State-of-the-art electronic systems and decision-making architectures for wildfire detection and suppression: a comprehensive review

Wildfires represent an escalating global hazard intensified by climate change and land-use change, rendering traditional detection approaches such as satellite monitoring and manual ground patrols insufficient because of high latency and vulnerability to adverse weather. This review critically synthesizes the cited peer-reviewed and technical literature to evaluate the state of the art in electronic sensing systems, embedded artificial intelligence (AI), and autonomous platforms for wildfire management. The study organizes technologies into an engineering taxonomy covering wireless sensor networks, thermal infrared imaging systems, computer vision models, geospatial scaling methodologies, autonomous unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs), and multispectral/hyperspectral fuel condition sensing used for risk assessment before a fire occurs. Multispectral and hyperspectral sensing is therefore treated as a risk assessment and mission prioritization layer rather than as a primary modality for active fire detection. Beyond component-level performance metrics, the review evaluates the physical failure mechanisms and methodological limitations, including thermal crossover, nonfire hot surface confusion, smoke-induced optical degradation, radiative heat exposure, and the limited realism of laboratory or controlled burn validation protocols. It further distinguishes component connectivity from decision-level integration by emphasizing multirate temporal fusion, confidence arbitration, closed-loop suppression feedback, communication-denied edge autonomy, near-fire thermal constraints, and mission-level decision governance. The reviewed evidence suggests that thermal infrared imaging generally provides stronger smoke penetration capability than visible spectrum sensors under the reviewed conditions, whereas edge-optimized deep learning architectures can achieve the real-time detection performance essential for a rapid response. However, individual component maturity does not by itself imply operational readiness; reliable deployment requires standardized benchmarks, robust sensor fusion, degradation-aware autonomy, and validated end-to-end intervention pipelines under extreme environmental conditions. Beyond fully autonomous execution, the review frames wildfire robotics as supervised human-robot teaming in which operators retain mission intent, approval, override, and safety authority while autonomous platforms manage perception, local planning, and exception reporting. Compared with recent integrative surveys that already connect remote sensing, AI, UAV platforms, and wildfire management workflows, the distinctive contribution of this review is a deployment-oriented cross-layer analysis of how these components interact, fail, and must be governed as part of a safety-critical detection and suppression architecture.