To address the issues of low accuracy and slow speed in flame and smoke detection in natural environments, this paper proposes an im-proved lightweight YOLOv8n-based detection algorithm for flames and smoke. The algorithm replaces the backbone network of YOLOv8n with the lightweight PP-LCNet network, introduces the CARAFE upsampling operator to enhance detail capture and reduce information loss, and adds the EMA attention mechanism module to improve the model’s ability to recognize and extract detection targets. Experimental results show that the improved YOLOv8n reduces the number of parameters by 0.89MB and the computational cost by 1.8G compared to the base-line YOLOv8n. Furthermore, compared with Faster R-CNN, SSD, YOLOv4, YOLOv5s, YOLOv7, YOLOv8n, and models from the liter-ature, it achieves precision, recall, mAP50, and F1 scores of 96.5%, 94.7%, 95.3%, and 95.6%, respectively, demonstrating the best perfor-mance. The improved algorithm not only enhances detection accuracy but also achieves lightweight characteristics, making it highly valuable for practical applications.