Research on Strategy of Wildfire Detection Towards Different Weather Information-Based on ARIMA Model
DOI: 10.23977/csoc.2022.020102 | Downloads: 7 | Views: 897
Chao Jing 1
1 School of Aeronautics, Northwestern Polytechnical University, Shaanxi, Xi'an, 710072, China
Corresponding AuthorChao Jing
Wildfires have caused huge economic and ecological damage to Australia in the past few years. This paper studies a man-machine cooperation based response system to help the Victorian Country Fire Authority better monitor and control the wildfire disaster. In order to solve the problem, this paper establishes mathematical model called ARIMA. The Model is a probability prediction model based on climate factors. The occurrence of wildfire is closely related to the climatic conditions. In this paper, the time series auto-regressive model (ARIMA) is established to predict the temperature, precipitation and other meteorological factors in the next ten years. On this basis, the contribution of meteorological factors to the occurrence of wildfire was analyzed, and the future wildfire occurrence was predicted by using Logistic linear regression method.Finally, we discuss the advantages and disadvantages of the model.
KEYWORDSman-machine, ARIMA, climate factors, Logistic linear regression method, wildfire detection
CITE THIS PAPER
Chao Jing, Research on Strategy of Wildfire Detection Towards Different Weather Information-Based on ARIMA Model. Cloud and Service-Oriented Computing (2022) Vol. 2: 14-20. DOI: http://dx.doi.org/10.23977/csoc.2022.020102.
 Geraldes R, Goncalves A, Lai T, et al. UAV-based situational awareness system using deep learning[J]. IEEE Access, 2019, 7: 122583-122594.
 Shen Fuqiang. Automatic UAV route planning method based on 3D surface model[D]. Southwest Jiaotong University, 2015.
 Huang Kaili. Research on improved algorithm for radio wave propagation prediction in mountainous environment[D]. Nanjing University of Posts and Telecommunications, 2017.
 Cheng, Ruiting. Research on radio wave propagation model ITU-R P.526 and multi-edge peak bypassing[J]. China Radio, 2006(10):51-53.
 Wen B, Xie Xianqiang, Sun Meng, Du Zhiguo, Li Suo, Huang Ping, Zhu Yuhao, Xie Bolian. Forest fire prediction based on weighted logistic regression model[J]. Forestry and Environmental Science, 2019, 35(04):79-83.