Scholarlink

Wildfire detection and management represent critical challenges. Due to the climate change, innovative solutions that enhance responsiveness and effectiveness are required to minimize environmental impact. This paper introduces the Aerial Fire Tracking and Optimization Network (AFTON), an integration of sustainable Unmanned Aerial Vehicle (UAV) systems designed through System of Systems (SoS) analysis. An Agent-Based Model (ABM) is used to simulate the dynamics of UAVs patrolling over at-risk areas, tasked with the early detection of wildfires. A consensus algorithm is employed to provide the UAVs with adaptive behaviors and communication strategies, enabling a coordinated response upon the detection of a fire. The machine learning component of AFTON focuses on predicting battery weight to optimize flight time and coverage area, thereby enhancing the sustainability of UAV operations. This holistic approach not only improves the capabilities of UAV networks in environmental monitoring but also the potential for designing resilient, autonomous systems for disaster management. The aim of the study is to integrate a holistic view to combine SoS and artificial intelligence. By emphasizing sustainable design and innovative technological integration, AFTON contributes to proactive management of the growing threat of wildfires, thus supporting the development of resilient futures in disaster response and environmental preservation.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Designing Sustainable UAV Systems: Aerial Fire Tracking and Optimization Network (AFTON) with Machine Learning and Consensus Algorithms

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Jorge L. Lovaco,
  • Raghu Chaitanya Munjulury,
  • Petter Krus

摘要

Wildfire detection and management represent critical challenges. Due to the climate change, innovative solutions that enhance responsiveness and effectiveness are required to minimize environmental impact. This paper introduces the Aerial Fire Tracking and Optimization Network (AFTON), an integration of sustainable Unmanned Aerial Vehicle (UAV) systems designed through System of Systems (SoS) analysis. An Agent-Based Model (ABM) is used to simulate the dynamics of UAVs patrolling over at-risk areas, tasked with the early detection of wildfires. A consensus algorithm is employed to provide the UAVs with adaptive behaviors and communication strategies, enabling a coordinated response upon the detection of a fire. The machine learning component of AFTON focuses on predicting battery weight to optimize flight time and coverage area, thereby enhancing the sustainability of UAV operations. This holistic approach not only improves the capabilities of UAV networks in environmental monitoring but also the potential for designing resilient, autonomous systems for disaster management. The aim of the study is to integrate a holistic view to combine SoS and artificial intelligence. By emphasizing sustainable design and innovative technological integration, AFTON contributes to proactive management of the growing threat of wildfires, thus supporting the development of resilient futures in disaster response and environmental preservation.