Ecological mapping with geospatial foundation models

2026-02-11

AI Summary

This study systematically evaluates the potential of geospatial foundation models for high-value ecological mapping tasks, including land use/cover classification, forest functional trait mapping, and peatland detection. Through fine-tuning Prithvi-E0-2.0 and TerraMind and comparing them against a ResNet-101 baseline, we conduct multimodal experiments leveraging multi-source remote sensing data. Results demonstrate that both foundation models significantly outperform the conventional baseline, with TerraMind exhibiting slightly superior performance. The integration of multimodal inputs further enhances model accuracy. To our knowledge, this work provides the first empirical validation of emerging geospatial foundation models in multimodal ecological mapping, highlighting their advantages and promising potential for complex environmental monitoring applications.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Multimodal Learning
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Geospatial foundation models (GFMs) are a fast-emerging paradigm for various geospatial tasks, such as ecological mapping. However, the utility of GFMs has not been fully explored for high-value use cases. This study aims to explore the utility, challenges and opportunities associated with the application of GFMs for ecological uses. In this regard, we fine-tune several pretrained AI models, namely, Prithvi-E0-2.0 and TerraMind, across three use cases, and compare this with a baseline ResNet-101 model. Firstly, we demonstrate TerraMind's LULC generation capabilities. Lastly, we explore the utility of the GFMs in forest functional trait mapping and peatlands detection. In all experiments, the GFMs outperform the baseline ResNet models. In general TerraMind marginally outperforms Prithvi. However, with additional modalities TerraMind significantly outperforms the baseline ResNet and Prithvi models. Nonetheless, consideration should be given to the divergence of input data from pretrained modalities. We note that these models would benefit from higher resolution and more accurate labels, especially for use cases where pixel-level dynamics need to be mapped.

Problem

• geospatial foundation models
• ecological mapping
• land use/land cover
• forest functional traits
• peatlands detection

Innovation

• Geospatial Foundation Models
• ecological mapping
• TerraMind
• multimodal fine-tuning
• forest functional traits