Dargana: fine-tuning EarthPT for dynamic tree canopy mapping from space
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908336079765504 |
|---|---|
| author | Smith, Michael J. Fleming, Luke Geach, James E. Roberts, Ryan J. Kalaitzis, Freddie Banister, James |
| author_facet | Smith, Michael J. Fleming, Luke Geach, James E. Roberts, Ryan J. Kalaitzis, Freddie Banister, James |
| contents | We present Dargana, a fine-tuned variant of the EarthPT time-series foundation model that achieves specialisation using <3% of its pre-training data volume and 5% of its pre-training compute. Dargana is fine-tuned to generate regularly updated classification of tree canopy cover at 10m resolution, distinguishing conifer and broadleaved tree types. Using Cornwall, UK, as a test case, the model achieves a pixel-level ROC-AUC of 0.98 and a PR-AUC of 0.83 on unseen satellite imagery. Dargana can identify fine structures like hedgerows and coppice below the training sample limit, and can track temporal changes to canopy cover such as new woodland establishment. Our results demonstrate how pre-trained Large Observation Models like EarthPT can be specialised for granular, dynamic land cover monitoring from space, providing a valuable, scalable tool for natural capital management and conservation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_17321 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dargana: fine-tuning EarthPT for dynamic tree canopy mapping from space Smith, Michael J. Fleming, Luke Geach, James E. Roberts, Ryan J. Kalaitzis, Freddie Banister, James Geophysics Machine Learning We present Dargana, a fine-tuned variant of the EarthPT time-series foundation model that achieves specialisation using <3% of its pre-training data volume and 5% of its pre-training compute. Dargana is fine-tuned to generate regularly updated classification of tree canopy cover at 10m resolution, distinguishing conifer and broadleaved tree types. Using Cornwall, UK, as a test case, the model achieves a pixel-level ROC-AUC of 0.98 and a PR-AUC of 0.83 on unseen satellite imagery. Dargana can identify fine structures like hedgerows and coppice below the training sample limit, and can track temporal changes to canopy cover such as new woodland establishment. Our results demonstrate how pre-trained Large Observation Models like EarthPT can be specialised for granular, dynamic land cover monitoring from space, providing a valuable, scalable tool for natural capital management and conservation. |
| title | Dargana: fine-tuning EarthPT for dynamic tree canopy mapping from space |
| topic | Geophysics Machine Learning |
| url | https://arxiv.org/abs/2504.17321 |