A new prediction method of industrial atmospheric pollutant emission intensity based on pollutant emission standard quantification

Highlights

● Established a quantification method of pollutant emission standard.

● Predicted the SO₂ emission intensity of single coking enterprises in China.

● Evaluated the influence of pollutant discharge standard on prediction accuracy.

● Analyzed the SO₂ emissions of Chinese provincial and municipal coking enterprises.

Abstract

Industrial emissions are the main source of atmospheric pollutants in China. Accurate and reasonable prediction of the emission of atmospheric pollutants from single enterprise can determine the exact source of atmospheric pollutants and control atmospheric pollution precisely. Based on China’s coking enterprises in 2020, we proposed a quantitative method for pollutant emission standards and introduced the quantification results of pollutant emission standards (QRPES) into the construction of support vector regression (SVR) and random forest regression (RFR) prediction methods for SO₂ emission of coking enterprises in China. The results show that, affected by the types of coke ovens and regions, China’s current coking enterprises have implemented a total of 21 emission standards, with marked differences. After adding QRPES, it was found that the root mean squared error (RMSE) of SVR and RFR decreased from 0.055 kt/a and 0.059 kt/a to 0.045 kt/a and 0.039 kt/a, and theR² increased from 0.890 and 0.881 to 0.926 and 0.945, respectively. This shows that the QRPES can greatly improve the prediction accuracy, and the SO₂ emissions of each enterprise are highly correlated with the strictness of standards. The predicted result shows that 45% of SO₂ emissions from Chinese coking enterprises are concentrated in Shanxi, Shaanxi and Hebei provinces in central China. The method created in this paper fills in the blank of forecasting method of air pollutant emission intensity of single enterprise and is of great help to the accurate control of air pollutants.

Graphical abstract

Keywords

Industrial atmospheric pollutants / Pollutant emission standards / Quantitative method / Machine learning / Single enterprise

References

[1] AghionP, DechezlepretreA, HemousD, MartinR, Van ReenenJ. (2016). Carbon taxes, path dependency, and directed technical change: evidence from the auto industry. Journal of Political Economy, 124( 1): 1– 51

[2] Asefi-NajafabadyS, RaynerP J, GurneyK R, McrobertA, SongY, ColtinK, HuangJ, ElvidgeC, BaughK ( 2014). A multiyear, global gridded fossil fuel CO ₂ emission data product: e valuation and analysis of results. Journal of Geophysical Research, D, Atmospheres, 119( 17): 10213– 10231

[3] BelkA, XuZ Z, CarterD O, LynneA, BucheliS, KnightR, MetcalfJ L. (2018). Microbiome data accurately predicts the postmortem interval using random forest regression models. Genes, 9( 2): 104

[4] BreimanL. (2001). Random forests. Machine Learning, 45( 1): 5– 32

[5] BrokampC, JandarovR, HossainM, RyanP. (2018). Predicting daily urban fine particulate matter concentrations using a random forest model. Environmental Science & Technology, 52( 7): 4173– 4179

[6] CaiS, WangY, ZhaoB, WangS, ChangX, HaoJ. (2017). The impact of the “Air Pollution Prevention and Control Action Plan” on PM_2.5 concentrations in Jing-Jin-Ji region during 2012–2020. Science of the Total Environment, 580 : 197– 209

[7] CevikA, KurtogluA E, BilgehanM, GulsanM E, AlbegmprliH M. (2015). Support vector machines in structural engineering: a review. Journal of Civil Engineering and Management, 21( 3): 261– 281

[8] ChaiT, DraxlerR R. (2014). Root mean square error (RMSE) or mean absolute error (MAE)? Arguments against avoiding RMSE in the literature. Geoscientific Model Development, 7( 3): 1247– 1250

[9] ChenZ Y, ZhangT H, ZhangR, ZhuZ M, YangJ, ChenP Y, OuC Q, GuoY M. (2019). Extreme gradient boosting model to estimate PM_2.5 concentrations with missing-filled satellite data in China. Atmospheric Environment, 202 : 180– 189

[10] ChengW, NgC A. (2019). Using machine learning to classify bioactivity for 3486 Per- and Polyfluoroalkyl Substances (PFASs) from the OECD list. Environmental Science & Technology, 53( 23): 13970– 13980

[11] ChouJ S, ChengM Y, WuY W, PhamA D. (2014). Optimizing parameters of support vector machine using fast messy genetic algorithm for dispute classification. Expert Systems with Applications, 41( 8): 3955– 3964

[12] ConstantinD E, BocanealaC, VoiculescuM, RosuA, MerlaudA, Van RoozendaelM, GeorgescuP L. (2020). Evolution of SO₂ and NO_x emissions from several large combustion plants in Europe during 2005–2015. International Journal of Environmental Research and Public Health, 17( 10): 17103630

[13] DeCiccaP, MalakN. (2020). When good fences aren’t enough: the impact of neighboring air pollution on infant health. Journal of Environmental Economics and Management, 102 : 102324

[14] EbensteinA, FanM, GreenstoneM, HeG, ZhouM. (2017). New evidence on the impact of sustained exposure to air pollution on life expectancy from China’s Huai River Policy. Proceedings of the National Academy of Sciences of the United States of America, 114( 39): 10384– 10389

[15] FaloonaI. (2009). Sulfur processing in the marine atmospheric boundary layer: a review and critical assessment of modeling uncertainties. Atmospheric Environment, 43( 18): 2841– 2854

[16] FanT Y, LiuX H, WuC L, ZhangQ, ZhaoC F, YangX, LiY L. (2022). Comparison of the anthropogenic emission inventory for CMIP6 models with a country-level inventory over china and the simulations of the aerosol properties. Advances in Atmospheric Sciences, 39( 1): 80– 96

[17] GengG N, ZhengY X, ZhangQ, XueT, ZhaoH Y, TongD, ZhengB, LiM, LiuF, HongC P, HeK B, DavisS J. (2021). Drivers of PM_2.5 air pollution deaths in China 2002–2017. Nature Geoscience, 14 : 645– 650

[18] GomezD, SalvadorP, SanzJ, CasanovaJ L ( 2021). A new approach to monitor water quality in the Menor sea (Spain) using satellite data and machine learning methods. Environmental Pollution 286: 117489

[19] HanZ, LiJ, HossainM M, QiQ, ZhangB, XuC. (2022). An ensemble deep learning model for exhaust emissions prediction of heavy oil-fired boiler combustion. Fuel, 308 : 121975

[20] HouB, WangB, DuM, ZhangN. (2020). Does the SO₂ emissions trading scheme encourage green total factor productivity? An empirical assessment on China’s cities. Environmental Science and Pollution Research International, 27( 6): 6375– 6388

[21] HowardD B, ThéJ, SoriaR, FannN, SchaefferR, SaphoresJ M. (2019). Health benefits and control costs of tightening particulate matter emissions standards for coal power plants: the case of Northeast Brazil. Environment International, 124 : 420– 430

[22] JingW L, YangY P, YueX F, ZhaoX D. (2016). A spatial downscaling algorithm for satellite-based precipitation over the Tibetan Plateau based on NDVI, DEM, and land surface temperature. Remote Sensing (Basel), 8( 8): 655

[23] KarplusV J, ZhangS, AlmondD. (2018). Quantifying coal power plant responses to tighter SO₂ emissions standards in China. Proceedings of the National Academy of Sciences of the United States of America, 115( 27): 7004– 7009

[24] LarkinA, GeddesJ A, MartinR V, XiaoQ, LiuY, MarshallJ D, BrauerM, HystadP. (2017). Global land use regression model for nitrogen dioxide air pollution. Environmental Science & Technology, 51( 12): 6957– 6964

[25] LiR, CuiL, LiangJ, ZhaoY, ZhangZ, FuH. (2020). Estimating historical SO₂ level across the whole China during 1973–2014 using random forest model. Chemosphere, 247 : 125839

[26] LinZ L, YanL M. (2016). A support vector machine classifier based on a new kernel function model for hyperspectral data. GIScience & Remote Sensing, 53( 1): 85– 101

[27] LiuF, ZhangQ, TongD, ZhengB, LiM, HuoH, HeK B. (2015). High-resolution inventory of technologies, activities, and emissions of coal-fired power plants in China from 1990 to 2010. Atmospheric Chemistry and Physics, 15( 23): 13299– 13317

[28] LiuX, TaylorM P, AelionC M, DongC. (2021). Novel application of machine learning algorithms and model-agnostic methods to identify factors influencing childhood blood lead levels. Environmental Science & Technology, 55( 19): 13387– 13399

[29] LuQ, ZhengJ Y, YeS Q, ShenX L, YuanZ B, YinS S. (2013). Emission trends and source characteristics of SO₂, NO_x, PM₁₀ and VOCs in the Pearl River Delta region from 2000 to 2009. Atmospheric Environment, 76 : 11– 20

[30] MeyerA, PacG. (2017). Analyzing the characteristics of plants choosing to opt-out of the large combustion plant directive. Utilities Policy, 45 : 61– 68

[31] MiaoZ, BalezentisT, TianZ H, ShaoS, GengY, WuR. (2019). Environmental performance and regulation effect of China’s atmospheric pollutant emissions: evidence from “three regions and ten urban agglomerations”. Environmental and Resource Economics, 74( 1): 211– 242

[32] NanY Q, LiQ, Yu J X, CaiH Y, ZhouQ ( 2020). Has the emissions intensity of industrial sulphur dioxide converged? New evidence from China’s prefectural cities with dynamic spatial panel models. Environment, Development and Sustainability, 22( 6): 5337– 5369

[33] NBSC ( 2018). China Statistical Yearbook 2017. Beijing: China Statistics Press (in Chinese)

[34] NietoP J G, LasherasF S, Garcia-GonzaloE, JuezF J D. (2018). PM₁₀ concentration forecasting in the metropolitan area of Oviedo (Northern Spain) using models based on SVM, MLP, VARMA and ARIMA: a case study. Science of the Total Environment, 621 : 753– 761

[35] QianY, CaoH, HuangS. (2020). Decoupling and decomposition analysis of industrial sulfur dioxide emissions from the industrial economy in 30 Chinese provinces. Journal of Environmental Management, 260 : 110142

[36] RakseS K, ShuklaS. (2010). Spam classification using new kernel function in support vector machine. International Journal on Computer Science and Engineering, 2 : 1819– 1823

[37] RingM, EskofierB M. (2016). An approximation of the Gaussian RBF kernel for efficient classification with SVMs. Pattern Recognition Letters, 84 : 107– 113

[38] SagiO, RokachL. (2018). Ensemble learning: a survey. Wiley Interdisciplinary Reviews. Data Mining and Knowledge Discovery, 8( 4): 1249

[39] SCPRC ( 2013). Air Pollution Prevention and Control Action Plan. Beijing: Ministry of Ecology and Environment of China

[40] SheykhmousaM, MahdianpariM, GhanbariH, MohammadimaneshF, GhamisiP, HomayouniS. (2020). Support vector machine versus random forest for remote sensing image classification: a meta-analysis and systematic review. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13 : 6308– 6325

[41] ShogrkhodaeiS Z, Razavi-TermehS V, FathniaA. (2021). Spatio-temporal modeling of PM_2.5 risk mapping using three machine learning algorithms. Environmental Pollution, 289 : 117859

[42] TanZ, YangQ, ZhengY. (2020). Machine learning models of groundwater arsenic spatial distribution in bangladesh: influence of holocene sediment depositional history. Environmental Science & Technology, 54( 15): 9454– 9463

[43] U.S. EPA ( 2012). Clean Air Interstate Rule, Acid Rain Program, and Former NO _x Budget Trading Program, 2012 Progress Report. Washengton, DC: United States Environmental Protection Agency

[44] VapnikV N ( 1995). The Nature of Statistical Learning Theory. New York: Springer

[45] VapnikV N ( 1998). Statistical Learning Theory. New York: Wiley

[46] WangK, CheL, MaC, WeiY M. (2017). The shadow price of CO₂ emissions in China’s iron and steel industry. Science of the Total Environment, 598 : 272– 281

[47] WangY, ChengK, TianH Z, YiP, XueZ G. (2018). Analysis of reduction potential of primary air pollutant emissions from coking industry in China. Aerosol and Air Quality Research, 18( 2): 533– 541

[48] XiaH, TangJ, AljerfL. (2022). Dioxin emission prediction based on improved deep forest regression for municipal solid waste incineration process. Chemosphere, 294 : 133716

[49] XiaoQ, ChangH H, GengG, LiuY. (2018). An ensemble machine-learning model to predict historical PM_2.5 concentrations in China from satellite data. Environmental Science & Technology, 52( 22): 13260– 13269

[50] YangJ, WenY, WangY, ZhangS, PintoJ P, PenningtonE A, WangZ, WuY, SanderS P, JiangJ H, HaoJ, YungY L, SeinfeldJ H. (2021). From COVID-19 to future electrification: assessing traffic impacts on air quality by a machine-learning model. Proceedings of the National Academy of Sciences of the United States of America, 118( 26): e2102705118

[51] ZhangL, WangY, FengC, LiangS, LiuY, DuH, JiaN. (2021). Understanding the industrial NO_x and SO₂ pollutant emissions in China from sector linkage perspective. Science of the Total Environment, 770 : 145242

[52] ZhengB, ZhangQ, TongD, ChenC C, HongC P, LiM, GengG N, LeiY, HuoH, HeK B. (2017). Resolution dependence of uncertainties in gridded emission inventories: a case study in Hebei, China. Atmospheric Chemistry and Physics, 17( 2): 921– 933

[53] ZhengH T, CaiS Y, WangS X, ZhaoB, ChangX, HaoJ M. (2019). Development of a unit-based industrial emission inventory in the Beijing-Tianjin-Hebei region and resulting improvement in air quality modeling. Atmospheric Chemistry and Physics, 19( 6): 3447– 3462

[54] ZouB, YouJ, LinY, DuanX, ZhaoX, FangX, CampenM J, LiS. (2019). Air pollution intervention and life-saving effect in China. Environment International, 125 : 529– 541

Acknowledgements

This research was supported by the National Key R&D Program of China (No. 2018YFC1800106). The authors thank the relevant editor and the anonymous reviewers for their valuable comments and suggestions.

Electronic Supplementary Material

Supplementary material is available in the online version of this article at https://doi.org/10.1007/s11783-023-1608-1 and is accessible for authorized users.

RIGHTS & PERMISSIONS

2023 Higher Education Press