A wildfire occurrence risk model based on a back-propagation neural network-optimized genetic algorithm

Abstract

To reduce the impact of wildfires on the operation of power systems, a back-propagation neural network (BPNN) model is used to evaluate the wildfire risk distribution after feature selection. Data from 14 types of wildfire-related features, including anthropogenic, geographical, and meteorological factors, were collected from public data websites and local departments. The weight ranking was calculated using filtering and wrapper methods to form five feature subsets. These are used as the input sets of the BPNN model training, and network parameters are optimized by genetic algorithm (GA). Finally, the optimal feature subset is chosen to establish the optimal BPNN model. With the optimal model, the prediction results are graded to draw a wildfire risk distribution map. Situated in medium-, high-, and very-high-risk zones are 90.26% of new fire incidents, indicating the applicability of the proposed BPNN model.

Optimization of the lightning warning model for distribution network lines based on multiple meteorological factor thresholds

“…According to the theory of information entropy, the smaller the information entropy of the index, the greater the degree of change in the index value, the greater the amount of information provided, and the more obvious the role played in the evaluation system. Therefore, the information entropy under the lightning warning index can be used to objectively determine the weight (Zhang et al, 2023).…”