Low-Rank Adaptation of Geospatial Foundation Models for Wildfire Mapping Using Sentinel-2 Data

• URL: http://arxiv.org/abs/2605.04989v1
• Date: Wed, 06 May 2026 14:47:01 GMT
• Title: Low-Rank Adaptation of Geospatial Foundation Models for Wildfire Mapping Using Sentinel-2 Data
• Abstract summary: This study evaluates three state-of-the-art Geospatial Foundation Models (GFMs) for burned-area mapping across the United States and Canada using Sentinel-2 data.<n>We compare full fine-tuning, decoder-only fine-tuning, and Low-Rank Adaptation (LoRA) for adapting each model.<n> Prithvi-v2 with LoRA achieves the highest overall accuracy and the largest improvement compared to full fine-tuning.
• Score: 0.9558392439655014
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Wildfire burned-area mapping is essential for damage assessment, emissions modeling, and understanding fire-climate interactions across diverse ecological regions. Recent geospatial foundation models provide strong general-purpose representations for satellite imagery, yet there is still no clear understanding of how to efficiently adapt these models for downstream Earth observation tasks, particularly under geographic and temporal domain shift. This study evaluates three state-of-the-art Geospatial Foundation Models (GFMs) - Terramind, DINOv3, and Prithvi-v2 - for burned-area mapping across the United States and Canada using Sentinel-2 data. Leveraging 3,820 wildfire events from 2017-2023, we conduct spatial and temporal generalization tests across diverse biomes. We systematically compare full fine-tuning, decoder-only fine-tuning, and Low-Rank Adaptation (LoRA) for adapting each model. Across all experiments, LoRA provides the strongest cross-domain generalization while updating less than 1% of parameters, demonstrating a favorable trade-off between accuracy and efficiency. Prithvi-v2 with LoRA achieves the highest overall accuracy and the largest improvement compared to full fine-tuning. These findings indicate that geospatial foundation models, when adapted using lightweight parameter-efficient methods such as LoRA, offer a robust and scalable solution for large-scale burned-area mapping. Code is available at https://github.com/alishibli97/wildfire-lora-gfm.

Related papers

• Spectral-Morphological Attention U-Net: An Efficient Network for Active Wildfire Detection [0.692305735698369]
  We propose a new model named spectral-morphological attention U-Net(SMA-UNet), which includes a spectral attention module, a residual attention UNet backbone, a channel-spatial modulator, and a pair of differentiable morphological gates.<n>These modules, excluding the backbone, are used to detect active fire events for the first time, especially the pair of differentiable morphological gates.
  arXiv  Detail & Related papers  (2026-07-17T19:37:16Z)
• GEO-Bench-2: From Performance to Capability, Rethinking Evaluation in Geospatial AI [52.13138825802668]
  GeoFMs are transforming Earth Observation, but evaluation lacks standardized protocols.<n> GEO-Bench-2 addresses this with a comprehensive framework spanning classification, segmentation, regression, object detection, and instance segmentation.<n>Code, data, and leaderboard for GEO-Bench-2 are publicly released under a permissive license.
  arXiv  Detail & Related papers  (2025-11-19T17:45:02Z)
• TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation [65.74990259650984]
  We introduce TerraFM, a scalable self-supervised learning model that leverages globally distributed Sentinel-1 and Sentinel-2 imagery.<n>Our training strategy integrates local-global contrastive learning and introduces a dual-centering mechanism.<n>TerraFM achieves strong generalization on both classification and segmentation tasks, outperforming prior models on GEO-Bench and Copernicus-Bench.
  arXiv  Detail & Related papers  (2025-06-06T17:59:50Z)
• The World As Large Language Models See It: Exploring the reliability of LLMs in representing geographical features [0.0]
  This study evaluates the performance of GPT-4o and Gemini 2.0 Flash in three key geospatial tasks: geocoding, elevation estimation, and reverse geocoding.<n>Neither model achieved an accurate reconstruction of Austria's federal states, highlighting persistent misclassifications.
  arXiv  Detail & Related papers  (2025-05-30T20:14:17Z)
• EarthMapper: Visual Autoregressive Models for Controllable Bidirectional Satellite-Map Translation [50.433911327489554]
  We introduce EarthMapper, a novel framework for controllable satellite-map translation.<n>We also contribute CNSatMap, a large-scale dataset comprising 302,132 precisely aligned satellite-map pairs across 38 Chinese cities.<n> experiments on CNSatMap and the New York dataset demonstrate EarthMapper's superior performance.
  arXiv  Detail & Related papers  (2025-04-28T02:41:12Z)
• A Deep Learning Architecture for Land Cover Mapping Using Spatio-Temporal Sentinel-1 Features [1.907072234794597]
  The study focuses on three distinct regions - Amazonia, Africa, and Siberia - and evaluates the model performance across diverse ecoregions within these areas.<n>The results demonstrate the effectiveness and the capabilities of the proposed methodology in achieving overall accuracy (O.A.) values, even in regions with limited training data.
  arXiv  Detail & Related papers  (2025-03-10T12:15:35Z)
• LiDAR-based Registration against Georeferenced Models for Globally Consistent Allocentric Maps [16.335109366948473]
  Modern unmanned aerial vehicles (UAVs) are irreplaceable in search and rescue (SAR) missions to obtain a situational overview or provide closeups without endangering personnel.<n>However, UAVs heavily rely on global navigation satellite system (GNSS) for localization which works well in open spaces, but the precision drastically degrades in the vicinity of buildings.<n>In contrast, CityGML models provide approximate building shapes with accurate georeferenced poses.
  arXiv  Detail & Related papers  (2024-12-03T16:25:08Z)
• Comparing remote sensing-based forest biomass mapping approaches using new forest inventory plots in contrasting forests in northeastern and southwestern China [6.90293949599626]
  Large-scale high spatial resolution aboveground biomass (AGB) maps play a crucial role in determining forest carbon stocks and how they are changing. GEDI is a sampling instrument, collecting dispersed footprints, and its data must be combined with that from other continuous cover satellites to create high-resolution maps. We developed local models to estimate forest AGB from GEDI L2A data, as the models used to create GEDI L4 AGB data incorporated minimal field data from China.
  arXiv  Detail & Related papers  (2024-05-24T11:10:58Z)
• FLOGA: A machine learning ready dataset, a benchmark and a novel deep learning model for burnt area mapping with Sentinel-2 [41.28284355136163]
  Wildfires pose significant threats to human and animal lives, ecosystems, and socio-economic stability. In this work, we create and introduce a machine-learning ready dataset we name FLOGA (Forest wiLdfire Observations for the Greek Area) This dataset is unique as it comprises of satellite imagery acquired before and after a wildfire event. We use FLOGA to provide a thorough comparison of multiple Machine Learning and Deep Learning algorithms for the automatic extraction of burnt areas.
  arXiv  Detail & Related papers  (2023-11-06T18:42:05Z)
• Energy-Based Models for Cross-Modal Localization using Convolutional Transformers [52.27061799824835]
  We present a novel framework for localizing a ground vehicle mounted with a range sensor against satellite imagery in the absence of GPS. We propose a method using convolutional transformers that performs accurate metric-level localization in a cross-modal manner. We train our model end-to-end and demonstrate our approach achieving higher accuracy than the state-of-the-art on KITTI, Pandaset, and a custom dataset.
  arXiv  Detail & Related papers  (2023-06-06T21:27:08Z)
• GeoNet: Benchmarking Unsupervised Adaptation across Geographies [71.23141626803287]
  We study the problem of geographic robustness and make three main contributions. First, we introduce a large-scale dataset GeoNet for geographic adaptation. Second, we hypothesize that the major source of domain shifts arise from significant variations in scene context. Third, we conduct an extensive evaluation of several state-of-the-art unsupervised domain adaptation algorithms and architectures.
  arXiv  Detail & Related papers  (2023-03-27T17:59:34Z)
• Activation Regression for Continuous Domain Generalization with Applications to Crop Classification [48.795866501365694]
  Geographic variance in satellite imagery impacts the ability of machine learning models to generalise to new regions. We model geographic generalisation in medium resolution Landsat-8 satellite imagery as a continuous domain adaptation problem. We develop a dataset spatially distributed across the entire continental United States.
  arXiv  Detail & Related papers  (2022-04-14T15:41:39Z)

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.