Wildfire Detection Powered by Involutional Neural Network and Multi-Task Learning with Dark Channel Prior Technique

In addition to being a crucial part of ecosystem health, wildfires also pose a grave threat to human lives and the environment. Early detection remains challenging, especially in remote areas. Satellite data and Unmanned Aerial Vehicles (UAVs) have become crucial tools for detecting and monitoring wildfires. Achieving proper identification is challenging due to the intricacy of wildfires, which are impacted by a variety of environmental factors. Recent advances in remote sensing data analysis, especially the use of machine learning (ML) models, demonstrate captivating potential. Using machine learning in remote sensing data analysis, this study examines state-of-theart strategies for wildfire identification. Based on the modified involution neural network (INN), Inv-Net is a new and innovative framework. By utilizing the concept of multi-task learning, Inv- Net achieves an accuracy of 98.1% in the classification task and exhibits a noteworthy Intersection over Union (IoU) score of 97.6% in the segmentation task, notably when used for wildfire image analysis. To improve wildfire detection accuracy and resilience, Inv-Net uses the synergies between classification and segmentation. Furthermore, the Dark Channel Prior (DCP) technique is used to address atmospheric disturbances such as haze and fog in static images. DCP reduces optical interference by estimating depth maps and transmission maps. The results highlight the importance of the DCP method, which achieves an excellent SSIM of 0.7831 and PSNR of 17.4321, indicating greater image dehazing methods. In comprehensive trials and comparisons, we demonstrate the robustness of our approach in identifying and mapping wildfires in challenging conditions.