Guardado en:
Detalles Bibliográficos
Autores principales: Heffring, Mabel, Xu, Lincoln Linlin
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2509.25437
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912615812300800
author Heffring, Mabel
Xu, Lincoln Linlin
author_facet Heffring, Mabel
Xu, Lincoln Linlin
contents Although high-resolution mapping of Pan-Arctic sea ice with reliable corresponding uncertainty is essential for operational sea ice concentration (SIC) charting, it is a difficult task due to some key challenges, e.g., the subtle nature of ice signature features, model uncertainty, and data heterogeneity. This letter presents a novel Bayesian Transformer approach for Pan-Arctic SIC mapping and uncertainty quantification using Sentinel-1, RADARSAT Constellation Mission (RCM), and Advanced Microwave Scanning Radiometer 2 (AMSR2) data. First, to improve feature extraction, we design a novel high-resolution Transformer model with both global and local modules that can better discern the subtle differences in sea ice patterns. Second, to improve uncertainty quantification, we design a Bayesian extension of the proposed Transformer model, treating its parameters as random variables to more effectively capture uncertainties. Third, to address data heterogeneity, we fuse three different data types (Sentinel-1, RCM, and AMSR2) at decision-level to improve both SIC mapping and uncertainty quantification. The proposed approach is tested on Pan-Arctic datasets from September 2021, and the results demonstrate that the proposed model can achieve both high-resolution SIC maps and robust uncertainty maps compared to other uncertainty quantification approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2509_25437
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bayesian Transformer for Pan-Arctic Sea Ice Concentration Mapping and Uncertainty Estimation using Sentinel-1, RCM, and AMSR2 Data
Heffring, Mabel
Xu, Lincoln Linlin
Computer Vision and Pattern Recognition
Machine Learning
Although high-resolution mapping of Pan-Arctic sea ice with reliable corresponding uncertainty is essential for operational sea ice concentration (SIC) charting, it is a difficult task due to some key challenges, e.g., the subtle nature of ice signature features, model uncertainty, and data heterogeneity. This letter presents a novel Bayesian Transformer approach for Pan-Arctic SIC mapping and uncertainty quantification using Sentinel-1, RADARSAT Constellation Mission (RCM), and Advanced Microwave Scanning Radiometer 2 (AMSR2) data. First, to improve feature extraction, we design a novel high-resolution Transformer model with both global and local modules that can better discern the subtle differences in sea ice patterns. Second, to improve uncertainty quantification, we design a Bayesian extension of the proposed Transformer model, treating its parameters as random variables to more effectively capture uncertainties. Third, to address data heterogeneity, we fuse three different data types (Sentinel-1, RCM, and AMSR2) at decision-level to improve both SIC mapping and uncertainty quantification. The proposed approach is tested on Pan-Arctic datasets from September 2021, and the results demonstrate that the proposed model can achieve both high-resolution SIC maps and robust uncertainty maps compared to other uncertainty quantification approaches.
title Bayesian Transformer for Pan-Arctic Sea Ice Concentration Mapping and Uncertainty Estimation using Sentinel-1, RCM, and AMSR2 Data
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2509.25437