Forest Fire Characterization Using Landsat-8 Satellite Data in Dalma Wildlife Sanctuary

A forest fire has caused a loss of biodiversity and forest heterogeneity and resulted in forest degradation and fragmentation. Remote sensing techniques have been widely used for locating and delineating forest fires. The present study has employed Landsat-8 satellite data during 2014-2020 for spatiotemporal analysis of forest fire in Dalma Wildlife Sanctuary (DWS). Normalized burn ratio (NBR) has been used to delineate forest fire-affected locations along with visual interpretation techniques. The results showed that an extensive area was burnt and deforested due to forest fire in DWS during 2014-2020. The burned areas due to forest fires within the notified forest boundary in DWS were 12.11 km², 25.5 km², 22.45 km², 9.11 km², 24.44 km², 10.09 km², and 1 km² during 2014, 2015, 2016, 2017, 2018, 2019, and 2020, respectively, whereas burned areas outside notified boundary were 2.24 km², 4.15 km², 1.48 km², 3.29 km², 3.31 km², 1.9 km², and 0.1 km². According to visual image interpretation, the highest burned area was found in 2015 (25.5 km²), whilst the least affected was found in 2020 (1 km²), and fires were mainly seen in the degraded forests and open forest regions. The present study revealed that forest fire is more dominant in Asanbani, Pardih, Bhelaipahari, Gobargushi, Bamri, Andharjhor, Somadih, Koira, Tetla, Bochkamkocha, Sah, Rbera, and Jamdih locations/beats in DWS. Thereby, these forest beats need attention from forest managers to control fire-mediated forest degradation for the conservation and restoration of forests in DWS.

Active Fire Detection from Landsat-8 Imagery Using Deep Multiple Kernel Learning

Active fires are devastating natural disasters that cause socio-economical damage across the globe. The detection and mapping of these disasters require efficient tools, scientific methods, and reliable observations. Satellite images have been widely used for active fire detection (AFD) during the past years due to their nearly global coverage. However, accurate AFD and mapping in satellite imagery is still a challenging task in the remote sensing community, which mainly uses traditional methods. Deep learning (DL) methods have recently yielded outstanding results in remote sensing applications. Nevertheless, less attention has been given to them for AFD in satellite imagery. This study presented a deep convolutional neural network (CNN) “MultiScale-Net” for AFD in Landsat-8 datasets at the pixel level. The proposed network had two main characteristics: (1) several convolution kernels with multiple sizes, and (2) dilated convolution layers (DCLs) with various dilation rates. Moreover, this paper suggested an innovative Active Fire Index (AFI) for AFD. AFI was added to the network inputs consisting of the SWIR2, SWIR1, and Blue bands to improve the performance of the MultiScale-Net. In an ablation analysis, three different scenarios were designed for multi-size kernels, dilation rates, and input variables individually, resulting in 27 distinct models. The quantitative results indicated that the model with AFI-SWIR2-SWIR1-Blue as the input variables, using multiple kernels of sizes 3 × 3, 5 × 5, and 7 × 7 simultaneously, and a dilation rate of 2, achieved the highest F1-score and IoU of 91.62% and 84.54%, respectively. Stacking AFI with the three Landsat-8 bands led to fewer false negative (FN) pixels. Furthermore, our qualitative assessment revealed that these models could detect single fire pixels detached from the large fire zones by taking advantage of multi-size kernels. Overall, the MultiScale-Net met expectations in detecting fires of varying sizes and shapes over challenging test samples.