基于粒子群算法的BP 神经网络在大气
NO2 浓度预测中的应用研究

大气与环境光学学报 ›› 2022, Vol. 17 ›› Issue (2): 230-240.

基于粒子群算法的BP 神经网络在大气 NO2 浓度预测中的应用研究

郭映映, 齐贺香, 李素文∗, 牟福生∗

淮北师范大学物理与电子信息学院, 安徽淮北 235000

收稿日期:2020-10-16 修回日期:2022-01-14 出版日期:2022-03-28 发布日期:2022-03-28
通讯作者: E-mail: swli@chnu.edu.cn;E-mail: fsmou@aiofm.ac.cn E-mail:swli@chnu.edu.cn
作者简介:郭映映 (1994 - ), 女, 安徽马鞍山人, 硕士研究生, 主要从事差分吸收光谱技术方法与应用方面的研究。 E-mail: yingyingguo2019@outlook.com
基金资助:
Supported by National Natural Science Foundation of China (国家自然科学基金, 41875040, 41705012), Top-Notch Talent Support Program of Higher Learning Institutions of Anhui (安徽省高校学科拔尖人才项目, gxbjZD2020067)

Application of BP neural network based on particle swarm optimization in atmospheric NO2 concentration prediction

GUO Yingying, QI Hexiang, LI Suwen∗, MOU Fusheng∗

College of Physics and Electronic Information, Huaibei Normal University, Huaibei 235000 China

Received:2020-10-16 Revised:2022-01-14 Published:2022-03-28 Online:2022-03-28
Contact: Li SuWen E-mail:swli@chnu.edu.cn

摘要/Abstract

摘要： NO2 是主要的大气污染气体之一, 在大气光化学过程中起着重要作用。研究 NO2 浓度的时空演变, 预测其浓度变化趋势, 对政府出台改善环境措施具有重要意义。提出利用粒子群算法 (PSO) 的反向传播 (BP) 神经网络对大气 NO2 浓度进行预测。以合肥地区 2017 年 1 月 1 日至 2019 年 12 月 31 日的大气污染数据和气象数据为基础, 结合逐步回归方法筛选出与 NO2 浓度相关性较大的影响因子作为输入样本。构建 PSO-BP 神经网络预测模型, 利用 PSO 找出 BP 神经网络最优的初始权值和阈值。对比 BP 神经网络、遗传算法改进的 BP 神经网络和 PSO 改进的 BP 神经网络三种模型的预测结果, 发现 PSO-BP 模型能够较为准确地预测出 NO2 浓度的动态变化规律, 并且预测精度高、模式简单, 有望广泛应用于大气污染物浓度预测等方面的研究。

关键词: 粒子群算法, 反向传播神经网络, 逐步回归, NO2 浓度预测

Abstract: NO2 is one of the main atmospheric pollutants, which plays an important role in atmospheric photochemical process. It is of great significance to study the temporal and spatial variation law of NO2 concentration and predict the variation trend of NO2 concentration. The BP neural network based on particle swarm optimization (PSO) was proposed to predict atmospheric NO2 concentration. Based on the air pollution data and meteorological data of Hefei area, China, from January 1, 2017 to December 31, 2019 and combined with the stepwise regression method, the influencing factors with high correlation with NO2 concentration were selected as the input samples. The PSO-BP neural network prediction model was constructed, and then the optimal solution of the initial weight and threshold value of the BP neural network were found by using PSO algorithm. By comparing the prediction results of the traditional BP neural network, BP neural network improved by genetic algorithm and BP neural network improved by PSO, it was found that PSO-BP model can accurately predict the dynamic change of NO2 concentration with high prediction accuracy and simple model, which is expected to be widely used in air pollutant concentration prediction in the future.

Key words: particle swarm optimization, back propagation neural network, stepwise regression, NO2 concentration prediction

中图分类号:

X831

郭映映, 齐贺香, 李素文∗, 牟福生∗. 基于粒子群算法的BP 神经网络在大气 NO2 浓度预测中的应用研究[J]. 大气与环境光学学报, 2022, 17(2): 230-240.

GUO Yingying, QI Hexiang, LI Suwen∗, MOU Fusheng∗. Application of BP neural network based on particle swarm optimization in atmospheric NO2 concentration prediction[J]. Journal of Atmospheric and Environmental Optics, 2022, 17(2): 230-240.

参考文献 15

[1]	Mou F S, Luo J, Li S W, et al. Vertical profile of aerosol extinction based on the measurement of O4 of multi-elevation angles
	with MAX-DOAS [J]. Chinese Physics B, 2019, 28(8): 084212.
[2]	Peng Y, Zhao Z R, Wu T X, et al. Prediction of PM2:5 concentration based on ensemble learning [J]. Journal of Beijing
	University of Posts and Telecommunications, 2019, 42(6): 162-169.
	彭岩, 赵梓如, 吴婷娴, 等. PM2:5 浓度预测与影响因素分析 [J]. 北京邮电大学学报, 2019, 42(6): 162-169.
[3]	Zhang Y W, Guo A D, Wu H L, et al. Seasonal prediction of PM2:5 based on the PCA-BP neural network [J]. Journal of Nanjing
	Forestry University (Natural Sciences Edition), 2020, 44(5): 231-238.
	张怡文, 郭傲东, 吴海龙, 等. 基于 PCA-BP 神经网络的 PM2:5 季节性预测方法研究 [J]. 南京林业大学学报 (自然科学
版)	, 2020, 44(5): 231-238.
[4]	Huang H, Lan H Y, Huang Y B. A detection method of SO2 concentration based on DBN and ELM [J]. Journal of Atmospheric
	and Environmental Optics, 2020, 15(3): 207-216.
	黄鸿, 兰洪勇, 黄云彪. 基于深度信念网络和极限学习机的 SO2 浓度检测 [J]. 大气与环境光学学报, 2020, 15(3):
20	7-216.
[5]	Li S W, Liu W Q, Xie P H, et al. Real-time forecasting model for monitoring pollutant with differential optical absorption
	spectroscopy [J]. Spectroscopy and Spectral Analysis, 2009, 29(11): 3057-3060.
	李素文, 刘文清, 谢品华, 等. 差分吸收光谱系统监测污染物浓度实时预测模型 [J]. 光谱学与光谱分析, 2009, 29(11):
30	57-3060.
[6]	Zeng W L, Miwa T, Morikawa T. Prediction of vehicle CO2 emission and its application to eco-routing navigation [J]. Transportation Research Part C: Emerging Technologies, 2016, 68: 194-214.
[7]	Luna A S, Paredes M L L, de Oliveira G C G, et al. Prediction of ozone concentration in tropospheric levels using artificial
	neural networks and support vector machine at Rio de Janeiro, Brazil [J]. Atmospheric Environment, 2014, 98: 98-104.
[8]	Jiang Q F, Du J L, Zhou Y. A method for predicting PM2:5 concentration based on QPSO-RBF model and its application [J].
	Computer Applications and Software, 2020, 37(9): 202-208.
	蒋奇峰, 杜景林, 周芸. 一种基于 QPSO-RBF 模型预测 PM2:5 浓度值的方法研究及应用 [J]. 计算机应用与软件, 2020,
37	(9): 202-208.
[9]	Chen Z Y. Research on VOCs Mixed Gas Detection Based on BP Neural Network [D]. Ningbo: Ningbo University, 2017.
	陈志芸. 基于 BP 神经网络的 VOCs 混合气体检测研究 [D]. 宁波: 宁波大学, 2017.
[10]	Sun H, Zhang L X, Yang Q G, et al. Prediction of refractive index and density of supercritical carbon dioxide based on GA-BP
	neural network [J]. Thermal Power Generation, 2020, 49(10): 59-64.
	孙辉, 章立新, 杨其国, 等. 基于 GA-BP 神经网络的超临界二氧化碳折射率及密度预测 [J]. 热力发电, 2020, 49(10):
59	-64.
[11]	Yi Z M, Deng Z D, Qin J Z, et al. NOx prediction of sintering flue gas based on RBF-BP hybrid neural network [J]. Journal of
	Iron and Steel Research, 2020, 32(7): 639-646.
	易正明, 邓植丹, 覃佳卓, 等. 基于 RBF-BP 混合神经网络的烧结烟气 NOx 预测 [J]. 钢铁研究学报, 2020, 32(7): 639-646.
[12]	Zhang X. Air Quality Prediction Based on Neural Network [D]. Nanjing: Nanjing University of Information Science & Technology, 2019.
	张旭. 基于神经网络的空气质量预测 [D]. 南京: 南京信息工程大学, 2019.
[13]	Vongkok A, Pochai N. Numerical models of nitrogen compound measurements in a stream with removal mechanism using
	Saulyev technique with cubic spline interpolation [J]. Journal of Interdisciplinary Mathematics, 2019, 22(8): 1235-1275.
[14]	Sicard P, Paoletti E, Agathokleous E, et al. Ozone weekend effect in cities: Deep insights for urban air pollution control [J].
	Environmental Research, 2020, 191: 110193.
[15]	Li J X. Research on Forecast and Influencing Factors of PM2:5 Concentration in Chengdu [D]. Lanzhou: Lanzhou University,
	2020.
	李佳旭. 成都市 PM2:5 浓度的影响因素分析及预测 [D]. 兰州: 兰州大学, 2020.