The main objectives of this paper are to demonstrate the results of an ensemble learning method based on prediction results of support vector machine and random forest methods using Bayesian average. In this study, we generated susceptibility maps of forest fire using supervised machine learning method (support vector machine—SVM) and its comparison with a versatile machine learning algorithm (random forest—RF) and their ensembles. In order to achieve this, first of all, a forest fire inventory map was constructed using Serbian historical forest fire database, Moderate Resolution Imaging Spectro radiometer (MODIS), Landsat 8 OLI and Worldview-2 satellite images, field surveys, and interpretation of aerial photo images. A total of 126 forest fire locations were identified and randomly divided by a random selection algorithm into two groups, including training (70%) and validation data sets (30%). Forest fire susceptibility maps were prepared using SVM, RF, and their ensemble models using the training dataset and 14 selected different conditioning factors. Finally, to explore the performance of the mentioned models we used the values for area under the curve (AUC) of receiver operating characteristics (ROC). The results depicted that the ensemble model had an AUC = 0.848, followed by the SVM model (AUC = 0.844), and RF model (AUC = 0.834). According to achieved AUC results, it can be deduced that SVM, RF, and their ensemble method had satisfactory performance. The study was applied in the Tara National Park (West Serbia), a region of about 191.7 sq. km distinguished by a very high forest density and a large number of forest fires.

Frequent flooding can greatly jeopardize local people’s lives, properties, agriculture, economy, etc. The Swat River Basin (SRB), in the eastern Hindukush region of Pakistan, is a major flood-prone basin with a long history of devastating floods and substantial socioeconomic and physical damages. Here we produced a flood susceptibility map of the SRB, using the frequency ratio (FR) bivariate statistical model. A database was created that comprised flood inventory as a dependent variable and causative factors of the flood (slope, elevation, curvature, drainage density, topographic wetness index, stream power index, land use land cover, normalized difference vegetation index, and rainfall) as independent variables and the association between them were quantified. Data were collected using remote sensing sources, field surveys, and available literature, and all the studied variables were resampled to 30 m resolution and spatially distributed. The results show that about 26% of areas are very high and highly susceptible to flooding, 19% are moderate, whereas 55% are low and very low susceptible to flood in the SRB. Overall, the southern areas of the SRB were highly susceptible compared to their northern counterparts, while slope, elevation, and curvature were vital factors in flood susceptibility. Our model’s success and prediction rates were 91.6% and 90.3%, respectively, based on the ROC (receiver operating characteristic) curve. The findings of this study will lead to better management and control of flood risk in the SRB region. The study’s findings can assist the decision-makers to make appropriate sustainable management strategies for the mitigation of future damage in the study region.