Preprints
https://doi.org/10.5194/egusphere-2023-1810
https://doi.org/10.5194/egusphere-2023-1810
28 Sep 2023
 | 28 Sep 2023

Using Deep Learning and Multi-source Remote Sensing Images to Map Landlocked Lakes in Antarctica

Anyao Jiang, Xin Meng, Yan Huang, and Guitao Shi

Abstract. Antarctic landlocked lakes' open water (LLOW) plays an important role in the Antarctic ecosystem and serves as a reliable climate indicator. However, since field surveys are currently the main method to study Antarctic landlocked lakes, the spatial and temporal distribution of landlocked lakes across Antarctica remains understudied. We first developed an automated detection workflow for Antarctic LLOW using deep learning and multi-source satellite images. The U-Net model and LLOW identification model achieved average Kappa values of 0.85 and 0.62 on testing datasets respectively, demonstrating strong spatio-temporal robustness across various study areas. We chose four typical ice-free areas located along the coastal Antarctica as our study areas. After applying our LLOW identification model to a total of 79 Landsat 8-9 images and 390 Sentinel-1 images in these four regions, we generated high spatiotemporal resolution LLOW time series from January to April between 2017 and 2021. We analyzed the fluctuation of LLOW areas in the four study areas, and found that during expansion of LLOW, over 90 % of the changes were explained by positive degree days; while during contraction, air temperature changes accounted for more than 50 % of the LLOW area fluctuations. It is shown that our model can provide long-term LLOW series products that help us better understand how lakes change under a changing climate in the future.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Anyao Jiang, Xin Meng, Yan Huang, and Guitao Shi

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2023-1810', Anonymous Referee #1, 22 Nov 2023
  • RC2: 'Comment on egusphere-2023-1810', Anonymous Referee #2, 19 Dec 2023
  • EC1: 'Comment on egusphere-2023-1810', Nicholas Barrand, 21 Feb 2024
Anyao Jiang, Xin Meng, Yan Huang, and Guitao Shi
Anyao Jiang, Xin Meng, Yan Huang, and Guitao Shi

Viewed

Total article views: 555 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
367 153 35 555 47 24 28
  • HTML: 367
  • PDF: 153
  • XML: 35
  • Total: 555
  • Supplement: 47
  • BibTeX: 24
  • EndNote: 28
Views and downloads (calculated since 28 Sep 2023)
Cumulative views and downloads (calculated since 28 Sep 2023)

Viewed (geographical distribution)

Total article views: 534 (including HTML, PDF, and XML) Thereof 534 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 23 Jul 2024
Download
Short summary
Landlocked lakes are crucial in the Antarctic ecosystem and sensitive to climate change. Limited research on their distribution prompted us to develop an automated detection process using deep learning and multi-source satellite imagery. This allowed us to accurately determine the landlocked lakes’ open water (LLOW) area in Antarctica, generating high-resolution time series data. We find that the changes in positive degree days and air temperature predominantly drive variations in the LLOW area.