An Integrated MCDM Framework for UAV Platform Selection in Early Forest Fire Detection Missions

Abstract

Forest fires are among the most significant threats to ecosystems, biodiversity, and environmental sustainability; therefore, early fire detection is a critical component of effective forest fire management. Traditional fire detection methods, including ground patrols, fire observation towers, and satellite imagery, often fail to provide both adequate spatial coverage and the temporal resolution required for timely detection. In this context, Unmanned Aerial Vehicles (UAVs) have emerged as an effective solution for wildfire monitoring due to their operational flexibility, real-time data transmission capabilities, and ability to support various firefighting tasks, including search and rescue, fire surveillance, and containment operations. However, selecting a suitable UAV for early-stage fire detection is a challenging decision, as stakeholders are faced with multiple options based on technological and operational considerations, rather than a single one. This study presents a comprehensive Multi-Criteria Decision-Making (MCDM) model to identify the most suitable commercially available UAV platforms for early forest fire detection. The proposed method integrates objective and subjective evaluation approaches by combining the Criteria Importance Through Intercriteria Correlation (CRITIC) and Weighted Aggregated Sum Product Assessment (WASPAS) methods with the Best-Worst Method (BWM) and Multi-Objective Optimization by Ratio Analysis plus the Full Multiplicative Form (MULTIMOORA). UAV alternatives were evaluated using key criteria, including flight endurance, payload capacity, operational range, sensor capability, and cost. According to the CRITIC–WASPAS approach, alternative A2 achieved the highest ranking, followed by A6 and A5. In contrast, the BWM–MULTIMOORA approach identified A6 and A5 as the two best-performing alternatives, while A4 was ranked last by both integrated approaches. Overall, the findings demonstrate that the proposed hybrid MCDM framework provides a reliable decision-support tool for UAV selection and can support more effective wildfire monitoring, early fire detection, and disaster management strategies.