SpectralIndices.jl

Documentation	Build Status	Julia	Testing

SpectralIndices.jl is a Julia package for working with spectral indices commonly used in remote sensing and earth observation applications. It provides a convenient way to compute various spectral indices using Julia's high-performance capabilities.

• Computation for a wide range of spectral indices
• Computation support for Float64, Float32 and Float16 at index formula level to support fast computation for ML applications
• Support for various data types, including but not limited to (see this issue for an updated list and WIP)
  • Arrays
  • DataFrames
  • YAXArrays
• Flexible parameter input options
• Compatibility with multiple remote sensing platforms and sensors

SpectralIndices.jl is registered in the general registry, please install it using the following:

julia> ]
pkg> add SpectralIndices

or

using Pkg
Pkg.add("SpectralIndices")

You can compute spectral indices either by specifying the index and its parameters or using predefined SpectralIndex instances.

using SpectralIndices
using DataFrames

# Compute NDVI with direct parameter input
result = compute_index("NDVI", N = 0.643, R = 0.175)

# Compute NDVI with direct parameter input and direct NDVI call
result = compute_index(NDVI, N = 0.643, R = 0.175)

# Compute multiple indices with array inputs
multi_result = compute_index(["NDVI", "SAVI"], N = fill(0.643, 5), R = fill(0.175, 5), L = fill(0.5, 5))

# use Dataframes
df = DataFrame(N = [0.643, 0.560], R = [0.175, 0.225])
result_df_single = compute_index("NDVI", df)
# Multiple inputs in a dataframe
df = DataFrame(N = [0.643, 0.560], R = [0.175, 0.225], L = [0.5, 0.5])
result_df_multiple = compute_index(["NDVI", "SAVI"], df)

To compute at custom Float precision input the bands at the chosen precision and specify the Float type to the compute_index function

# Compute NDVI with direct parameter input
result = compute_index(Float32, "NDVI", N = Float32(0.643), R = Float32(0.175))

# Define a SpectralIndex instance

# Compute using the instance with keyword arguments
result = compute(NDVI, N = 0.643, R = 0.175) #NDVI is autmatically in namespace with the import of SpectraIndices.jl

# Compute with array inputs
array_result = compute(NDVI, N = fill(0.643, (5, 5)), R = fill(0.175, (5, 5)))

For more advanced usage and detailed documentation, please refer to the documentation.

Contributions to SpectralIndices.jl are welcome! If you would like to contribute, please see our Contribution Guidelines for more information.

SpectralIndices.jl is licensed under the MIT License. See LICENSE for more information.

This package is inspired by the Spyndex Python library for spectral indices. The logo is AI-generated by dalle3 through ChatGPT and modified by the talented David Montero.

If you have any questions, issues, or feature requests, please open an issue or contact us via email.

If you use SpectralIndices.jl in your research, please consider citing it using the following DOI:

@article{martinuzzi2024spectral,
  title = {SpectralIndices.jl: Streamlining spectral indices access and computation for Earth system research},
  volume = {XLVIII-4/W12-2024},
  ISSN = {2194-9034},
  url = {http://dx.doi.org/10.5194/isprs-archives-XLVIII-4-W12-2024-89-2024},
  DOI = {10.5194/isprs-archives-xlviii-4-w12-2024-89-2024},
  journal = {The International Archives of the Photogrammetry,  Remote Sensing and Spatial Information Sciences},
  publisher = {Copernicus GmbH},
  author = {Martinuzzi,  Francesco and Mahecha,  Miguel D. and Montero,  David and Alonso,  Lazaro and Mora,  Karin},
  year = {2024},
  month = jun,
  pages = {89–95}
}

Also consider citing the paper introducing the Awesome Spectral Indices collection:

@article{montero2023standardized,
  title={A standardized catalogue of spectral indices to advance the use of remote sensing in Earth system research},
  author={Montero, David and Aybar, C{\'e}sar and Mahecha, Miguel D and Martinuzzi, Francesco and S{\"o}chting, Maximilian and Wieneke, Sebastian},
  journal={Scientific Data},
  volume={10},
  number={1},
  pages={197},
  year={2023},
  publisher={Nature Publishing Group UK London}
}