Optimizing fire detection in remote sensing imagery for edge devices: A quantization-enhanced hybrid deep learning model

Wildfires are increasing in frequency and severity, presenting critical challenges for timely detection and response, particularly in remote or resource-limited environments. This study introduces the Inception-ResNet Transformer with Quantisation (IRTQ), a novel hybrid deep learning (DL) framework that integrates multi-scale feature extraction with global attention and advanced quantization. The proposed model is specifically optimized for edge deployment on platforms such as unmanned aerial vehicles (UAVs), offering a unique combination of high accuracy, low latency, and compact memory footprint. The IRTQ model achieves 98.9% accuracy across diverse datasets and shows strong generalisation through cross-dataset validation. Quantisation significantly reduces the parameter count to 0.09M and memory usage to 0.13 MB, enabling real-time inference in 3 ms. Interpretability is further enhanced through Grad-CAM visualizations, supporting transparent decision-making. While achieving state-of-the-art performance, the model encounters challenges in visually ambiguous fire-like regions. To address these, future work will explore multi-modal inputs and extend the model toward multi-class classification. IRTQ represents a technically grounded, interpretable, and deployable solution for AI-driven wildfire detection and disaster response. • The study introduces the IRTQ model, a hybrid deep learning approach that integrates the Inception-ResNet architecture with transformer technology, enabling rapid and precise bushfire prediction using real-time UAV-based remote sensing imagery. • Achieving an impressive accuracy of 98% with a low false-positive rate, the IRTQ model is highly efficient, featuring only 0.09 million parameters and employing advanced quantization techniques to minimize computational demands without compromising accuracy. • Trained on two extensive datasets covering diverse wildfire scenarios, the model has been rigorously validated through cross-validation, demonstrating its adaptability and reliability in various conditions. • By significantly improving the efficiency of fire detection and rescue operations, the IRTQ model offers a robust and dependable solution for addressing the growing challenges posed by bushfires, benefiting human lives, infrastructure, and the environment.