Towards Acoustic Bioindicator Integration in AI-Based Wildfire Monitoring: A Systematic Review

Abstract

Wildfires are becoming more frequent, severe, and long-lasting, driving rapid growth in sensor-based and artificial intelligence (AI)-enabled systems for early detection and risk assessment. This article presents a systematic literature review, based on 169 studies screened from 7511 records, of wildfire monitoring approaches using satellite and aerial remote sensing, fixed cameras, wireless sensor networks, and Internet of Things (IoT) platforms combined with machine learning (ML) and deep learning (DL) models for ignition detection, fire-weather indices, spread prediction, and burned-area mapping. The review organizes existing work by sensing modality, spatial and temporal scale, learning task, model type, and deployment architecture, and identifies the environmental drivers most commonly used across systems, including temperature, humidity, vegetation state, drought indices, and smoke or air quality. Based on this analysis, the review summarizes key technical challenges, including data sparsity in remote regions, high false-alarm rates, limited edge resources, and difficulty fusing heterogeneous data streams in real time. As an exploratory future direction, the review discusses bioindicator signals from wildlife and managed species, using honeybee colonies as a case example. Current bee bioacoustic studies support the detection of colony states and environmental stress proxies, but they do not yet validate wildfire or smoke detection. Therefore, this review proposes bee bioacoustics only as a potential complementary contextual signal for future hybrid wildfire monitoring systems.