# TerraTorch: The Geospatial Foundation Models Toolkit

arXiv: https://arxiv.org/abs/2503.20563 · HTML: https://mlsanity.com/paper/2503.20563/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 35 references that are in the map.
- First posted on arXiv 26 Mar 2025.

## Builds on (most cited first, 15 of 15)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Ray: A Distributed Framework for Emerging AI Applications](https://mlsanity.com/paper/1712.05889/) (2017)
- [Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning](https://mlsanity.com/paper/2212.14532/) (2022)
- [Tackling Climate Change with Machine Learning](https://mlsanity.com/paper/1906.05433/) (2019)
- [SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understanding](https://mlsanity.com/paper/2211.15660/) (2022)
- [Foundation Models for Generalist Geospatial Artificial Intelligence](https://mlsanity.com/paper/2310.18660/) (2023)
- [Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications](https://mlsanity.com/paper/2412.02732/) (2024)
- [GEO-Bench: Toward Foundation Models for Earth Monitoring](https://mlsanity.com/paper/2306.03831/) (2023)
- [TorchGeo: Deep Learning With Geospatial Data](https://mlsanity.com/paper/2111.08872/) (2021)
- [Decoupling Common and Unique Representations for Multimodal Self-supervised Learning](https://mlsanity.com/paper/2309.05300/) (2023)

## Built on by (most cited first, 25 of 25)

- [GEO-Bench-2: From Performance to Capability, Rethinking Evaluation in Geospatial AI](https://mlsanity.com/paper/2511.15658/) (2025)
- [No One Knows the State of the Art in Geospatial Foundation Models](https://mlsanity.com/paper/2605.12678/) (2026)
- [Fine-tune Smarter, Not Harder: Parameter-Efficient Fine-Tuning for Geospatial Foundation Models](https://mlsanity.com/paper/2504.17397/) (2025)
- [CSMoE: An Efficient Remote Sensing Foundation Model with Soft Mixture-of-Experts](https://mlsanity.com/paper/2509.14104/) (2025)
- [Benchmarking Geospatial Foundation Models for Agriculture Applications](https://mlsanity.com/paper/2606.29664/) (2026)
- [TerraFlow: Multimodal, Multitemporal Representation Learning for Earth Observation](https://mlsanity.com/paper/2603.12762/) (2026)
- [Location Is All You Need: Continuous Spatiotemporal Neural Representations of Earth Observation Data](https://mlsanity.com/paper/2604.07092/) (2026)
- [Assessing the value of Geo-Foundational Models for Flood Inundation Mapping: Benchmarking models for Sentinel-1, Sentinel-2, and Planetscope for end-users](https://mlsanity.com/paper/2511.01990/) (2025)
- [The Potential of Copernicus Satellites for Disaster Response: Retrieving Building Damage from Sentinel-1 and Sentinel-2](https://mlsanity.com/paper/2511.05461/) (2025)
- [Prithvi-Complimentary Adaptive Fusion Encoder (CAFE): unlocking full-potential for flood inundation mapping](https://mlsanity.com/paper/2601.02315/) (2026)
- [Spectral Gaps and Spatial Priors: Studying Hyperspectral Downstream Adaptation Using TerraMind](https://mlsanity.com/paper/2603.06690/) (2026)
- [How to Embed Matters: Evaluation of EO Embedding Design Choices](https://mlsanity.com/paper/2603.10658/) (2026)
- [Emerging Flexible Designs for Geospatial Multimodal Foundation Models](https://mlsanity.com/paper/2606.12595/) (2026)
- [Beyond Backscatter: AlphaEarth Land-Cover Priors for Rapid SAR Flood Segmentation Across Foundation Backbones](https://mlsanity.com/paper/2606.29134/) (2026)
- [GEOID-Flood: A Large-Scale Multi-Modal Benchmark Dataset for Flood Segmentation](https://mlsanity.com/paper/2608.02315/) (2026)
- [Detection and Simulation of Urban Heat Islands Using a Fine-Tuned Geospatial Foundation Model](https://mlsanity.com/paper/2509.16617/) (2025)
- [Habitat and Land Cover Change Detection in Alpine Protected Areas: A Comparison of AI Architectures](https://mlsanity.com/paper/2511.00073/) (2025)
- [Aligned explanations in neural networks](https://mlsanity.com/paper/2601.04378/) (2026)
- [Towards Onboard Continuous Change Detection for Floods](https://mlsanity.com/paper/2601.13751/) (2026)
- [How Much of a Model Do We Need? Redundancy and Slimmability in Remote Sensing Foundation Models](https://mlsanity.com/paper/2601.22841/) (2026)
- [Ecological mapping with geospatial foundation models](https://mlsanity.com/paper/2602.10720/) (2026)
- [Now We Know? A Systematic Comparison of TerraMind and THOR](https://mlsanity.com/paper/2607.18504/) (2026)
- [SomBench: Benchmark Dataset for Advancing Machine Learning in Lunar Science](https://mlsanity.com/paper/2609.13277/) (2026)
- [Multimodal-Multiresolution Foundation Model for Lunar Remote Sensing](https://mlsanity.com/paper/2609.13283/) (2026)
- [Transferability and operational reliability of a Prithvi crop classification foundation model under phenological and geographic shift across three continents](https://mlsanity.com/paper/2610.08810/) (2026)

## Abstract (arXiv)

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.