基于逆方差多模型融合的空气质量指数预测方法

孙朝云; 杜耀辉; 裴莉莉; 刘英; 吴玉龙

doi:10.13205/j.hjgc.202302026

基于逆方差多模型融合的空气质量指数预测方法

doi: 10.13205/j.hjgc.202302026

长安大学信息工程学院, 西安 710064

基金项目:

陕西省重点研发计划"基于大数据和云计算路面智慧养护决策系统研发"(2022JBGS3-08)

国家重点研发计划"高速公路基础设施绿色能源自洽供给与高效利用系统关键技术研究"(2021YFB1600205)

详细信息

作者简介:
孙朝云(1962-),女,教授,主要研究方向为人工智能与大数据分析。zhaoyunsun@126.com

通讯作者:
裴莉莉(1995-),女,博士,主要研究方向为人工智能与大数据分析。peilili@chd.edu.cn

计量
- 文章访问数: 84
- HTML全文浏览量: 12
- PDF下载量: 9
- 被引次数: 0
出版历程
- 收稿日期: 2022-04-27
- 网络出版日期: 2023-05-25
- 刊出日期: 2023-02-01

AN AIR QUALITY INDEX PREDICTION METHOD BASED ON INVERSE VARIANCE MULTI-MODEL FUSION

School of Information Engineering, Chang'an University, Xi'an 710064, China

摘要

摘要: 空气质量预测对合理制定环境治理政策具有重要意义。针对目前单体预测模型存在模型不稳定和泛化能力不强的问题,提出基于逆方差权重分配方法融合3种单体模型的空气质量指数(air quality index,AQI)预测方法。首先,以北京市为例,构建空气质量指数预测数据集;其次,分别构建长短期记忆网络(LSTM)、门控循环单元(GRU)、双向长短期记忆网络(Bi-LSTM)、自回归积分滑动平均模型(ARIMA)和多元线性回归(MLR)5种模型对数据集进行预测,并对比以上模型的预测结果; 最后,在多模型融合方法中,选择逆方差法计算预测精度较高的3种单体模型的权重,根据算得权重构建逆方差融合预测模型。与预测精度较高的3种单体模型以及加权平均融合预测模型相比,逆方差融合预测模型对空气质量指数的预测精度R²分别提高3.9%、3.4%、1.6%和0.5%,达到0.933。结果表明:逆方差融合预测模型综合了各单体预测模型的优点,能够提高AQI预测精度。
- 空气质量指数预测 /
- 模型融合 /
- 神经网络 /
- 长短期记忆网络 /
- 逆方差
Abstract: The prediction of air quality is of great significance for formulating environmental governance policies. Aiming at the problems of instability and weak generalization ability of the single model method, a multi-model fusion prediction method of air quality index (AQI) based on the inverse variance weight distribution method and fusion of three single model methods was proposed. Firstly, taking Beijing as an example, the air quality index prediction dataset was constructed. Secondly, five models, LSTM, GRU, Bi-LSTM, ARIMA and MLR, were constructed to predict the dataset, and the prediction results of these models were compared. Finally, in the multi-model fusion method, the inverse variance method was used to calculate the weight of three monomer models with high prediction accuracy, and the inverse variance fusion prediction model was constructed according to the calculated weight. Compared with the three monomer models with higher prediction accuracy and the weighted average fusion prediction model, the prediction accuracy, R² of the inverse variance fusion prediction model for air quality index was improved by 3.9%, 3.4%, 1.6% and 0.5% respectively, reaching 0.933. The results showed that the proposed inverse variance fusion prediction model integrated the advantages of each monomer prediction model, which could improve the prediction accuracy of air quality index.
- air quality index prediction /
- model fusion /
- neural network /
- long-short-term memory neural network /
- inverse variance

HTML全文

参考文献(23)

[1]	LIU H, YIN S, CHEN C, et al. Data multi-scale decomposition strategies for air pollution forecasting:a comprehensive review[J]. Journal of Cleaner Production, 2020, 277:124023.
[2]	DINCER N G, AKKU Z. A new fuzzy time series model based on robust clustering for forecasting of air pollution[J]. Ecological Informatics, 2018, 43:157-164.
[3]	MIRI M, ALAHABADI A, EHRAMPUSH M H, et al. Mortality and morbidity due to exposure to ambient particulate matter[J]. Ecotoxicology and Environmental Safety, 2018, 165:307-313.
[4]	赵文成, 王访. 基于多尺度交叉趋势样本熵的城市空气质量指数分析[J]. 环境工程, 2020, 38(2):91-98.
[5]	LIU H, YAN G X, DUAN Z, et al. Intelligent modeling strategies for forecasting air quality time series:a review[J]. Applied Soft Computing, 2021, 102:106957.
[6]	QIAO X, YING Q, LI X, et al. Source apportionment of PM_2.5 for 25 Chinese provincial capitals and municipalities using a source-oriented Community Multiscale Air Quality model[J]. Science of the Total Environment, 2017, 612:462-471.
[7]	JEONG J I, PARK R, WOO J H, et al. Source contributions to carbonaceous aerosol concentrations in Korea[J]. Atmospheric Environment, 2011, 45(5):1116-1125.
[8]	LI C, HSU N C, TSAY S C. A study on the potential applications of satellite data in air quality monitoring and forecasting[J]. Atmospheric Environment, 2011, 45(22):3663-3675.
[9]	史凯赫, 丁日佳, 吴利丰, 等.预测空气质量的新型灰色系统多变量模型构建:以石家庄市为例[J]. 系统科学学报, 2023(2):75-81.
[10]	ZHANG L Y, LIN J N, QIU R Z, et al. Trend analysis and forecast of PM_2.5 in Fuzhou, China using the ARIMA model[J]. Ecological Indicators, 2018, 95:702-710.
[11]	LIU B C, ARIHANT B, CHANG P C, et al. Urban air quality forecasting based on multi-dimensional collaborative Support Vector Regression (SVR):a case study of Beijing-Tianjin-Shijiazhuang[J]. PLoS One, 2017, 12(7):0179763.
[12]	徐乔王, 胡红萍, 白艳萍, 等. 基于MEA_SVM空气质量指数预测[J]. 重庆理工大学学报(自然科学版), 2019, 33(12):150-155.
[13]	LI X, PENG L, YAO X J, et al. Long short-term memory neural network for air pollutant concentration predictions:method development and evaluation[J]. Environmental Pollution, 2017, 231:997-1004.
[14]	SHARMA E, DEO R C, PRASAD R, et al. A hybrid air quality early-warning framework:an hourly forecasting model with online sequential extreme learning machines and empirical mode decomposition algorithms[J]. Science of the Total Environment, 2020, 709:135934.
[15]	YAN R, LIAO J Q, YANG J, et al. Multi-hour and multi-site air quality index forecasting in Beijing using CNN, LSTM, CNN-LSTM, and spatiotemporal clustering[J]. Expert Systems with Applications, 2020, 169(4):114513.
[16]	LIU B, YU X, CHEN J, et al. Air pollution concentration forecasting based on wavelet transform and combined weighting forecasting model[J]. Atmospheric Pollution Research, 2021, 12(8):101144.
[17]	GREFF K, SRIVASTAVA R K, KOUTNÍK J, et al. LSTM:a search space odyssey[J]. IEEE Transactions on Neural Networks & Learning Systems, 2016, 28(10):2222-2232.
[18]	ZHANG B, ZHANG H, ZHAO G, et al. Constructing a PM_2.5 concentration prediction model by combining auto-encoder with Bi-LSTM neural networks[J]. Environmental Modelling and Software, 2019, 124:104600.
[19]	HUANG G Y, LI X Y, ZHANG B, et al. PM_2.5 concentration forecasting at surface monitoring sites using GRU neural network based on empirical mode decomposition[J]. Science of the Total Environment, 2021, 768(3):144516.
[20]	ALABDULRAZZAQ H, ALENEZI M, RAWAJFIH Y, et al. On the accuracy of ARIMA based prediction of COVID-19 spread[J]. Results in Physics, 27:104509.
[21]	杜展鹏, 王明净, 严长安, 等. 基于绝对主成分-多元线性回归的滇池污染源解析[J]. 环境科学学报, 2020, 40(3):1130-1137.
[22]	谭小钰, 刘芳, 马俊杰, 等. 基于DBN与T-S时变权重组合的光伏功率超短期预测模型[J]. 太阳能学报, 2021, 42(10):42-48.
[23]	裴莉莉, 孙朝云, 户媛姣, 等. 基于多特征因子的路用集料粒径计算神经网络模型[J]. 华南理工大学学报(自然科学版), 2020, 48(6):77-86.