librecubo 0.0.21

This is a template repository for Python projects that use Poetry for their dependency management.

Download, process, correct, and enhance images sourced from various satellite providers.

---

• Github repository: https://github.com/orgs/librecubo/repositories/
• Documentation https://librecubo.readthedocs.io/
• PyPI: https://pypi.org/project/librecubo/
• Conda-forge: https://anaconda.org/conda-forge/librecubo
• Tutorials: https://librecubo.readthedocs.io/en/latest/tutorials.html

---

Overview

The "librecubo" package in Python represents a powerful ensemble of modules tailored for satellite image processing and enhancement. This comprehensive toolkit is designed to handle diverse satellite imagery, enabling tasks ranging from data acquisition to intricate processing techniques like cloud masking, BRDF correction, temporal referencing, and resolution enhancement. With its multifaceted capabilities, "librecubo" streamlines the retrieval, manipulation, and refinement of satellite data, facilitating efficient and comprehensive image analysis for various applications.

How to use

The example below shows how to use librecubo module to download Sentinel-2 images.

from librecubo import librecubo_download

librecubo_download.download_sentinel2(
    lat=-12.046374,
    lon=-77.042793,
    project="test1",
    path="path/to/save/data",
    start_date="2000-02-16",
    end_date="2022-12-31",
    edge_size=1000
)
# 0%|▍                                     | 1/281 [00:17<\1:19:41, 17.08s/it]

Installation

Install the latest version from PyPI:

pip install librecubo

Upgrade opensr-test by running:

pip install -U librecubo

Install the latest dev version from GitHub by running:

pip install git+https://github.com/librecubo

Examples

Visualizations

Workflow

The workflow below shows the main steps to process satellite images using librecubo package.

1. librecubo-download: Facilitates simultaneous download of multiple images from Landsat (1-9), Sentinel-2, and MODIS using multiprocessing for efficient data retrieval.
2. librecubo-clouds: Handles cloud masking in MODIS, Landsat, and Sentinel-2 images via the CloudSEN12v2 database. Generates a Zarr object with temporal-based chunk organization.
3. librecubo-reference: Establishes temporal series references by extending MODIS data. Performs BRDF correction for Landsat images (5-9) and Sentinel-2 using Roy et al.'s 2020 method (librecubo-brdf).
4. librecubo-brdf: Focuses on BRDF correction specifically for Sentinel-2 images.
5. librecubo-mss2tm: Corrects Landsat MSS images.
6. librecubo-smoother: Manages gap-filling and data smoothing post-reference generation. Improves overall coherence and quality by filling missing data spaces and applying smoothing techniques.

Auxiliary Modules:

1. librecubo-semantic: Enables generation of image semantics, likely involving addition of contextual information or metadata.
2. librecubo-super: Focuses on super-resolution, enhancing image quality by upscaling images from 10 meters to 5 meters resolution.

Citation

If you use librecubo in your research, please cite our paper. Coming soon!

Acknowledgements

We received funding from the National Council of Science, Technology, and Technological Innovation (CONCYTEC, Peru) under the “Proyectos de Investigación Básica – 2023-01” program (PE501083135-2023-PROCIENCIA).