Wildfire Risk Assessment of Transmission-Line Corridors Based on Naïve Bayes Network and Remote Sensing Data.

Weijie Chen,Zhun Xiang,Enze Zhou,You Zhou,Wentao Zhou,Junhan Lu

doi:10.3390/s21020634

Abstract

Considering the complexity of the physical model of wildfire occurrence, this paper develops a method to evaluate the wildfire risk of transmission-line corridors based on Naïve Bayes Network (NBN). First, the data of 14 wildfire-related factors including anthropogenic, physiographic, and meteorologic factors, were collected and analyzed. Then, the relief algorithm is used to rank the importance of factors according to their impacts on wildfire occurrence. After eliminating the least important factors in turn, an optimal wildfire risk assessment model for transmission-line corridors was constructed based on the NBN. Finally, this model was carried out and visualized in Guangxi province in southern China. Then a cost function was proposed to further verify the applicability of the wildfire risk distribution map. The fire events monitored by satellites during the first season in 2020 shows that 81.8% of fires fall in high- and very-high-risk regions.

Highlights

Due to the inhomogeneous distribution of energy resources and power loads in China, a large number of overhead transmission lines pass through forests and mountains to achieve an optimal allocation of power resources [1,2]
We aim to propose a wildfire risk assessment model based on Naïve Bayes Network (NBN) and remote sensing data
This study develops a spatial framework to assess and map wildfire risk of transmissionline corridors by integrating remote sensing data

Summary

Introduction

Due to the inhomogeneous distribution of energy resources and power loads in China, a large number of overhead transmission lines pass through forests and mountains to achieve an optimal allocation of power resources [1,2]. After identifying the flame strength of wildfire, the tripping risk would be evaluated by comparing the height of fire and transmission line [17,18]. This method needs numerous land-surface and environmental parameters to estimate the possible height of wildfire. Multiple wildfires usually occur simultaneously during the period of the Spring Festival, Qingming Festival, and autumn harvest in China. It is difficult for operation and maintenance personnel to rush the field and put out the fire in time. It is necessary to assess occurrence probability of wildfire to propose differentiated wildfire prevention strategies

Objectives

Results

Conclusion