Automated Identification of Landfast Sea Ice in the Laptev Sea from the True-Color MODIS Images Using the Method of Deep Learning
Landfast sea ice (LFSI) refers to sea ice attached to the shoreline with little or no horizonal motion in contrast to drifting sea ice. The LFSI plays an important role in the Arctic marine environmental and biological systems. Therefore, it is crucial to accurately monitor the spatiotemporal change...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/6/1610 |
| _version_ | 1797609245590421504 |
|---|---|
| author | Cheng Wen Mengxi Zhai Ruibo Lei Tao Xie Jinshan Zhu |
| author_facet | Cheng Wen Mengxi Zhai Ruibo Lei Tao Xie Jinshan Zhu |
| author_sort | Cheng Wen |
| collection | DOAJ |
| description | Landfast sea ice (LFSI) refers to sea ice attached to the shoreline with little or no horizonal motion in contrast to drifting sea ice. The LFSI plays an important role in the Arctic marine environmental and biological systems. Therefore, it is crucial to accurately monitor the spatiotemporal changes in the LFSI distribution. Here we present an automatic LFSI retrieval method for the Laptev Sea, eastern Arctic Ocean, based on a conditional generative adversarial network Pix2Pix using the true-color images of Moderate Resolution Imaging Spectroradiometer (MODIS). The spatial resolution of the derived product is 1.25 km, with a temporal interval of 7 days. Compared to the manually identified data from the true-color images of MODIS, the average precision of the LFSI area derived from LFSI mapping model reaches 91.4%, with the recall reaching 98.7% and F1-score reaching 94.5%. The LFSI coverage is consistent with the traditional large-scale LFSI products, but provides more details. Intraseasonal and interannual variations in LFSI area of the Laptev Sea in spring (March–May) during the period of 2002–2021 are investigated using the new product. The spring LFSI area in this region decreases at a rate of 0.67 × 10<sup>3</sup> km<sup>2</sup> per year during this period (R<sup>2</sup> = 0.117, <i>p</i> < 0.01). According to the spatial and temporal changes, we conclude that the LFSI is becoming more stable while the area is shrinking. The method is fully-automatic and computationally efficient, which can be further applied to the entire Arctic Ocean for LFSI identification and monitoring. |
| first_indexed | 2024-03-11T05:57:49Z |
| format | Article |
| id | doaj.art-f5324c7da1a546ef8afc7f431b4a4891 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T05:57:49Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-f5324c7da1a546ef8afc7f431b4a48912023-11-17T13:39:30ZengMDPI AGRemote Sensing2072-42922023-03-01156161010.3390/rs15061610Automated Identification of Landfast Sea Ice in the Laptev Sea from the True-Color MODIS Images Using the Method of Deep LearningCheng Wen0Mengxi Zhai1Ruibo Lei2Tao Xie3Jinshan Zhu4School of Remote Sensing and Geomatics Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaKey Laboratory for Polar Science of the MNR, Polar Research Institute of China, Shanghai 201209, ChinaKey Laboratory for Polar Science of the MNR, Polar Research Institute of China, Shanghai 201209, ChinaSchool of Remote Sensing and Geomatics Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaKey Laboratory of Ocean Geomatics, Ministry of Natural Resources, Qingdao 266590, ChinaLandfast sea ice (LFSI) refers to sea ice attached to the shoreline with little or no horizonal motion in contrast to drifting sea ice. The LFSI plays an important role in the Arctic marine environmental and biological systems. Therefore, it is crucial to accurately monitor the spatiotemporal changes in the LFSI distribution. Here we present an automatic LFSI retrieval method for the Laptev Sea, eastern Arctic Ocean, based on a conditional generative adversarial network Pix2Pix using the true-color images of Moderate Resolution Imaging Spectroradiometer (MODIS). The spatial resolution of the derived product is 1.25 km, with a temporal interval of 7 days. Compared to the manually identified data from the true-color images of MODIS, the average precision of the LFSI area derived from LFSI mapping model reaches 91.4%, with the recall reaching 98.7% and F1-score reaching 94.5%. The LFSI coverage is consistent with the traditional large-scale LFSI products, but provides more details. Intraseasonal and interannual variations in LFSI area of the Laptev Sea in spring (March–May) during the period of 2002–2021 are investigated using the new product. The spring LFSI area in this region decreases at a rate of 0.67 × 10<sup>3</sup> km<sup>2</sup> per year during this period (R<sup>2</sup> = 0.117, <i>p</i> < 0.01). According to the spatial and temporal changes, we conclude that the LFSI is becoming more stable while the area is shrinking. The method is fully-automatic and computationally efficient, which can be further applied to the entire Arctic Ocean for LFSI identification and monitoring.https://www.mdpi.com/2072-4292/15/6/1610Arctic Oceanlandfast sea iceareaPix2Pixdeep learning |
| spellingShingle | Cheng Wen Mengxi Zhai Ruibo Lei Tao Xie Jinshan Zhu Automated Identification of Landfast Sea Ice in the Laptev Sea from the True-Color MODIS Images Using the Method of Deep Learning Remote Sensing Arctic Ocean landfast sea ice area Pix2Pix deep learning |
| title | Automated Identification of Landfast Sea Ice in the Laptev Sea from the True-Color MODIS Images Using the Method of Deep Learning |
| title_full | Automated Identification of Landfast Sea Ice in the Laptev Sea from the True-Color MODIS Images Using the Method of Deep Learning |
| title_fullStr | Automated Identification of Landfast Sea Ice in the Laptev Sea from the True-Color MODIS Images Using the Method of Deep Learning |
| title_full_unstemmed | Automated Identification of Landfast Sea Ice in the Laptev Sea from the True-Color MODIS Images Using the Method of Deep Learning |
| title_short | Automated Identification of Landfast Sea Ice in the Laptev Sea from the True-Color MODIS Images Using the Method of Deep Learning |
| title_sort | automated identification of landfast sea ice in the laptev sea from the true color modis images using the method of deep learning |
| topic | Arctic Ocean landfast sea ice area Pix2Pix deep learning |
| url | https://www.mdpi.com/2072-4292/15/6/1610 |
| work_keys_str_mv | AT chengwen automatedidentificationoflandfastseaiceinthelaptevseafromthetruecolormodisimagesusingthemethodofdeeplearning AT mengxizhai automatedidentificationoflandfastseaiceinthelaptevseafromthetruecolormodisimagesusingthemethodofdeeplearning AT ruibolei automatedidentificationoflandfastseaiceinthelaptevseafromthetruecolormodisimagesusingthemethodofdeeplearning AT taoxie automatedidentificationoflandfastseaiceinthelaptevseafromthetruecolormodisimagesusingthemethodofdeeplearning AT jinshanzhu automatedidentificationoflandfastseaiceinthelaptevseafromthetruecolormodisimagesusingthemethodofdeeplearning |