MMSeaIce: a collection of techniques for improving sea ice mapping with a multi-task model
-
Published:2024-04-08
Issue:4
Volume:18
Page:1621-1632
-
ISSN:1994-0424
-
Container-title:The Cryosphere
-
language:en
-
Short-container-title:The Cryosphere
Author:
Chen XinweiORCID, Patel Muhammed, Pena Cantu Fernando J., Park Jinman, Noa Turnes Javier, Xu Linlin, Scott K. Andrea, Clausi David A.
Abstract
Abstract. The AutoICE challenge, organized by multiple national and international agencies, seeks to advance the development of near-real-time sea ice products with improved spatial resolution, broader spatial and temporal coverage, and enhanced consistency. In this paper, we present a detailed description of our solutions and experimental results for the challenge. We have implemented an automated sea ice mapping pipeline based on a multi-task U-Net architecture, capable of predicting sea ice concentration (SIC), stage of development (SOD), and floe size (FLOE). The AI4Arctic dataset, which includes synthetic aperture radar (SAR) imagery, ancillary data, and ice-chart-derived label maps, is utilized for model training and evaluation. Among the submissions from over 30 teams worldwide, our team achieved the highest combined score of 86.3 %, as well as the highest scores on SIC (92.0 %) and SOD (88.6 %). Notably, the result analysis and ablation studies demonstrate that instead of model architecture design, a collection of strategies/techniques we employed led to substantial enhancement in accuracy, efficiency, and robustness within the realm of deep-learning-based sea ice mapping. Those techniques include input SAR variable downscaling, input feature selection, spatial–temporal encoding, and the choice of loss functions. By highlighting the various techniques employed and their impacts, we aim to underscore the scientific advancements achieved in our methodology.
Funder
Environment and Climate Change Canada Natural Sciences and Engineering Research Council of Canada
Publisher
Copernicus GmbH
Reference42 articles.
1. Boulze, H., Korosov, A., and Brajard, J.: Classification of sea ice types in Sentinel-1 SAR data using convolutional neural networks, Remote Sens., 12, 2165, https://doi.org/10.3390/rs12132165, 2020. a 2. Buus-Hinkler, J., Wulf, T., Stokholm, A. R., Korosov, A., Saldo, R., Pedersen, L. T., Arthurs, D., Solberg, R., Longépé, N., and Brandt Kreiner, M.: AI4Arctic Sea Ice Challenge Dataset, DTU [code and data set], https://doi.org/10.11583/DTU.c.6244065.v2, 2022. a, b, c 3. Chen, S., Shokr, M., Li, X., Ye, Y., Zhang, Z., Hui, F., and Cheng, X.: MYI floes identification based on the texture and shape feature from dual-polarized Sentinel-1 imagery, Remote Sens., 12, 3221, 2020. a 4. Chen, X., Scott, K. A., Jiang, M., Fang, Y., Xu, L., and Clausi, D. A.: Sea Ice Classification With Dual-Polarized SAR Imagery: A Hierarchical Pipeline, in: Proc. IEEE/CVF Winter Conf. Appl. Comput. Vis., Waikoloa, USA, January, 2023, 224–232, 2023a. a 5. Chen, X., Valencia, R., Soleymani, A., and Scott, K. A.: Predicting Sea Ice Concentration With Uncertainty Quantification Using Passive Microwave and Reanalysis Data: A Case Study in Baffin Bay, IEEE Trans. Geosci. Remote Sens., 61, 1–13, https://doi.org/10.1109/TGRS.2023.3250164, 2023b. a, b
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|