Multitemporal monitoring of Impervious Surface Areas (ISA) changes in an Arctic setting, using ML, Remote Sensing data and GEE

Urban expansion in Arctic environments presents unique challenges and opportunities for sustainable development, environmental management, and adaptation to the impacts of climate change. The special characteristics of these regions, including extreme climatic conditions and limited infrastructure, require customized approaches for monitoring and planning urban growth. The aim of the present study is the multi-temporal mapping of urban changes, through Impervious Surface Areas (ISA), in an Arctic setting characterized by high structural density, over the past decade. This endeavor is implemented by the application of Machine Learning classification methods in conjunction with Sentinel satellite imagery, while the execution of this methodology is carried out in Google Earth Engine (GEE) cloud platform. The results of this study map with high accuracy ISA changes in Tromso area from 1993 to 2023. These findings hold the promise of enhancing our comprehension of the dynamics behind urban expansion, the primary factors associated with urban sprawl and their interaction with the challenges posed by climate change in Arctic environments