Academic Journal of Environment & Earth Science, 2021, 3(2); doi: 10.25236/AJEE.2021.030203.
Hu Yu1, Jinshi Liu2, Yan Li2, Xin Li1
1College of Transportation Engineering, Dalian Maritime University, Dalian, Liaoning, 116033, China
2School of Information Science and Technology, Dalian Maritime University, Dalian, Liaoning, 116033, China
Wildfires are one of the most devastating natural disasters in Australia. In this paper, we design a model to predict the likely variability of extreme fires over the next decade. Aiming at the forecasting problem, we downloaded the extreme fire event data from NASA for the last 18 years in Victoria, and established a combined prediction model, combining the unbiased gray GM(1,1) model, the BP neural network prediction model optimized by genetic algorithm, and finally the resulting prediction data were approximated by Gaussian function on the data point set using MATLAB toolbox to obtain the temporal and spatial prediction results, and the number of drone combinations under different terrains is simulated by simulation.
unbiased gray GM(1,1) model, Genetic algorithm optimization, BP neural network prediction model
Hu Yu, Jinshi Liu, Yan Li, Xin Li. Study on the Prediction Model of Wildfire in Victoria. Academic Journal of Environment & Earth Science (2021) Vol. 3 Issue 2: 14-18. https://doi.org/10.25236/AJEE.2021.030203.
[1] https://earthdata.nasa.gov/earth-observation-data/near-real-time/firms/active-fire-data
[2] YUAN Peng-wei, SONG Shou-xin, DONG Xiao-qing. Study on fire accident prediction based on optimized grey neural network combination model [J]. China Safety and Production Technology, 2014, 10 (03): 119-124.