SylvaCarbon-0

AI-Powered Carbon Credit Estimation Model

This project is available on Hugging Face.

1. What It Does

This project uses an AI model to estimate a tree's carbon credit value from an image. It predicts the tree's size and species, then calculates how much CO₂ it can capture next year.

Note: This is a proof-of-concept. The included model is trained on placeholder data, not real tree images, so its predictions are currently for demonstration purposes only. The main achievement is a complete, working pipeline ready for real data.

2. How to Get Started

Follow these steps to set up and run the project on your own machine.

Step 1: Get the Code & Install Packages

First, clone the repository and install the necessary Python packages.

# Clone the repository
git clone https://huggingface.co/hermits001/SylvaCarbon-0

cd SylvaCarbon-0

# Create a virtual environment (recommended)
python3 -m venv venv
source venv/bin/activate

# Install dependencies
pip install -r requirements.txt

Step 2: Download the Data

The model needs the NEON scientific dataset to learn from.

1. Go to the NEON Data Portal.
2. Download the "Woody Plant Vegetation Structure" dataset.
3. Unzip the downloaded file.
4. Rename the unzipped folder to exactly NEON_struct-plant.
5. Move this folder into your SylvaCarbon-0 project directory.
6. Your folder should now look like this:SylvaCarbon-0/

├── NEON_struct-plant/  <-- Your data folder
├── model/
├── src/
└── ...

Step 3. How to Use the Model

To Test a Prediction (Recommended)

This is the quickest way to see the project in action. It uses the pre-trained model included in the repository.

1. Save any tree image in the SylvaCarbon-0 folder as my_tree.jpg.
2. Open the file src/predict.py and make sure the IMAGE_TO_TEST variable is set to "my_tree.jpg".
3. Run the script from your terminal:python src/predict.py

src/predict.py

To Train a New Model (Optional) If you want to run the full training process yourself, which takes many hours:

python src/carbon_credit_model.py