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…
How strong is the evidence?
Evidence Hub reads this as a systematic review, done in animal and computer models (in silico), not in people. Its evidence level is 5 of 5 (Very low · case / narrative / animal / in vitro / in silico). Case reports, narrative reviews, and animal, cell or computer-model studies give the weakest evidence for human health.
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.