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

Abstract

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.

Object Tracking Based on Satellite Videos: A Literature Review

“…For example, Ref. [127] revised the general CNN models to enhance the fire detection performance in 2022. The proposed network consists of several convolution kernels with multiple sizes and dilated convolution layers with various dilation rates.…”

“…In addition, Figure 4 shows a comparison of algorithm structure between two categories. [110] 2021 GAN with deep multi-scale frame prediction method [111] 2022 GAN to predict both the track and intensity of typhoons RNN-based [112] 2017 A convolutional sequence-to-sequence autoencoder [113] 2018 MNNs for typhoon tracking [114] 2018 A CLSTM based model [115] 2021 A CLSTM layer with FCLs [116] 2022 A CLSTM with 3D CNN based on multimodal data [117] 2022 An echo state network-based tracking Fire Traditional [118] 2017 Identify possible fire hotspots from two bands of AHI [119] 2018 A threshold algorithm with visual interpretation [120] 2019 A multi-temporal method of temperature estimation [121] 2020 Temperature dynamics by data assimilation [122] 2022 Wildfire tracking via visible and infrared image series DL-based [123] 2019 3D CNN to capture spatial and spectral patterns [124] 2019 Inception-v3 model with transfer learning [125] 2021 Near-real-time fire smoking prediction [126] 2022 Combine the residual convolution and separable convolution to detect fire [127] 2022 Multiple Kernel learning for various size fire detections…”

A Comparative Study of Machine Learning Classifiers for Crop Type Mapping Using Vegetation Indices

“…For example, Liu et al(2018) used eight MODIS coarse resolution images to compute EVI in the growing season of Henan province of China and achieved the OA of 84% by the global threshold model. The ML and deep learning algorithm can develop a model that simulates the relation between output and different variables as inputs (Aghdami-Nia et al, 2022;Rostami et al, 2022b). Nevertheless, ML algorithms have parameters that should be optimized with some methods (Ansari and Akhoondzadeh, 2020;Ranjbar et al, 2021).…”

Effect of Transferring Pre-Trained Weights on a Siamese Change Detection Network

“…This method for CD is usually considered a pre-processing step for more complex frameworks where change classes are also detected. Deep learning (Aghdami-Nia et al, 2022;Ansari et al, 2021;Rostami et al, 2022b) and machine learning (Ranjbar et al, 2021;Rostami et al, 2022a;Zarei et al, 2021) methods have dominated many RS fields and CD is no exception. Siamese networks have attracted special attention for CD purposes among researchers in recent years.…”