Ecological mapping with geospatial foundation models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911463976730624 |
|---|---|
| author | Mahlasi, Craig Baloyi, Gciniwe S. Gaffoor, Zaheed Klein, Levente Jones, Anne Vos, Etienne Muszynski, Michal Dawson, Geoffrey Watson, Campbell |
| author_facet | Mahlasi, Craig Baloyi, Gciniwe S. Gaffoor, Zaheed Klein, Levente Jones, Anne Vos, Etienne Muszynski, Michal Dawson, Geoffrey Watson, Campbell |
| contents | The value of Earth observation foundation models for high-impact ecological applications remains insufficiently characterized. This study is one of the first to systematically evaluate the performance, limitations and practical considerations across three common ecological use cases: forest functional trait estimation, land use and land cover mapping and peatland detection. We fine-tune two pretrained models (Prithvi-EO-2.0 and TerraMind) and benchmark them against a ResNet-101 baseline using datasets collected from open sources. Across all tasks, Prithvi-EO-2.0 and TerraMind consistently outperform the ResNet baseline, demonstrating improved generalization and transfer across ecological domains. TerraMind marginally exceeds Prithvi-EO-2.0 in unimodal settings and shows substantial gains when additional modalities are incorporated. However, performance is sensitive to divergence between downstream inputs and pretraining modalities, underscoring the need for careful dataset alignment. Results also indicate that higher-resolution inputs and more accurate pixel-level labels remain critical for capturing fine-scale ecological dynamics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_10720 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Ecological mapping with geospatial foundation models Mahlasi, Craig Baloyi, Gciniwe S. Gaffoor, Zaheed Klein, Levente Jones, Anne Vos, Etienne Muszynski, Michal Dawson, Geoffrey Watson, Campbell Computer Vision and Pattern Recognition The value of Earth observation foundation models for high-impact ecological applications remains insufficiently characterized. This study is one of the first to systematically evaluate the performance, limitations and practical considerations across three common ecological use cases: forest functional trait estimation, land use and land cover mapping and peatland detection. We fine-tune two pretrained models (Prithvi-EO-2.0 and TerraMind) and benchmark them against a ResNet-101 baseline using datasets collected from open sources. Across all tasks, Prithvi-EO-2.0 and TerraMind consistently outperform the ResNet baseline, demonstrating improved generalization and transfer across ecological domains. TerraMind marginally exceeds Prithvi-EO-2.0 in unimodal settings and shows substantial gains when additional modalities are incorporated. However, performance is sensitive to divergence between downstream inputs and pretraining modalities, underscoring the need for careful dataset alignment. Results also indicate that higher-resolution inputs and more accurate pixel-level labels remain critical for capturing fine-scale ecological dynamics. |
| title | Ecological mapping with geospatial foundation models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.10720 |