基于集成学习策略的化工园区大气污染影响预测

doi:10.12005/orms.2021.0360

运筹与管理 ›› 2021, Vol. 30 ›› Issue (11): 127-134.DOI: 10.12005/orms.2021.0360

基于集成学习策略的化工园区大气污染影响预测

王旭坪¹, 于秀丽^1,2, 王天腾¹

1.大连理工大学经济管理学院,辽宁大连 116023;
2.大连海洋大学海洋法律与人文学院,辽宁大连 116023

收稿日期:2020-02-05 出版日期:2021-11-25
通讯作者: 于秀丽(1980-),女,辽宁大连人,副教授,博士,研究方向:信息系统集成与应急管理。
作者简介:王旭坪 (1962-),男,辽宁锦州人,博士,教授,博士生导师,研究方向:电子商务与物流管理、应急管理;王天腾(1997-),男,黑龙江牡丹江人,硕士,研究方向:数据挖掘,应急管理。
基金资助:
国家自然科学基金资助项目(72071028);辽宁省经济社会发展研究课题(2021lslybkt-058);辽宁省社会科学规划基金项目(L20BGL051)

Air Pollution Impact Prediction of Chemical Industry Park Based on Ensemble Learning Strategy

WANG Xu-ping¹, YU Xiu-li^1,2, WANG Tian-teng¹

1. School of Economics and Management, Dalian University of Technology, Dalian 116023, China;
2. School of Marine Law and Humanities, Dalian Ocean University, Dalian 116623, China

Received:2020-02-05 Online:2021-11-25

摘要/Abstract

摘要： 建立科学、有效、准确的空气质量预测系统,对于保护人们的身体健康和促进社会的和谐稳定具有重要的科学价值和实际意义。研究聚焦化工园区,基于物联网背景下企业排放实时数据,融合气象信息,采用多种有监督式机器学习(决策树、多元线性回归、Lasso回归、支持向量机、Xgboost、梯度提升机、Light GBM、MLP(多层感知觉神经网络))及改进的集成学习Stacking策略实现化工园区空气质量的预测,并识别影响大气污染的关键因素。结果表明:(1)Stacking策略下的预测框架与单模型预测结果相比有统计学意义上的显著提升。(2)在Stacking策略中,初级、次级学习器的选择策略影响预测的精度和泛化性,最佳模式为初级采用强学习器,次级使用线性模型。(3)在同一园区、不同企业污染物不同排放口对空气质量影响不同,研究结论可为政府监管部门对化工园区的治理和管控提供决策支持。

关键词: Stacking策略, 机器学习, 大气污染影响, 化工园区

Abstract: Establishing a scientific, effective and accurate air quality prediction system has important scientific value and practical significance for protecting people's health and promoting social harmony and stability. In this paper, we focus on chemical industry parks, with the data of enterprise emissions and meteorological information, utilizing supervised machine learning (decision tree, multiple linear regression, Lasso regression, support vector machine, Xgboost, gradient boosting machine, Light GBM, MLP) and ensemble learning Stack strategy to realize the prediction and control of atmospheric environmental pollution in chemical industry park. The results show that: (1)The prediction results under stacking strategy have improved significantly compared with the prediction result of single model. (2)In stacking strategy, the choice of primary and secondary learners affects the accuracy and generalization of prediction. The best mode is to use strong learners at the primary level and linear models at the secondary level. (3)Different outlets in the same park and different enterprises have different impacts on air quality. In this paper, the trend of pollution events in chemical industrial parks is predicted reasonably, which can provide decision support for the government in the management and control of enterprises in chemical industry parks.

Key words: stacking strategy, machine learning, air pollution impact, chemical industrial park

中图分类号:

F205

王旭坪, 于秀丽, 王天腾. 基于集成学习策略的化工园区大气污染影响预测[J]. 运筹与管理, 2021, 30(11): 127-134.

WANG Xu-ping, YU Xiu-li, WANG Tian-teng. Air Pollution Impact Prediction of Chemical Industry Park Based on Ensemble Learning Strategy[J]. Operations Research and Management Science, 2021, 30(11): 127-134.

参考文献

[1] 李丹,戴玄吏,董黎静,蔡焕兴.化工园区大气环境特征及其对健康的影响[J].环境工程,2014,32(01):84-87,125.
[2] 罗宏远,王德运,刘艳玲,魏帅,林彦兵.基于二层分解技术和改进极限学习机模型的PM2.5浓度预测研究[J].系统工程理论与实践,2018,38(5):1321-1330.
[3] Wu Q L, Lin H X. Daily urban air quality index forecasting based on variational mode decomposition, sample entropy and LSTM neural network[J]. Sustainable Cities and Society, 2019, 50(10): 1-9.
[4] Wang B, Jiang Q C, Jiang P. A combined forecasting structure based on the L1norm: application to the air quality[J]. Journal of environmental management, 2019, 246: 299-313.
[5] 王建州,杨文栋.基于非线性修正策略的空气质量预警系统研究[J].系统理论工程与实践,2019,39(8):2138-2151.
[6] 杨思琪,赵丽华.随机森林算法在城市空气质量预测中的应用[J].统计与决策,2017(20):84-87.
[7] 赵琦琳,邱飞,杨健.NARX神经网络模型在昆明市环境空气质量预测中的应用[J].中国环境监测,2019,35(3):42-48
[8] Polikar R. Bootstrap-inspired techniques in computation intelligence[J]. IEEE Signal Processing Magazine, 2007, 24(4): 59-72.
[9] Feng X, Li Q, Zhu Y J, Hou J X, Jin L Y, Wang J J. Artificial neural networks forecasting of PM2.5 pollution using air mass trajectory based geographic model and wavelet transformation[J]. Atmospheric Environment, 2015, 107: 118-128.
[10] Vlachogianni A, Kassomenos P, Karppinen A, Karakitsios S, Kukkonen J. Evaluation of a multiple regression model for the forecasting of the concentrations of NO_x and PM10 in athens and helsinki[J]. Science of the Total Environment, 2011, 409(8): 1559-1571.
[11] Jian L, Zhao Y, Zhu Y P, Zhang M B. An application of ARIMA model to predict submicron particle concentrations from meteorological factors at a busy roadside in Hangzhou, China[J]. Science of the Total Environment, 2012, 426: 336-345.
[12] Zhu D. A hybrid approach for efficient ensembles[J]. Decision Support Systems, 2010, 48(3): 480-487.
[13] Goyal P, Chan A T, Jaiswal N. Statistical models for the prediction of respirable suspended particulate matter in urban cities[J]. Atmospheric Environment, 2006, 40(11): 2068-2077.
[14] Jordan M I, Mitchell T M. Machine learning: trends, perspectives, and prospects[J]. Science, 2015, 349(6245): 255-260.
[15] Sun C, Ma M, Zhao Z, Chen X F. Sparse deep stacking network for fault diagnosis of motor[J]. IEEE Transactions on Industrial Informatics, 2018, 14(7): 3261-3270.
[16] Džeroski S, Ženko B. Is combining classifiers with stacking better than selecting the best one?[J]. Machine Learning, 2004, 54(3): 255-273.
[17] Moudrik J, Neruda R. Evolving non-linear stacking ensembles for prediction of go player attributes[C]// Computational Intelligence, IEEE Symposium. 2015.1673-1680.
[18] Alvear-Sandoval R F, Figueiras-Vidal A R. On building ensembles of stacked denoising auto-encoding classifiers and their further improvement[J]. Information Fusion, 2018, 39: 41-52.
[19] Demir N, Dalkiliç G. Modified stacking ensemble approach to detect network intrusion[J]. Turkish Journal of Electrical Engineering and Computer Science, 2018, 26(1): 418-433
[20] Guo Y, Liu S H, Li Z H, Shang X Q. BCDForest: a boosting cascade deep forest model towards the classification of cancer subtypes based on gene expression data[J]. BMC bioinformatics, 2018, 19(5): 118.
[21] Khamparia A, Gupta D, Nguyen N G, Khanna A. Sound classification using convolutional neural network and tensor deep stacking network[J]. IEEE Access, 2019, 7(99): 7717-7727.
[22] 周志华.机器学习[M].清华大学出版社,2016.
[23] Flocas H, Kelessis A, Helmis C, Petrakakis M. Synoptic and local scale atmospheric circulation associated with air pollution episodes in an urban Mediterranean area[J]. Theoretical and Applied Climatology, 2009, 95(3-4): 265-277.
[24] Ragosta M, Caggiano R, Macchiato M, Sabia S, Trippetta S. Trace elements in daily collected aerosol: level characterization and source identification in a four-year study[J]. Atmospheric Research, 2008, 89(1): 206-217.
[25] Wolpert D. H. Stacked generalization[M]. Springer US, 2017.
[26] Wolpert D H, Macready W G. No free lunch theorems for optimization[J]. IEEE transactions on evolutionary computation, 1997, 1(1): 67-82.

基于集成学习策略的化工园区大气污染影响预测

Air Pollution Impact Prediction of Chemical Industry Park Based on Ensemble Learning Strategy

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

[1]	李培志, 董清利. 基于网络搜索数据和机器学习的票房预测模型[J]. 运筹与管理, 2021, 30(11): 168-175.
[2]	梁爽, 刁节文, 肖邦. P2P网贷平台风险预测研究[J]. 运筹与管理, 2021, 30(1): 170-176.
[3]	郭换换, 王飞跃, 裴甲坤, 杨宸宇. 化工园区应急设施区间规划选址模型研究[J]. 运筹与管理, 2020, 29(5): 67-73.