A Comparison of Two Machine Learning Classification Methods for Remote Sensing Predictive Modeling of the Forest Fire in the North-Eastern Siberia

• Published in: Remote sensing (Basel, Switzerland) Vol. 12; no. 24; pp. 4157 - 20
• Main Authors: Janiec, Piotr, Gadal, Sébastien
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 18.12.2020; MDPI
• Subjects: Anthropogenic factors; Bioclimatology; Computer Science; Entropy; Environment and Society; Environmental Sciences; Fire prevention; Forest & brush fires; Forest fires; Forest management; Geography; Geology; GIS; Human influences; Humanities and Social Sciences; Image Processing; Landsat; Landsat satellites; Learning algorithms; Machine learning; MaxENT; Maximum entropy; Maximum entropy method; Methods and statistics; Modeling and Simulation; Modelling; multi-scale analysis; Permafrost; Population density; Precipitation; Prediction models; random forest; Remote sensing; Risk analysis; Risk assessment; Risk factors; risk modeling; Satellite imagery; Satellites; Spectral resolution; Taiga & tundra; Timber; Wildfires; United States > US; Siberia; Russia; GIS; Yakutia; Wildfires; MaxENT; Multi-scale Analysis; Siberia; Risk Modeling; Arctic; Random Forest
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs12244157

The problem of forest fires in Yakutia is not as well studied as in other countries. Two methods of machine learning classifications were implemented to determine the risk of fire: MaxENT and random forest. The initial materials to define fire risk factors were satellite images and their products of various spatial and spectral resolution (Landsat TM, Modis TERRA, GMTED2010, VIIRS), vector data (OSM), and bioclimatic variables (WORLDCLIM). The results of the research showed a strong human influence on the risk in this region, despite the low population density. Anthropogenic factors showed a high correlation with the occurrence of wildfires, more than climatic or topographical factors. Other factors affect the risk of fires at the macroscale and microscale, which should be considered when modeling. The random forest method showed better results in the macroscale, however, the maximum entropy model was better in the microscale. The exclusion of variables that do not show a high correlation, does not always improve the modeling results. The random forest presence prediction model is a more accurate method and significantly reduces the risk territory. The reverse is the method of maximum entropy, which is not as accurate and classifies very large areas as endangered. Further study of this topic requires a clearer and conceptually developed approach to the application of remote sensing data. Therefore, this work makes sense to lay the foundations of the future, which is a completely automated fire risk assessment application in the Republic of Sakha. The results can be used in fire prophylactics and planning fire prevention. In the future, to determine the risk well, it is necessary to combine the obtained maps with the seasonal risk determined using indices (for example, the Nesterov index 1949) and the periodic dynamics of forest fires, which Isaev and Utkin studied in 1963. Such actions can help to build an application, with which it will be possible to determine the risk of wildfire and the spread of fire during extreme events.