pyl2bv 1.1.2

Package for vegetation trait retrievals with ARTMO-based GPR models from hyperspectral images.

PyL2BV

Overview

PyL2BV (Python Level 2B Vegetation) is a Python package for processing ARTMO-based Gaussian Process Regression (GPR) models on hyperspectral images. It enables biophysical parameter retrieval using machine learning models.

Key Features

• Process hyperspectral images (ENVI Standard, CHIME netCDF)
• Gaussian Process Regression (GPR) for vegetation parameters
• Command-Line Interface (CLI) and Graphical User Interface (GUI)
• Customizable chunk-based retrieval
• Supports large-scale image processing with parallelization
• Automated ENVI file and NetCDF exports

Installation Guide

Prerequisites

Ensure you have Python 3.10 or later installed on your system.

Install via PyPI (Coming Soon)

pip install PyL2BV

Install the package directly from GitHub using pip:

pip install git+https://github.com/mv-xion/PyL2BV.git

Creating a Virtual Environment

Using venv

# 1. Create a virtual environment
   python -m venv pyl2bv_env
# 2. Activate the virtual environment:
   source pyl2bv_env/bin/activate  # macOS/Linux
   pyl2bv_env\Scripts\activate    # Windows

Using conda

# 1. Create a new conda environment:
   conda create --name pyl2bv_env python=3.10
# 2. Activate the conda environment:
   conda activate pyl2bv_env

Installing Side-Packages

Once you have activated your virtual environment, install the necessary packages from requirements.txt:

pip install -r requirements.txt

Usage

Using the Python API

Use PyL2BV in Python scripts, below is an example:

from PyL2BV.pyl2bv_code.model_runner import run_retrieval

# Define the input folder path
input_folder_path = "/path/to/your/input_folder"
# Define the input type (assuming it's a required argument)
input_type = "ENVI Standard"
# Define the model folder path
model_folder_path = "/path/to/your/model_folder"
# Define the conversion factor (example value, replace with actual if needed)
conversion_factor = 0.0001
# Define the chunk size based on your memory (example value, replace with actual if needed)
chunk_size = 300

# Run the retrieval
run_retrieval(
    input_folder_path=input_folder_path,
    input_type=input_type,
    model_folder_path=model_folder_path,
    conversion_factor=conversion_factor,
    chunk_size=chunk_size,
    plot=False,
    debug_log=False,
)

Using the Command-Line Interface (CLI)

You can also run the model using the CLI. Below is an example of how to use it:

python -m PyL2BV.cli /path/to/your/input/folder "ENVI Standard" /path/to/your/model/folder 0.0001 300 --plot

The CLI accepts the following arguments:

• input_folder_path: Path to the input folder
• input_type: Type of input file
• model_folder_path: Path to the model folder
• conversion_factor: Image conversion factor
• `chunk_size: Retrieval chunk size
• --plot: Optional flag to enable plotting

GUI Usage

The GUI allows the user to set the following parameters:

• Input Folder: Select the folder containing the input files.
• Model Folder: Choose the folder with the required model files.
• Input Type: Specify the type of input (options include "CHIME netCDF" and "ENVI Standard").
• Conversion Factor: Set the image conversion factor as needed.
• Chunk Size: Set the optimal retrieval chunk size factor for your PC.
• Advanced Settings: The "Plotting results" option can be toggled in this dropdown.

Program Running

When the "Run" button is pressed, the program begins retrieval and opens a progress window for tracking.

Outcomes

Below are examples of outcome images generated by the program:

After the progress window closes, the user can initiate another retrieval directly from the GUI.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Contributing to PyL2BV

Thank you for your interest in contributing to PyL2BV!
We welcome contributions that help improve the project, whether it's fixing bugs, adding new features, or improving documentation.

1. Fork the repository on GitHub.
2. Create a new branch (git checkout -b feature-name)
3. Commit changes
4. Push to the branch
5. Open a Pull Request

Support

For issues, please open a GitHub Issue.

References

ARTMO Toolbox