Optimized Wireless Sensor Network Architecture for AI-Based Wildfire Detection in Remote Areas

Wildfires are complex natural disasters that significantly impact ecosystems and human communities. The early detection and prediction of forest fire risk are necessary for effective forest management and resource protection. This paper proposes an innovative early detection system based on a wirele...

Full description

Saved in:
Bibliographic Details
Main Authors: Safiah Almarri, Hur Al Safwan, Shahd Al Qisoom, Soufien Gdaim, Abdelkrim Zitouni
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Fire
Subjects:
Online Access:https://www.mdpi.com/2571-6255/8/7/245
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849303494198034432
author Safiah Almarri
Hur Al Safwan
Shahd Al Qisoom
Soufien Gdaim
Abdelkrim Zitouni
author_facet Safiah Almarri
Hur Al Safwan
Shahd Al Qisoom
Soufien Gdaim
Abdelkrim Zitouni
author_sort Safiah Almarri
collection DOAJ
description Wildfires are complex natural disasters that significantly impact ecosystems and human communities. The early detection and prediction of forest fire risk are necessary for effective forest management and resource protection. This paper proposes an innovative early detection system based on a wireless sensor network (WSN) composed of interconnected Arduino nodes arranged in a hybrid circular/star topology. This configuration reduces the number of required nodes by 53–55% compared to conventional Mesh 2D topologies while enhancing data collection efficiency. Each node integrates temperature/humidity sensors and uses ZigBee communication for the real-time monitoring of wildfire risk conditions. This optimized topology ensures 41–81% lower latency and 50–60% fewer hops than conventional Mesh 2D topologies. The system also integrates artificial intelligence (AI) algorithms (multiclass logistic regression) to process sensor data and predict fire risk levels with 99.97% accuracy, enabling proactive wildfire mitigation. Simulations for a 300 m radius area show the non-dense hybrid topology is the most energy-efficient, outperforming dense and Mesh 2D topologies. Additionally, the dense topology achieves the lowest packet loss rate (PLR), reducing losses by up to 80.4% compared to Mesh 2D. Adaptive routing, dynamic round-robin arbitration, vertical tier jumps, and GSM connectivity ensure reliable communication in remote areas, providing a cost-effective solution for wildfire mitigation and broader environmental monitoring.
format Article
id doaj-art-6a7b6cb0b6f94bad8434b40e99d5610d
institution Kabale University
issn 2571-6255
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Fire
spelling doaj-art-6a7b6cb0b6f94bad8434b40e99d5610d2025-08-20T03:58:26ZengMDPI AGFire2571-62552025-06-018724510.3390/fire8070245Optimized Wireless Sensor Network Architecture for AI-Based Wildfire Detection in Remote AreasSafiah Almarri0Hur Al Safwan1Shahd Al Qisoom2Soufien Gdaim3Abdelkrim Zitouni4Department of Physics, College of Science & Humanities Jubail, Imam Abdulrahman Bin Faisal University, Dammam 31961, Saudi ArabiaDepartment of Physics, College of Science & Humanities Jubail, Imam Abdulrahman Bin Faisal University, Dammam 31961, Saudi ArabiaDepartment of Physics, College of Science & Humanities Jubail, Imam Abdulrahman Bin Faisal University, Dammam 31961, Saudi ArabiaPRINCE Research Laboratory, ISITCom, Sousse University, Sousse 4011, TunisiaDepartment of Physics, College of Science & Humanities Jubail, Imam Abdulrahman Bin Faisal University, Dammam 31961, Saudi ArabiaWildfires are complex natural disasters that significantly impact ecosystems and human communities. The early detection and prediction of forest fire risk are necessary for effective forest management and resource protection. This paper proposes an innovative early detection system based on a wireless sensor network (WSN) composed of interconnected Arduino nodes arranged in a hybrid circular/star topology. This configuration reduces the number of required nodes by 53–55% compared to conventional Mesh 2D topologies while enhancing data collection efficiency. Each node integrates temperature/humidity sensors and uses ZigBee communication for the real-time monitoring of wildfire risk conditions. This optimized topology ensures 41–81% lower latency and 50–60% fewer hops than conventional Mesh 2D topologies. The system also integrates artificial intelligence (AI) algorithms (multiclass logistic regression) to process sensor data and predict fire risk levels with 99.97% accuracy, enabling proactive wildfire mitigation. Simulations for a 300 m radius area show the non-dense hybrid topology is the most energy-efficient, outperforming dense and Mesh 2D topologies. Additionally, the dense topology achieves the lowest packet loss rate (PLR), reducing losses by up to 80.4% compared to Mesh 2D. Adaptive routing, dynamic round-robin arbitration, vertical tier jumps, and GSM connectivity ensure reliable communication in remote areas, providing a cost-effective solution for wildfire mitigation and broader environmental monitoring.https://www.mdpi.com/2571-6255/8/7/245forest firehybrid WSNenergy efficiencyadaptive routingartificial intelligence
spellingShingle Safiah Almarri
Hur Al Safwan
Shahd Al Qisoom
Soufien Gdaim
Abdelkrim Zitouni
Optimized Wireless Sensor Network Architecture for AI-Based Wildfire Detection in Remote Areas
Fire
forest fire
hybrid WSN
energy efficiency
adaptive routing
artificial intelligence
title Optimized Wireless Sensor Network Architecture for AI-Based Wildfire Detection in Remote Areas
title_full Optimized Wireless Sensor Network Architecture for AI-Based Wildfire Detection in Remote Areas
title_fullStr Optimized Wireless Sensor Network Architecture for AI-Based Wildfire Detection in Remote Areas
title_full_unstemmed Optimized Wireless Sensor Network Architecture for AI-Based Wildfire Detection in Remote Areas
title_short Optimized Wireless Sensor Network Architecture for AI-Based Wildfire Detection in Remote Areas
title_sort optimized wireless sensor network architecture for ai based wildfire detection in remote areas
topic forest fire
hybrid WSN
energy efficiency
adaptive routing
artificial intelligence
url https://www.mdpi.com/2571-6255/8/7/245
work_keys_str_mv AT safiahalmarri optimizedwirelesssensornetworkarchitectureforaibasedwildfiredetectioninremoteareas
AT huralsafwan optimizedwirelesssensornetworkarchitectureforaibasedwildfiredetectioninremoteareas
AT shahdalqisoom optimizedwirelesssensornetworkarchitectureforaibasedwildfiredetectioninremoteareas
AT soufiengdaim optimizedwirelesssensornetworkarchitectureforaibasedwildfiredetectioninremoteareas
AT abdelkrimzitouni optimizedwirelesssensornetworkarchitectureforaibasedwildfiredetectioninremoteareas