A machine learning method for Arctic lakes detection in the permafrost areas of Siberia

• Published in: European Journal of Remote Sensing
• Main Authors: Piotr Janiec, Jakub Nowosad, Zbigniew Zwoliński
• Format: Article in Journal/Newspaper
• Language: English
• Published: Taylor & Francis Group 2023
• Subjects: Thermokarst lakes; subpolar areas; Landsat; MERIT DEM; supervised classification; Siberia; Oceanography; GC1-1581; Geology; QE1-996.5; Arctic; permafrost; Subarctic; Thermokarst; Yakutia
• Online Access: https://doi.org/10.1080/22797254.2022.2163923; https://doaj.org/article/73d3be4c3a1f4b18a512deac53b10acd

ABSTRACTThermokarst lakes are the main components of the vast Arctic and subarctic landscapes. These lakes can serve as geoindicators of permafrost degradation; therefore, proper lake distribution assessment methods are necessary. In this study, we compared four machine learning methods to improve existing lake detection systems. The northern part of Yakutia was selected as the study area owing to its complex environment. We used data from Landsat 8 and spectral indices to take into account the spectral characteristics of the lakes, and MERIT DEM data to take into account the topography. The lowest accuracy was found for the classification and regression trees (CART) method (overall accuracy = 81%). On the other hand, the random forests (RF) classification provided the best results (overall accuracy = 92%), and only this classification coped well in all problematic areas, such as shaded and humid areas, near steep slopes, burn scars, and rivers. The altitude and bands SWIR1 (Short wave infrared 1), SWIR2 (Short wave infrared 2), and Green were the most important. Spectral indices did not have significant impact on the classification results in the specific conditions of the thermokarst lakes environment. 17,700 lakes were identified with the total area of 271.43 km2.