De Rango Alessio, Furnari Luca, Cortale Fabio, Senatore Alfonso, Mendicino Giuseppe
Department of Environmental Engineering, University of Calabria, Rende, 87036 Cosenza, Italy.
Sensors (Basel). 2025 Mar 23;25(7):2012. doi: 10.3390/s25072012.
Climate change exacerbates wildfire risks in regions like the Mediterranean, where rising temperatures and prolonged droughts create ideal fire conditions. Adapting to this scenario requires implementing advanced risk management strategies that leverage cutting-edge technologies. Wildfire early warning systems are crucial tools for detecting fires at an early stage, helping prevent potential future damage. This paper proposes a smart CO sensor network-based early warning system, relying on a platform that enables the connection, management, and processing of data from the devices through the cloud. The wildfire early warning system was tested in a real controlled experiment, in which 44 sensors were deployed in strategically selected locations at varying distances from the fire. To enhance early detection, three Artificial Intelligence (AI) models were developed using AutoEncoders (AEs) and Long-Short-Term Memory (LSTM), and these were compared to a simple threshold-based (NO-AI) model. All AI models, especially the LSTM-based model, were able to extract more valuable information from the CO records, activating up to 56% more sensors than the NO-AI model in less time and tracking potential fire front propagation based on wind patterns. Therefore, the system not only improves early fire detection models but also effectively supports firefighting operations.
气候变化加剧了地中海等地区的野火风险，在这些地区，气温上升和长期干旱创造了理想的火灾条件。适应这种情况需要实施利用前沿技术的先进风险管理策略。野火早期预警系统是在早期阶段探测火灾的关键工具，有助于防止未来可能的损害。本文提出了一种基于智能一氧化碳传感器网络的早期预警系统，该系统依赖于一个平台，该平台能够通过云连接、管理和处理来自设备的数据。该野火早期预警系统在一个实际控制实验中进行了测试，在实验中，44个传感器被部署在距离火灾不同距离的战略选定位置。为了加强早期探测，使用自动编码器（AE）和长短期记忆（LSTM）开发了三种人工智能（AI）模型，并将这些模型与基于简单阈值的（无AI）模型进行了比较。所有人工智能模型，尤其是基于LSTM的模型，都能够从一氧化碳记录中提取更有价值的信息，在更短的时间内比无AI模型多激活56%的传感器，并根据风向跟踪潜在的火线蔓延。因此，该系统不仅改进了早期火灾探测模型，还有效地支持了灭火行动。
