A Hybrid Machine Learning Model for Forest Wildfire Detection Using Sounds

Forest wildfires pose a significant threat to ecosystems, human settlements, and the global environment. Early detection is crucial for effective mitigation and response. Traditional methods, such as satellite imagery and smoke detectors, have limitations in real-time response and coverage. This paper introduces a novel approach to forest wildfire detection by harnessing the unique sound signatures associated with wildfires. Our proposed model combines the strengths of deep learning techniques with heuristic optimization algorithms. The deep learning component focuses on recognizing the intricate patterns in the sound data, while the heuristic optimization ensures the model's adaptability and efficiency in diverse forest environments. After preprocessing and feature extraction, a deep neural network was trained to recognize wildfire-specific sound patterns. The heuristic optimization, based on a Particle Sworm Optimization (PSO) algorithm, was then integrated to fine-tune the model parameters, ensuring optimal performance. Preliminary results indicate that our hybrid model outperforms traditional methods and existing machine learning models in terms of accuracy, sensitivity, and specificity. The model demonstrates robustness against ambient forest noise, ensuring fewer false alarms. This research not only contributes to the field of environmental monitoring through sound recognition but also showcases the potential of hybrid machine learning models to address complex real-world challenges. Future work will focus on deploying this model in real-time monitoring systems and further refining its capabilities through continuous learning.

---

1. This research paper has received funding from Horizon Europe Framework Programme (HORIZON), call Teaming for Excellence (HORIZON-WIDERA-2022-ACCESS-01-two-stage) - Creation of the centre of excellence in smart forestry “Forest 4.0” No. 101059985. This research has been co-funded by the European Union under the project "FOREST 4.0 - Ekscelencijos centras tvariai miško bioekonomikai vystyti" (Nr. 10-042-P-0002)

---

2. Main Track: Regular Papers

---

3. Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).