A tuning-free wildfire detection algorithm reveals the impact of both Chornobyl wildfires and the Russian invasion of Ukraine in 2022

Autor: Jun Hu, Yasunori Igarashi, Shunji Kotsuki, Ziping Yang, Mykola Talerko, Volodymyr Landin, Olga Tischenko, Mark Zheleznyak, Valentyn Protsak, Serhii Kirieiev
Rok vydání: 2022
Popis: The 2020 wildfires in the Chornobyl Exclusion Zone (ChEZ) have caused widespread public concern about the potential risk of radiation exposure from radionuclides resuspended and redistributed due to the fires. In this study, we developed a tuning-free wildfire detection algorithm (TuFda) to perform rapid detection of burned areas for the purpose of immediate post-fire assessment. We applied TuFda to detect wildfires in the ChEZ during the spring of 2022. The size of the burned areas in February and March was estimated as 0.4 km2 and 70 km2, respectively. We also applied the algorithm to other areas outside the boundaries of the ChEZ and detected land surface changes totaling 553 km2 in northern Ukraine between February and March 2022. These changes may have occurred as a result of the Russian invasion. This study is the first to identify areas in northern Ukraine impacted by both wildfires and the Russian invasion of Ukraine in 2022. Our algorithm facilitates the rapid provision of accurate information on significant land surface changes whether caused by wildfires, military action, or any other factor.
Databáze: OpenAIRE