paper-with-me

홈 › Papers

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

2025-04-24 · Michael J. Smith, Luke Fleming, James E. Geach, Ryan J. Roberts, Freddie Kalaitzis, James Banister

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.

📄 PDF Abstract BibTeX arXiv:2504.17321

Code (0)

등록된 구현이 없습니다.

Tasks

Management

Similar Papers 제목 키워드 기반

EarthPT: a time series foundation model for Earth Observation

2023-09-13 · Michael J. Smith, Luke Fleming, James E. Geach

We introduce EarthPT -- an Earth Observation (EO) pretrained transformer. EarthPT is a 700 million parameter decoding transformer foundation model trained in an autoregressive self-supervised manner and developed specifi…

Earth ObservationTime Series

Dynamic-TreeRPO: Breaking the Independent Trajectory Bottleneck with Structured Sampling

2025-09-27 · Xiaolong Fu, Lichen Ma, Zipeng Guo, ShiPing Dong 외 arxiv

The integration of Reinforcement Learning (RL) into flow matching models for text-to-image (T2I) generation has driven substantial advances in generation quality. However, these gains often come at the cost of exhaustive…

Reinforcement Learning

Unsupervised Parsing with S-DIORA: Single Tree Encoding for Deep Inside-Outside Recursive Autoencoders

2020-11-01 · EMNLP 2020 11 · Andrew Drozdov, Subendhu Rongali, Yi-Pei Chen, Tim O{'}Gorman 외

The deep inside-outside recursive autoencoder (DIORA; Drozdov et al. 2019) is a self-supervised neural model that learns to induce syntactic tree structures for input sentences *without access to labeled training data*. …

Constituency Grammar InductionConstituency ParsingSentence

FedTreeLoRA: Reconciling Statistical and Functional Heterogeneity in Federated LoRA Fine-Tuning

2026-02-27 · Jieming Bian, Lei Wang, Letian Zhang, Jie Xu arxiv

Federated Learning (FL) with Low-Rank Adaptation (LoRA) has become a standard for privacy-preserving LLM fine-tuning. However, existing personalized methods predominantly operated under a restrictive Flat-Model Assumptio…

Federated Learning

Fourier PlenOctrees for Dynamic Radiance Field Rendering in Real-time

2022-02-17 · CVPR 2022 1 · Liao Wang, Jiakai Zhang, Xinhang Liu, Fuqiang Zhao 외

Implicit neural representations such as Neural Radiance Field (NeRF) have focused mainly on modeling static objects captured under multi-view settings where real-time rendering can be achieved with smart data structures,…

NeRF