TerraTorch: The Geospatial Foundation Models Toolkit

2025-03-26

AI Summary

Fine-tuning and benchmarking geospatial foundation models on satellite, weather, and climate data suffer from low efficiency and high entry barriers. Method: This paper introduces the first modular fine-tuning and evaluation toolkit tailored for Earth observation. It features a plug-and-play “Model Factory” and domain-specific data modules, enabling flexible composition of arbitrary backbone networks and task-specific heads; integrates GEO-Bench for cross-task, reproducible systematic evaluation; and implements a configuration-driven pipeline built on PyTorch Lightning, incorporating Iterate for hyperparameter optimization and supporting heterogeneous remote sensing and meteorological data formats. Contribution/Results: The toolkit substantially lowers the barrier to model adaptation, accelerates fine-tuning and evaluation in novel observational scenarios, and is fully open-sourced with pip-installable deployment.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Machine Learning: Deep Neural Architectures and Foundation Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

TerraTorch is a fine-tuning and benchmarking toolkit for Geospatial Foundation Models built on PyTorch Lightning and tailored for satellite, weather, and climate data. It integrates domain-specific data modules, pre-defined tasks, and a modular model factory that pairs any backbone with diverse decoder heads. These components allow researchers and practitioners to fine-tune supported models in a no-code fashion by simply editing a training configuration. By consolidating best practices for model development and incorporating the automated hyperparameter optimization extension Iterate, TerraTorch reduces the expertise and time required to fine-tune or benchmark models on new Earth Observation use cases. Furthermore, TerraTorch directly integrates with GEO-Bench, allowing for systematic and reproducible benchmarking of Geospatial Foundation Models. TerraTorch is open sourced under Apache 2.0, available at https://github.com/IBM/terratorch, and can be installed via pip install terratorch.

Problem

• Facilitates fine-tuning of geospatial models for satellite and climate data
• Reduces expertise needed for Earth Observation model benchmarking
• Integrates with GEO-Bench for reproducible geospatial model evaluation

Innovation

• Fine-tuning toolkit for Geospatial Foundation Models
• Modular model factory with diverse decoder heads
• Automated hyperparameter optimization extension Iterate