Published Online:August 2024
Product Name:The IUP Journal of Telecommunications
Product Type:Article
Product Code:IJTC030824
Author Name:Mohan Tarun Polisetty, Satyanarayana Raju Vuddaraju, Jayavardhan Reddy Ponnapati, Sri Hari Sai Saran Polisetty and Mythili R
Availability:YES
Subject/Domain:Engineering
Download Format:PDF
Pages:13
The paper focuses on a novel hybrid strategy of using artificial intelligence (AI), real-time imaging, and predictive analysis for forest fire detection (Liu et al., 2020). Such approach drastically cuts operational costs, time, and the necessary manpower, using real-time imaging of AI and analytics (studies that use sensors and drones) and predictive algorithm via neurofuzzy Logic. The AI deep learning technology is well suited for areas with dense vegetation, giving valuable maps. They gather the information necessary for producing satellite images. In particular, the neuro-fuzzy Logic model collects and processes the data obtained from real-time satellite, drones and other observations. This makes a direct transition from staffcontrolled UAS to robots. The synergistic combination of these techniques increases realtime detection and prediction accuracy, which in turn provides a robust solution for effective disaster management and early intervention in forest ecosystems (Chen and Lin, 2024; and Jiang and Zhang, 2024).
Forest fires are a result of critical ecological and economic problems that destroy biodiversity, air quality and human life. The high-frequency and high-intensity of these fires, and the climate change, are major problems that must be addressed immediately as they show the need for advanced fire detection and prediction systems.