Forest Fire Prevention, Detection, and Fighting Based on Fuzzy Logic and Wireless Sensor Networks

Abstract

Huge losses and serious threats to ecosystems are common consequences of forest fires. This work describes a forest fire controller based on fuzzy logic and decision-making methods aiming at enhancing forest fire prevention, detection, and fighting systems. In the proposal, the environmental monitoring of several dynamic risk factors is performed with wireless sensor networks and analysed with the proposed fuzzy-based controller. With respect to this, meteorological variables, polluting gases and the oxygen level are measured in real time to estimate the existence of forest fire risks in the short-term and to detect the recent occurrence of fire outbreaks over different forest areas. Besides, the Analytic Hierarchy Process method is used to determine the level of fire spread, and, when necessary, environmental alerts are sent by a Web service and received by a mobile application. For this purpose, integrity, confidentiality, and authenticity of environmental information and alerts are protected with implementations of Lamport’s authentication scheme, Diffie-Lamport signature, and AES-CBC block cipher.

GIS-Based Forest Fire Susceptibility Zonation with IoT Sensor Network Support, Case Study—Nature Park Golija, Serbia

“…Alternatively, each sensor node can be equipped with a Global Positioning System (GPS) module, which would increase the power consumption and cost of the sensor node. Each sensor periodically collects the measured data and employs the fuzzy logic Mamdani inference system [ 57 , 58 ] that has been adopted to analyze the complex environmental changes. Seven input variables measured by sensors are fuzzified using the four membership functions shown in Figure 2 and Figure 3 .…”

“…The adopted fuzzy sets for the forest fire risk are designed according to the rule of 30, which is considered as a relevant preventive model of forest fire risk [ 57 ]. This rule considers measurements of temperature and wind speed above 30 °C and 30 km/h, respectively, with the humidity values below 30%, as the environmental conditions that favor the forest fires’ occurrence.…”

“…This rule considers measurements of temperature and wind speed above 30 °C and 30 km/h, respectively, with the humidity values below 30%, as the environmental conditions that favor the forest fires’ occurrence. The adopted fuzzy sets for the fire outbreak occurrence are proposed and designed, [ 57 ], based on the occurrence of the unusual increases in carbon monoxide and carbon dioxide levels above their typical environmental concentrations at forest areas, at the same time as the occurrence of the unexpected oxygen level decrease below 21%.…”

“…The literature review of IoT-based sensor networks and WSN-based systems intended for the real-time forest fire risk prediction and fire outbreak detection showed the broad set of possible meteorological and other parameters used in these systems. The following is observed: The most commonly used set of parameters consists of: temperature (T), relative humidity (H), wind speed (W speed ), and rainfall (R), [ 17 , 18 , 57 , 63 , 64 , 65 , 66 , 67 , 68 , 69 , 70 , 71 , 72 ]. For this set of parameters, the fuzzy AHP method is used [ 57 , 63 , 64 , 69 ] for the forest fire risk prediction, sometimes with additional parameters for human behavior and environment [ 64 ], while these same parameters were also combined with the concentrations of chemical gases (oxygen, carbon monoxide, and carbon dioxide) in order to detect forest fire outbreaks [ 57 ].…”

A Statistical Image Feature‐Based Deep Belief Network for Fire Detection

“…e most obvious property of deep learning models is the multiple layer structures. With multiple hidden layers stacked hierarchically, the deep learning model can realize very complicated transformation and abstraction of raw images [25][26][27][28]. Deep belief network (DBN) is a kind of the generative deep learning model with powerful feature learning ability [29].…”