Benchmarking Next-Generation YOLO Architectures for Multi-Platform Forest Fire Recognition

Early and reliable detection of forest fires is essential for reducing environmental damage and ensuring public safety. Deep learning-based object detection enables automated fire monitoring across heterogeneous sensing platforms, including satellite, Unmanned Aerial Vehicle (UAV), and ground-based imaging systems. However, differences in spatial resolution, viewing geometry, and computational constraints present challenges for developing unified detection models. This study presents a comparative benchmarking analysis of the lightweight YOLOv26-nano model for forest fire detection using the FASDD dataset, comprising satellite, UAV, and ground-based imagery. A unified experimental protocol with five-fold cross-validation is adopted to ensure robustness and cross-platform generalization. Performance is enhanced through data augmentation, contrast-limited adaptive histogram equalization, and stochastic gradient descent optimization. Experimental results demonstrate that YOLOv26-nano achieves reliable detection accuracy and demonstrates promising computational characteristics under simulated resource-constrained edge-computing conditions. The proposed benchmarking framework provides a standardized reference for multi-platform fire detection and highlights the suitability of nano-scale object detection models for scalable wildfire monitoring and early-warning systems.