Use of the U-Net convolutional neural network and its modifications for segmentation of tundra lakes in satellite optical images
I.A. Abramova1, D.M. Demchev2, E.V. Kharyutkina2,3, E.N. Savenkova2,4, I.A. Sudakov5
1Federal State Budgetary Institution "Arctic and Antarctic Research Institute", St. Petersburg, Russia
2OOO "TSNIR", Velikiy Novgorod, Russia
3Institute of Monitoring of Climatic and Ecological Systems of the Siberian Branch of the Russian Academy of Sciences, Tomsk, Russia
4Russian State Hydrometeorological University, St. Petersburg, Russia
5School of Mathematics and Statistics, The Open University, Milton Keynes, UK
Keywords: tundra lakes, U-Net, Arctic, remote sensing, permafrost
Abstract
Tundra lakes are an important indicator of climate change; therefore, the analysis of the dynamics of their size is of particular interest. This paper presents the results of using the U-Net convolutional neural network for tundra lakes segmentation in satellite optical images using Landsat data as an example. The comparative assessment of segmentation accuracy is performed for the original U-Net design and its modifications: U-Net++, Attention U-Net, and R2 U-Net, including with weights derived from a pre-trained VGG16 network. The segmentation accuracy is assessed based on the results of manual mapping of tundra lakes in northern Siberia. It is shown that more recent U-Net modifications do not provide a practically significant gain in segmentation accuracy, but increase the computational costs. A configuration based on the classic U-Net gives the best result in most cases (the average Soerens coefficient IoU = 0.88). The technique suggested and the resulting estimates can be used in analysis of modern climate trends.
|
