KOPRI Repository

Deep learning based retrieval algorithm for Arctic sea ice concentration from AMSR2 passive microwave and MODIS optical data

Cited 2 time in wos
Cited 2 time in scopus
Metadata Downloads
Title
Deep learning based retrieval algorithm for Arctic sea ice concentration from AMSR2 passive microwave and MODIS optical data
Other Titles
수동마이크로파와 광학원격탐사자료를 이용한 딥러닝 기반 북극 해빙농도 산출 연구
Authors
Chi, Junhwa
Kim, Hyun-cheol
Lee, sungjae
Crawford, Melba M.
Subject
Environmental Sciences & Ecology; Remote Sensing; Imaging Science & Photographic Technology
Keywords
Spectral unmixing; Spectral mixture analysis; Endmember extraction; Machine learning; Neural network
Issue Date
2019-09
Citation
Chi, Junhwa, et al. 2019. "Deep learning based retrieval algorithm for Arctic sea ice concentration from AMSR2 passive microwave and MODIS optical data". REMOTE SENSING OF ENVIRONMENT, 231(1): 111204-0.
Abstract
This study applies deep learning (DL) to retrieve Arctic sea ice concentration (SIC) from AMSR2 data. MODIS-derived SICs are calculated based on spectral unmixing with a new ice/water endmember extraction algorithm that exploits global/local representatives, and then used to train a DL network with AMSR2 data. The resulting SIC maps outperform popular SIC products both regionally and globally. The RMSE of the proposed DL model is 5.19, whereas those of the widely used Bootstrap and ASI-based SIC images are 6.54 and 7.38, respectively, with respect to MODIS-derived SICs at global scale. In particular, our proposed method better describes regions of low-SIC and melting ice in summer, which are generally difficult-to-estimate. As the DL-based model consistently generates accurate SIC values that are not time- or region-dependent, it is considered to be an operational system. Additionally, our SICs can be used to generate initial conditions facilitating development of more accurate climate models.
URI
https://repository.kopri.re.kr/handle/201206/10919
DOI
http://dx.doi.org/10.1016/j.rse.2019.05.023
Appears in Collections  
2019-2019, Research on analytical technique for satellite observation of Arctic sea ice (19-19) / Kim, Hyun-cheol (PE19120)
Files in This Item

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse