Dargana: fine-tuning EarthPT for dynamic tree canopy mapping from space

• URL: http://arxiv.org/abs/2504.17321v1
• Date: Thu, 24 Apr 2025 07:23:27 GMT
• Title: Dargana: fine-tuning EarthPT for dynamic tree canopy mapping from space
• Authors: Michael J. Smith, Luke Fleming, James E. Geach, Ryan J. Roberts, Freddie Kalaitzis, James Banister,
• Abstract summary: Dargana is fine-tuned to generate regularly updated classification of tree canopy cover at 10m resolution.<n>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.
• Score: 1.099532646524593
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: 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.

Related papers

• Depth Any Canopy: Leveraging Depth Foundation Models for Canopy Height Estimation [4.69726714177332]
  Estimating global tree canopy height is crucial for forest conservation and climate change applications. An efficient alternative is to train a canopy height estimator to operate on single-view remotely sensed imagery. Recent monocular depth estimation foundation models have show strong zero-shot performance even for complex scenes.
  arXiv  Detail & Related papers  (2024-08-08T15:24:07Z)
• Forecasting with Hyper-Trees [50.72190208487953]
  Hyper-Trees are designed to learn the parameters of time series models. By relating the parameters of a target time series model to features, Hyper-Trees also address the issue of parameter non-stationarity. In this novel approach, the trees first generate informative representations from the input features, which a shallow network then maps to the target model parameters.
  arXiv  Detail & Related papers  (2024-05-13T15:22:15Z)
• Individual mapping of large polymorphic shrubs in high mountains using satellite images and deep learning [1.6889377382676625]
  We release a large dataset of individual shrub delineations on freely available satellite imagery. We use an instance segmentation model to map all junipers over the treeline for an entire biosphere reserve. Our model achieved an F1-score in shrub delineation of 87.87% on the PI data and 76.86% on the FW data.
  arXiv  Detail & Related papers  (2024-01-31T16:44:20Z)
• Learning Robust Precipitation Forecaster by Temporal Frame Interpolation [65.5045412005064]
  We develop a robust precipitation forecasting model that demonstrates resilience against spatial-temporal discrepancies. Our approach has led to significant improvements in forecasting precision, culminating in our model securing textit1st place in the transfer learning leaderboard of the textitWeather4cast'23 competition.
  arXiv  Detail & Related papers  (2023-11-30T08:22:08Z)
• Long-term drought prediction using deep neural networks based on geospatial weather data [75.38539438000072]
  High-quality drought forecasting up to a year in advance is critical for agriculture planning and insurance. We tackle drought data by introducing an end-to-end approach that adopts a systematic end-to-end approach. Key findings are the exceptional performance of a Transformer model, EarthFormer, in making accurate short-term (up to six months) forecasts.
  arXiv  Detail & Related papers  (2023-09-12T13:28:06Z)
• The Canadian Cropland Dataset: A New Land Cover Dataset for Multitemporal Deep Learning Classification in Agriculture [0.8602553195689513]
  temporal patch-based dataset of Canadian croplands enriched with labels retrieved from the Canadian Annual Crop Inventory. The dataset contains 78,536 manually verified high-resolution spatial images from 10 crop classes collected over four crop production years. As a benchmark, we provide models and source code that allow a user to predict the crop class using a single image (ResNet, DenseNet, EfficientNet) or a sequence of images (LRCN, 3D-CNN) from the same location.
  arXiv  Detail & Related papers  (2023-05-31T18:40:15Z)
• Vision Transformers, a new approach for high-resolution and large-scale mapping of canopy heights [50.52704854147297]
  We present a new vision transformer (ViT) model optimized with a classification (discrete) and a continuous loss function. This model achieves better accuracy than previously used convolutional based approaches (ConvNets) optimized with only a continuous loss function.
  arXiv  Detail & Related papers  (2023-04-22T22:39:03Z)
• Very high resolution canopy height maps from RGB imagery using self-supervised vision transformer and convolutional decoder trained on Aerial Lidar [14.07306593230776]
  This paper presents the first high-resolution canopy height map concurrently produced for multiple sub-national jurisdictions. The maps are generated by the extraction of features from a self-supervised model trained on Maxar imagery from 2017 to 2020. We also introduce a post-processing step using a convolutional network trained on GEDI observations.
  arXiv  Detail & Related papers  (2023-04-14T15:52:57Z)
• Classification and mapping of low-statured 'shrubland' cover types in post-agricultural landscapes of the US Northeast [0.0]
  Novel plant communities reshape landscapes and pose challenges for land cover classification and mapping. In the US Northeast, emergence of low-statured woody vegetation, or'shrublands', is well-documented, but poorly understood from a landscape perspective. We developed models to predict'shrubland' distributions at 30m resolution across New York State (NYS)
  arXiv  Detail & Related papers  (2022-05-09T14:54:41Z)
• Embedding Earth: Self-supervised contrastive pre-training for dense land cover classification [61.44538721707377]
  We present Embedding Earth a self-supervised contrastive pre-training method for leveraging the large availability of satellite imagery. We observe significant improvements up to 25% absolute mIoU when pre-trained with our proposed method. We find that learnt features can generalize between disparate regions opening up the possibility of using the proposed pre-training scheme.
  arXiv  Detail & Related papers  (2022-03-11T16:14:14Z)
• Country-wide Retrieval of Forest Structure From Optical and SAR Satellite Imagery With Bayesian Deep Learning [74.94436509364554]
  We propose a Bayesian deep learning approach to densely estimate forest structure variables at country-scale with 10-meter resolution. Our method jointly transforms Sentinel-2 optical images and Sentinel-1 synthetic aperture radar images into maps of five different forest structure variables. We train and test our model on reference data from 41 airborne laser scanning missions across Norway.
  arXiv  Detail & Related papers  (2021-11-25T16:21:28Z)
• Accuracy Prediction with Non-neural Model for Neural Architecture Search [185.0651567642238]
  We study an alternative approach which uses non-neural model for accuracy prediction. We leverage gradient boosting decision tree (GBDT) as the predictor for Neural architecture search (NAS) Experiments on NASBench-101 and ImageNet demonstrate the effectiveness of using GBDT as predictor for NAS.
  arXiv  Detail & Related papers  (2020-07-09T13:28:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.