基于PSO-GA-BP神经网络的林火预测设计与研究

doi:10.16182/j.issn1004731x.joss.201805015

系统仿真学报 ›› 2018, Vol. 30 ›› Issue (5): 1739-1748.doi: 10.16182/j.issn1004731x.joss.201805015

基于PSO-GA-BP神经网络的林火预测设计与研究

白书华, 况明星

南昌理工学院,南昌 330044

收稿日期:2017-03-22 修回日期:2017-07-25 出版日期:2018-05-08 发布日期:2019-01-03
作者简介:白书华(1982-),男,河南,硕士,研究方向为电子信息科学与技术、信号与信息处理;况明星(1944-),男,江西,本科,教授,研究方向为信号与信息处理、电子信息科学与技术。
基金资助:
国家自然科学基金(61461033),江西省教育厅科学技术项目(GJJ171041)

Design and Study of Forest Fire Forecasting Based on PSO and GA-BP Neural Network

Bai Shuhua, Kuang Mingxing

Nanchang Institute of Technology, Nanchang 330044, China

Received:2017-03-22 Revised:2017-07-25 Online:2018-05-08 Published:2019-01-03

摘要/Abstract

摘要： 搜集了江西省4个站点(南昌、景德镇、吉安、赣州)2013-2015年的气象数据,以及相对应的森林火险等级数据,并建立神经网络林火预测模型。采用遗传算法、粒子群算法和粒子群遗传混合算法优化BP神经网络,分别构建了相对应的网络模型。通过分析BP网络、GA-BP网络、PSO-BP网络和PSO-GA-BP网络的预测结果,并与实验数据进行对比,结果表明PSO-GA-BP网络预测模型的预测正确率最高,PSO-GA的优化效果最佳。

关键词: 森林火险等级, 气象因子, PSO-GA-BP神经网络, 林火预测

Abstract: This paper collects the 2013-2015 meteorological data of four stations (Nanchang, Jingdezhen, Gi’an, Ganzhou) in Jiangxi province, and the corresponding forest fire danger grading, to establish a neural network fire prediction model. Corresponding network model is built respectively by adopting the genetic algorithm, particle swarm optimization (PSO) algorithm and particle swarm genetic hybrid algorithm to optimize the BP neural network. By comparing the prediction results of BP network, GA-BP network, PSO-BP network and PSO-GA-BP network with the experiments data, it shows that the PSO-GA-BP network prediction model is of higher accuracy, the PSO and GA enjoy the best optimization effect.

Key words: forest fire danger grading, meteorological factors, PSO-GA-BP neural network, Forest fire forecast

中图分类号:

O657.7

白书华, 况明星. 基于PSO-GA-BP神经网络的林火预测设计与研究[J]. 系统仿真学报, 2018, 30(5): 1739-1748.

Bai Shuhua, Kuang Mingxing. Design and Study of Forest Fire Forecasting Based on PSO and GA-BP Neural Network[J]. Journal of System Simulation, 2018, 30(5): 1739-1748.

参考文献

[1] 肖霞. 基于类间方差的MODIS森林火灾监测方法研究[D]. 合肥: 中国科学技术大学, 2010: 201-206.
XIAO X.Research on Forest Fire Monitoring Method Based on Interclass Variance MODIS[D]. Hefei: China University of Science and Technology, 2010: 201-206.
[2] 王伟, 宋卫国, 刘士兴, 等. Kmeans聚类与多光谱阈值相结合的MODIS云检测算法[J]. 光谱学与光谱分析, 2011, 31(4): 1061-1064.
WANG W, SONG W G, LIU S X, et al.A Cloud Detection Algorithm for MODIS Images Combining Kmeans Clustering and Multi-Spectral Threshold Method[J]. Spectrum and Spectrum Analysis, 2011, 31(4): 1061-1064.
[3] 黄儒乐. 基于视频图像的林火烟雾识别方法的研究[D]. 北京: 北京林业大学, 2012: 111-119.
HUANG R L.Research on Forest Fire Smoke Recognition Based on Video Image[D]. Beijing: Beijing Forestry University, 2012: 111-119.
[4] 田少卿. 林火稳像与识别定位算法研究[D]. 哈尔滨: 东北林业大学, 2014: 68-73.
TIAN S Q.Research on Forest Fire Stabilization and recognition Positioning Algorithm[D]. Haerbin: Northeast Forestry University, 2014: 68-73.
[5] 岳姣姣. 基于多特征融合的林火烟雾检测算法研究[D]. 秦皇岛: 燕山大学, 2016: 113-119.
YUE J J.The Research on Forest Fire Smoke Detection Algorithm Based on Feature Fusion[D]. Qinhuangdao: Yanshan University, 2016: 113-119.
[6] Vipin V.Image processing based forest fire detection[J]. International Journal of Emerging Technology and Advanced Engineering (S2250-2459), 2012, 2(2): 87-95.
[7] ANGAYARKKANI K, RADHAKRISHNAN N.Efficient forest fire detection system: A spatial data mining and image processing based approach[J]. International Journal of Computer Science and Network Security (S1738-7906), 2009, 9(3): 100-107.
[8] KANDIL M, SALAMA M.A new hybrid algorithm for fire vision recognition[C]∥Eurocon: Eurocon 09 IEEE , 2009 :1460-1466
[9] 王丹丹, 黄家荣, 刘伟, 等. 基于人工神经网络的森林火险预测[J]. 西北林学院学报, 2010, 25(3): 143-146.
WANG D D, HUANG J R, LIU W, et al.Benefit Evaluation of Conversion of Cropland to Forest Project in the Loess Plateau: A Review[J]. Journal of Northwest Forestry University, 2010, 25(3): 143-146.
[10] 苏漳文, 刘爱琴, 梁慧玲, 等. 基于气象因子的福建省森林火险预测模型[J]. 森林与环境学报, 2015, 35(4): 370-376.
SU Z W, LIU A Q, LIANG H L, et al.Model to Predict Forest Fire Occurrence in Fujian Province Based on Meteorological Factors[J]. Journal of Forests and the Environment, 2015, 35(4): 370-376.
[11] 钱兆楼. 一种基于改进粒子群算法优化BP神经网络的预测方法[J]. 电子测试, 2015(20): 39-40.
QIAN Z L.A Prediction Method for Optimizing BP Neural Network Based on Improved Particle Group Algorithm[J]. Electronic Test, 2015(20): 39-40.
[12] 王攀, 陈建, 曹中华, 等. 基于GA-BP神经网络的农业机械化综合水平预测模型[J]. 农业化研究, 2016(3): 75-79.
WANG P, CHEN J, CAO Z H, et al.Model for Forcasting the Agricultural Mechanization Integrated Level Based on GA-BP Neural Network[J]. Agricultural Research, 2016(3): 75-79.
[13] 王雅楠, 孟晓景. 基于动量BP算法的神经网络房价预测研究[J]. 软件导刊, 2015, 14(2): 59-61.
WANG Y N, MENG X J.Research on the Forecasting of House Prices By Neural Network Based on Momentum BP Algorithm[J]. Software Guide, 2015, 14(2): 59-61.
[14] 高玉明. 基于GA-PSO算法优化BP网络的短期电力负荷预测[D]. 贵阳: 贵州师范大学, 2014.
GAO Y M.Forecasting Based on BP Neural Network optimized by GA-PSO Algorithm[D]. Guiyang: Guizhou Normal University, 2014.
[15] Brown T J, Hall B L, Westerling A L.The Impact of Twenty-First Century Climate Change on Wildland Fire Danger in the Western United States: An Applications Perspective[J]. Climatic Change (S0165-0009), 2014(1): 68-72.
[16] Pausas J G.Changes in Fire and Climate in the Eastern Iberian Peninsula (Mediterranean Basin)[J]. Climatic Change (S0165-0009), 2004(3): 112-116.
[17] Jeremy S Fried, Margaret S Torn, Evan Mills.The Impact of Climate Change on Wildfire Severity: A Regional Forecast for Northern California[J]. Climatic Change (S0165-0009), 2014(1): 27-29.
[18] Williams A A J, Karoly D J, Tapper N. The Sensitivity of Australian Fire Danger to Climate Change[J]. Climatic Change (S0165-0009), 2010(1): 159-163.
[19] 唐阳山, 葛丽娜, 黄子龙, 等. 基于BP神经网络的交通事故预测方法研究[J]. 辽宁工业大学学报(自然科学版), 2016, 36(1): 27-30.
Tang Y S, Ge L N, Huang Z L, et al.Study on Traffic Accident Study on Traffic Accident Prediction Method Based on BP Neural Network[J]. Journal of Liaoning University of Technology(Natural Sciences), 2016, 36(1): 27-30.
[20] 王珍. 基于因子分析-BP神经网络模型在空气质量综合评价中的应用[D]. 昆明: 云南大学, 2015.
WANG Z.Application of Factor Based Analysis-BP Neural Network Model in Comprehensive Evaluation of Air Quality[D]. Kunming: Yunnan University, 2015.
[21] 胡瑞卿. 基于人工神经网络的煤矿安全评价研究[D]. 淮南: 安徽理工大学, 2015.
HU R Q.The Safety Evaluation Study of The Coal Mine Based on the Artificial Neural Network Measure[D]. Huinan: Anhui Polytechnic University, 2015.
[22] 武艺. 人工神经网络在土壤质量监测中的应用[D]. 舟山: 浙江海洋学院, 2015.
WU Y.Arts. Artificial Neural Networks Apply to Soil Quality Observation[D]. Zhoushan: Zhejiang Marine College, 2015.
[23] 任谢楠. 基于遗传算法的BP神经网络的优化研究及MATLAB仿真[D]. 天津: 天津师范大学, 2014.
Ren X N.Optimization Study and MATLAB Simulation of BP Neural Network Based on Genetic Algorithm[D]. Tianjin: Tianjin Normal University, 2014.

基于PSO-GA-BP神经网络的林火预测设计与研究

Design and Study of Forest Fire Forecasting Based on PSO and GA-BP Neural Network

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价