基于随机森林回归分析的PM2.5浓度预测模型

杜续; 冯景瑜; 吕少卿; 石薇

doi:10.11959/j.issn.1000−0801.2017211

您当前的位置：

首页 >

文章列表页 >

基于随机森林回归分析的PM2.5浓度预测模型

研究与开发 | 更新时间：2024-06-05

- 基于随机森林回归分析的PM2.5浓度预测模型
- PM2.5 concentration prediction model based on random forest regression analysis
- 电信科学 2017年33卷第7期页码：66-75
- 作者机构：
  
  1. 西安邮电大学通信与信息工程学院，陕西西安 710121
  2. 西安邮电大学陕西省信息通信网络及安全重点实验室，陕西西安 710121
- 作者简介：
  
  [ "杜续（1989−），男，西安邮电大学硕士生，主要研究方向为大数据分析与数据挖掘。" ]
  [ "冯景瑜（1984−），男，博士，西安邮电大学副教授，主要研究方向为无线通信安全、认知无线网络等。" ]
  [ "吕少卿（1987−），男，博士，西安邮电大学讲师，主要研究方向为大数据分析与网络安全。" ]
  [ "石薇（1980−），女，西安邮电大学讲师，主要研究方向为大数据分析与通信网络规划。" ]
- 基金信息：
  
  国家自然科学基金资助项目;The National Natural Science Foundation of China(6130109);陕西省工业科技攻关项目(2016GY-113);陕西省教育厅专项科研计划基金资助项目;The Natural Science Foundation of Education Department of Shaanxi Province(15JK1671);西安邮电大学“西邮新星”团队支持计划基金资助项目;The New Star Team of Xi’an University of Posts ＆ Telecommunications(2015-01)
- DOI：10.11959/j.issn.1000−0801.2017211
  中图分类号： TP391
- 网络出版日期：2017-07，
  
  纸质出版日期：2017-07-20
- 稿件说明：
移动端阅览
杜续, 冯景瑜, 吕少卿, 等. 基于随机森林回归分析的PM2.5浓度预测模型[J]. 电信科学, 2017,33(7):66-75.

Xu DU, Jingyu FENG, Shaoqing LV, et al. PM2.5 concentration prediction model based on random forest regression analysis[J]. Telecommunications science, 2017, 33(7): 66-75.
杜续, 冯景瑜, 吕少卿, 等. 基于随机森林回归分析的PM2.5浓度预测模型[J]. 电信科学, 2017,33(7):66-75. DOI： 10.11959/j.issn.1000−0801.2017211.

Xu DU, Jingyu FENG, Shaoqing LV, et al. PM2.5 concentration prediction model based on random forest regression analysis[J]. Telecommunications science, 2017, 33(7): 66-75. DOI： 10.11959/j.issn.1000−0801.2017211.

摘要

针对神经网络算法在当前PM2.5浓度预测领域存在的易过拟合、网络结构复杂、学习效率低等问题，引入RFR（random forest regression，随机森林回归）算法，分析气象条件、大气污染物浓度和季节所包含的22项特征因素，通过调整参数的最优组合，设计出一种新的PM2.5浓度预测模型——RFRP模型。同时，收集了西安市2013—2016年的历史气象数据，进行模型的有效性实验分析。实验结果表明，RFRP模型不仅能有效预测PM2.5浓度，还能在不影响预测精度的同时，较好地提升模型的运行效率，其平均运行时间为0.281 s，约为BP-NN（back propagation neural network，BP神经网络）预测模型的5.88%。

Abstract

The random foreat regression algorithm was introduced to solve the shortcomings of neural network in predicting the PM2.5 concentration

such as over-fitting

complex network structure

low learning efficiency.A novel PM2.5 concentration prediction model named RFRP was designed by analyzing the 22 characteristic factors including the meteorological conditions

the concentration of air pollutants and the season.The historical meteorological data of Xi’an in 2013—2016 were collected to verify the effectiveness of the model.The experimental results show that the proposed model can not only predict the PM2.5 concentration effectively

but also improve the operating efficiency of the model without affecting the prediction accuracy.The average run time of the proposed model is 0.281 s

which is about 5.58% of the neural network prediction model.

关键词

Keywords

references

MA H , SHEN H , LIANG Z , et al . Passenger’s exposure to PM2.5,PM10,and CO 2 in typical underground subway platforms in shanghai [J ] . Lecture Notes in Electrical Engineering , 2014 ( 261 ): 237 - 245 .

SCHWARTZ J , DOCKERY D W , NEAS L S . Is daily mortality associated specifically with fine particles? [J ] . Journal of the Air and Waste Management Association , 1996 ( 46 ):927.

马丽梅 , 张晓 . 中国雾霾污染的空间效应及经济、能源结构影响 [J ] . 中国工业经济 , 2014 ( 4 ): 19 - 31 .

MA L M , ZHANG X . The spatial effect of China’s haze pollution and the impact from economic change and energy structure [J ] . China Induxtrial Economics , 2014 ( 4 ): 19 - 31 .

付倩娆 . 基于多元线性回归的雾霾预测方法研究 [J ] . 计算机科学 , 2016 , 43 ( 6A ): 526 - 528 .

FU Q R . Research on haze prediction based on multivariate linear regression [J ] . Computer Science , 2016 , 43 ( 6A ): 526 - 528 .

CHELANI A B , DEVOTTA S . Prediction of ambient carbon monoxide concentration using nonlinear time series analysis technique [J ] . Transportation Research Part D:Transport and Environment , 2007 , 12 ( 8 ): 596 - 600 .

毛毳 , 孙宇 , 冯樷 , 等 . 空气中 PM2.5 浓度的灰色预测与关联因素分析 [J ] . 宁夏大学学报(自然科学版） , 2014 , 35 ( 3 ): 283 - 288 .

MAO C , SUN Y , FENG C , et al . >Grey forecast and correlation factors analysis of PM2.5 in the air [J ] . Journal of Ningxia University(Natural Science Edition) , 2014 , 35 ( 3 ): 283 - 288 .

ZHANG C J , DAI L J , MA L M . Rolling forecasting model for PM25 concentration based on support vector machine and particle swarm optimization [C ] // International Symposium on Optoelectronic Technology and Application,May 9-11,2016,Beijing,China .[S.l.:s.n. ] , 2016 .

BALACHANDRAN S , CHANG H , PACHON J , et al . >Bayesian-based ensemble source apportionment of PM2.5 [J ] . Environment Science ＆ Technology , 2013 , 47 ( 23 ): 13511 - 13518 .

GRIVAS G , CHALOULAKOU A . Artificial neural network models for prediction of PM10 hourly concentrations,in the Greater Area of Athens,Greece [J ] . Atmospheric Environment , 2006 , 40 ( 7 ): 1216 - 1229 .

马天成 , 刘大铭 , 李雪洁 , 等 . 基于改进型 PSO 的模糊神经网络 PM2.5 浓度预测 [J ] . 计算机工程与设计 , 2014 , 35 ( 9 ): 3258 - 3262 .

MA T C.LIU D M , LI X J , et al . Improved particle swarm optimization based fuzzy neural network for PM2.5 concentration prediction [J ] . Computer Engineering and Design , 2014 , 35 ( 9 ): 3258 - 3262 .

LIN C J , CHEN C H , LIN C T . A hybrid of cooperative particle swarm optimization and cultural algorithm for neural fuzzy networks and its prediction applications [J ] . IEEE Transactions on Systems Man ＆ Cybernetics Part C , 2009 , 39 ( 1 ): 55 - 68 .

杨云 , 付彦丽 . 基于T-S模型模糊神经网络的PM2.5质量浓度预测 [J ] . 陕西科技大学学报(自然科学版) , 2015 , 33 ( 6 ): 162 - 166 .

YANG Y , FU Y L.The prediction of mass concentration of PM2 . 5 based on T-S fuzzy neural network [J ] . Journal of Shaanxi University of Science ＆ Technology(Natural Science Edition) , 2015 , 33 ( 6 ): 162 - 166 .

MCKEEN S , CHUNG S H , WILCZAK J , et al . Evaluation of several PM2.5 forecast models using data collected during the ICARTT/NEAQS 2004 field study [J ] . Journal of Geophysical Research , 2007 , 112 ( D10 ): 541 - 553 .

BREIMAN L , CUTLER A . Random forests [J ] . MachineLearning , 2001 , 45 ( 1 ): 5 - 32 .

BREIMAN L . Bagging predictors [J ] . Machine Learning , 1996 , 24 ( 2 ): 123 - 140 .

HO T K . The random subspace method for constructing decision forests [J ] . IEEE Transactions on Pattern Analysisand Machine Intelligence , 1998 , 20 ( 8 ): 832 - 844 .

WOLPERT D H , MACREADY W G . An efficient method to estimate bagging’s generalization error [J ] . Machine Learning , 1999 , 35 ( 1 ): 41 - 45 .

CHEN B , WANG X P , YU L X , et al . Prediction of PM2.5 concentration in a agricultural park based on artificial neural network [J ] . Advance Journal of Food Science and Technology , 2016 , 11 ( 4 ): 274 - 280 .

吕昌国 . 基于 BP 算法的网格资源调度研究 [D ] . 哈尔滨:哈尔滨理工大学 , 2007 .

LV C G . Grid resources scheduling research based on BP algorithm [D ] . Harbin:HUST , 2007 .

鲍立威 , 何敏 , 沈平 . 关于BP模型的缺陷的讨论 [J ] . 模式识别与人工智能 , 1995 , 8 ( 1 ): 1 - 5 .

BAO L W , HE M , SHEN P . Argument on the shortcoming of BP-model [J ] . Pattern Recognition and Artificial Intelligence , 1995 , 8 ( 1 ): 1 - 5 .

BP 神经网络优缺点的讨论 [EB/OL ] . (2008-12-01)[2017-03-30].http://www.paper.edu.cn/releasepaper/content/ 200812-27 (2008-12-01)[2017-03-30].http://www.paper.edu.cn/releasepaper/content/ 200812-27 .

BP neural network to discuss the advantages and disadvantages [EB/OL ] . (2008-12-01)[2017-03-30].http://www.paper.edu.cn/releas-epaper/ content/200812-27 (2008-12-01)[2017-03-30].http://www.paper.edu.cn/releas-epaper/ content/200812-27 .

赵会敏 , 雒江涛 , 杨军超 , 等 . 集成BP神经网络预测模型的研究与应用 [J ] . 电信科学 , 2016 , 32 ( 2 ): 60 - 67 .

ZHAO H M , LUO J T , YANG J C , et al . Research and application of prediction model based on ensemble BP neural network [J ] . Telecommunications Science , 2016 , 32 ( 2 ): 60 - 67 .

张国玲 . 基于情感神经网络的风电功率预测 [J ] . 电信科学 , 2017 , 33 ( 3 ): 168 - 172 .

ZHANG G L . An emotional neural network based approach for wind power prediction [J ] . Telecommunications Science , 2017 , 33 ( 3 ): 168 - 172 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据