      year={2026},
      doi={10.1007/s42081-026-00371-z},
      url={https://doi.org/10.1007/s42081-026-00371-z},
}