From smoke to fire: A forest fire early warning and risk assessment model fusing multimodal data

Experienced forest firefighters can integrate knowledge of smoke patterns and risk factors to assess fire risk and anticipate potential fire spread and outbreaks in complex, variable environments. This study simulates the previously mentioned monitoring process and presents the Multimodal Smoke Risk Estimation Network (MM-SRENet), an innovative multimodal fusion model. This model uniquely integrates the Multi-Scale Dilation Block and Repulsion Loss into a lightweight and efficient target detection system to accurately identify smoke's presence. Furthermore, an advanced backbone based on star operation extracts the scene characteristics associated with smoke and merges them with various fire risk factors. The objective is to simulate fire risk assessments in smoke scenarios and to reduce the misallocation of fire resources resulting from false alarms and missed alerts. The proposed model was trained and validated on a multimodal dataset comprising multiple backgrounds. It successfully identified smoke features and fire potential risks in different scenarios, achieving a prediction accuracy of 93.06 %. Fusing smoke images with fire risk data resulted in an 18.75 % improvement in recognition accuracy compared to the single modal model. This work bridges the gap between multimodal data fusion and forest fire risk monitoring, providing a new direction for future intelligent forest fire prevention and control practices.