Granite Geospatial Biomass

--- license: apache-2.0 library_name: terratorch pipeline_tag: image-feature-extraction --- # Model Card for granite-geospatial-biomass This model is based on the paper [TerraTorch: The Geospatial Foundation Models Toolkit](https://huggingface.co/papers/2503.20563). <p align="center" width="100%"> <img src="https://github.com/ibm-granite/granite-geospatial-biomass/blob/main/biomass-image.jpeg?raw=true" width="600"> </p> The granite-geospatial-biomass model is a fine-tuned geospatial foundation model for predicting the total above ground biomass (i.e., living and dead plant material on the Earth's surface) using optical satellite imagery. Above ground biomass is an important component of the carbon cycle and is crucial for estimating crop yields, monitoring forest timber production, and quantifying the carbon sequestered by nature-based actions. The model predicts above ground biomass from the Harmonized Landsat and Sentinel-2 (HLS) L30 optical satellite imagery and is fine-tuned using training labels from the Global Ecosystem Dynamics Investigation (GEDI) L4A. Uniquely, the model has been fine-tuned using HLS and GEDI data collected from 15 biomes across the globe. Please see [Model Description](Model Description) below for more details. ## How to Get Started with the Model This model was trained using [Terratorch](https://github.com/IBM/terratorch). We make the weights as well as the configuration file that defines it available. You can use it easily with Terratorch through: ```python from terratorch.cli_tools import LightningInferenceModel from huggingface_hub import hf_hub_download ckpt_path = hf_hub_download(repo_id="ibm-granite/granite-geospatial-biomass", filename="biomass_model.ckpt") config_path = hf_hub_download(repo_id="ibm-granite/granite-geospatial-biomass", filename="config.yaml") model = LightningInferenceModel.from_config(config_path, ckpt_path) inference_results, input_file_names = model.inference_on_dir(<input_directory>) ``` For more details, check out the [Getting Started Notebook](https://github.com/ibm-granite/granite-geospatial-biomass/blob/main/notebooks/agb_getting_started.ipynb) or [Getting Started Google Colab Notebook](https://githubtocolab.com/ibm-granite/granite-geospatial-biomass/blob/main/notebooks/agb_getting_started.ipynb). To run the Colab Notebook beyond the initial example inferences, a high RAM instance m...

Source context: 120 downloads · 49 likes · Pipeline image-feature-extraction · Library terratorch · Repo ibm-granite/granite-geospatial-biomass