TFInterpy

TFInterpy is a Python package for spatial interpolation. A high-performance version of several interpolation algorithms is implemented based on TensorFlow. Including parallelizable IDW and Kriging algorithms. So far, tfinterpy is the fastest open source Kriging algorithm, which can reduce the operation time of large-scale interpolation tasks by an order of magnitude

Link to our paper

TFInterpy: A high-performance spatial interpolation Python package
(https://doi.org/10.1016/j.softx.2022.101229)

Performance comparison (unit: second)

Screenshots

Snapshot of GUI tool.

Requirements

Minimum usage requirements: Python 3+, Numpy, SciPy

TensorFlow based algorithm: TensorFlow 2

GSLIB file support: Pandas

3D visualization: VTK

GUI Tool: PyQT5

Usage

All examples are stored on the github homepage

Install tfinterpy

pip install tfinterpy

Then install dependencies

Full dependencies : (To avoid package version issues, the specific version numbers tested in Python3.9 are listed here)

pip install matplotlib==3.9.4
pip install numpy==2.0.2
pip install pandas==2.2.3
pip install PyQt5==5.15.11
pip install scipy==1.13.1
pip install tensorflow==2.18.0
pip install vtk==9.4.1

Notice！ You may do not need to install all dependencies

• If you only need to use the most basic interpolation algorithm, install the following package. (see "examples/" for usage)

  pip install numpy==2.0.2
  pip install scipy==1.13.1
  

• If you need to use TensorFlow-based interpolation algorithms, you need to install tensorflow. (see "examples/tf" for usage)

  pip install tensorflow==2.18.0
  

  or (Use GPU for computing)

  pip install tensorflow-gpu==2.18.0
  

• If you need to use the built-in GUI tools (see "examples/gui" for usage) provided, please install full dependencies as above list.

netcdf4 also needs to be installed to run the examples in the examples folder:

pip install netCDF4==1.7.2