Assessing Foundation Models for Sea Ice Type Segmentation in Sentinel-1 SAR Imagery

• URL: http://arxiv.org/abs/2503.22516v1
• Date: Fri, 28 Mar 2025 15:21:08 GMT
• Title: Assessing Foundation Models for Sea Ice Type Segmentation in Sentinel-1 SAR Imagery
• Authors: Samira Alkaee Taleghan, Morteza Karimzadeh, Andrew P. Barrett, Walter N. Meier, Farnoush Banaei-Kashani,
• Abstract summary: This study evaluates ten foundation models (FMs) for sea ice type segmentation using Sentinel-1 imagery.<n>Among the selected models, Prithvi-600M outperforms the baseline models, while CROMA achieves a very similar performance in F1-score.
• Score: 2.255599116578844
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate segmentation of sea ice types is essential for mapping and operational forecasting of sea ice conditions for safe navigation and resource extraction in ice-covered waters, as well as for understanding polar climate processes. While deep learning methods have shown promise in automating sea ice segmentation, they often rely on extensive labeled datasets which require expert knowledge and are time-consuming to create. Recently, foundation models (FMs) have shown excellent results for segmenting remote sensing images by utilizing pre-training on large datasets using self-supervised techniques. However, their effectiveness for sea ice segmentation remains unexplored, especially given sea ice's complex structures, seasonal changes, and unique spectral signatures, as well as peculiar Synthetic Aperture Radar (SAR) imagery characteristics including banding and scalloping noise, and varying ice backscatter characteristics, which are often missing in standard remote sensing pre-training datasets. In particular, SAR images over polar regions are acquired using different modes than used to capture the images at lower latitudes by the same sensors that form training datasets for FMs. This study evaluates ten remote sensing FMs for sea ice type segmentation using Sentinel-1 SAR imagery, focusing on their seasonal and spatial generalization. Among the selected models, Prithvi-600M outperforms the baseline models, while CROMA achieves a very similar performance in F1-score. Our contributions include offering a systematic methodology for selecting FMs for sea ice data analysis, a comprehensive benchmarking study on performances of FMs for sea ice segmentation with tailored performance metrics, and insights into existing gaps and future directions for improving domain-specific models in polar applications using SAR data.

Related papers

• Efficient Self-Supervised Learning for Earth Observation via Dynamic Dataset Curation [67.23953699167274]
  Self-supervised learning (SSL) has enabled the development of vision foundation models for Earth Observation (EO) In EO, this challenge is amplified by the redundancy and heavy-tailed distributions common in satellite imagery. We propose a dynamic dataset pruning strategy designed to improve SSL pre-training by maximizing dataset diversity and balance.
  arXiv  Detail & Related papers  (2025-04-09T15:13:26Z)
• PolSAM: Polarimetric Scattering Mechanism Informed Segment Anything Model [76.95536611263356]
  PolSAR data presents unique challenges due to its rich and complex characteristics.<n>Existing data representations, such as complex-valued data, polarimetric features, and amplitude images, are widely used.<n>Most feature extraction networks for PolSAR are small, limiting their ability to capture features effectively.<n>We propose the Polarimetric Scattering Mechanism-Informed SAM (PolSAM), an enhanced Segment Anything Model (SAM) that integrates domain-specific scattering characteristics and a novel prompt generation strategy.
  arXiv  Detail & Related papers  (2024-12-17T09:59:53Z)
• SIFM: A Foundation Model for Multi-granularity Arctic Sea Ice Forecasting [19.23074065880929]
  We propose to cultivate temporal multi-granularity that naturally derived from Arctic sea ice reanalysis data. Our Sea Ice Foundation Model ( SIFM) is designed to leverage both intra-granularity and inter-granularity information. Our experiments show that SIFM outperforms off-the-shelf deep learning models for their specific temporal granularity.
  arXiv  Detail & Related papers  (2024-10-16T08:52:12Z)
• SatSynth: Augmenting Image-Mask Pairs through Diffusion Models for Aerial Semantic Segmentation [69.42764583465508]
  We explore the potential of generative image diffusion to address the scarcity of annotated data in earth observation tasks. To the best of our knowledge, we are the first to generate both images and corresponding masks for satellite segmentation.
  arXiv  Detail & Related papers  (2024-03-25T10:30:22Z)
• Deep Learning on SAR Imagery: Transfer Learning Versus Randomly Initialized Weights [1.6969743728555278]
  We compare the performance of deep learning models trained from scratch and pretrained models that we fine-tune for this purpose. Our results show that pre-trained models lead to better results, especially on test samples from the melt season.
  arXiv  Detail & Related papers  (2023-10-26T03:52:54Z)
• MT-IceNet -- A Spatial and Multi-Temporal Deep Learning Model for Arctic Sea Ice Forecasting [0.31410342959104726]
  We propose MT-IceNet - a UNet based spatial and multi-temporal (MT) deep learning model for forecasting Arctic sea ice concentration (SIC) Our proposed model provides promising predictive performance for per-pixel SIC forecasting with up to 60% decrease in prediction error for a lead time of 6 months as compared to its state-of-the-art counterparts.
  arXiv  Detail & Related papers  (2023-08-08T18:18:31Z)
• Exploring the Application of Large-scale Pre-trained Models on Adverse Weather Removal [97.53040662243768]
  We propose a CLIP embedding module to make the network handle different weather conditions adaptively. This module integrates the sample specific weather prior extracted by CLIP image encoder together with the distribution specific information learned by a set of parameters.
  arXiv  Detail & Related papers  (2023-06-15T10:06:13Z)
• DeepAqua: Self-Supervised Semantic Segmentation of Wetland Surface Water Extent with SAR Images using Knowledge Distillation [44.99833362998488]
  We present DeepAqua, a self-supervised deep learning model that eliminates the need for manual annotations during the training phase. We exploit cases where optical- and radar-based water masks coincide, enabling the detection of both open and vegetated water surfaces. Experimental results show that DeepAqua outperforms other unsupervised methods by improving accuracy by 7%, Intersection Over Union by 27%, and F1 score by 14%.
  arXiv  Detail & Related papers  (2023-05-02T18:06:21Z)
• Data-Driven Short-Term Daily Operational Sea Ice Regional Forecasting [52.77986479871782]
  Global warming made the Arctic available for marine operations and created demand for reliable operational sea ice forecasts. In this work, we investigate the performance of the U-Net model trained in two regimes for predicting sea ice for up to the next 10 days. We show that this deep learning model can outperform simple baselines by a significant margin and improve its quality by using additional weather data and training on multiple regions.
  arXiv  Detail & Related papers  (2022-10-17T09:14:35Z)
• Learning-based estimation of in-situ wind speed from underwater acoustics [58.293528982012255]
  We introduce a deep learning approach for the retrieval of wind speed time series from underwater acoustics. Our approach bridges data assimilation and learning-based frameworks to benefit both from prior physical knowledge and computational efficiency.
  arXiv  Detail & Related papers  (2022-08-18T15:27:40Z)
• Guided deep learning by subaperture decomposition: ocean patterns from SAR imagery [36.922471841100176]
  Sentinel 1 SAR wave mode vignettes have made possible to capture many important oceanic and atmospheric phenomena since 2014. In this study, we propose to apply subaperture decomposition as a preprocessing stage for SAR deep learning models.
  arXiv  Detail & Related papers  (2022-04-09T09:49:05Z)
• Recognition of polar lows in Sentinel-1 SAR images with deep learning [5.571369922847262]
  We introduce a novel dataset consisting of Sentinel-1 images labeled as positive; representing a maritime mesocyclone, or negative; representing a normal sea state. The dataset is used to train a deep learning model to classify the labeled images. The model yields an F-1 score of 0.95, indicating that polar lows can be consistently detected from SAR images.
  arXiv  Detail & Related papers  (2022-03-30T15:32:39Z)

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.