PM10 and PM2.5 real-time prediction models using an interpolated convolutional neural network.


Journal

Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288

Informations de publication

Date de publication:
07 06 2021
Historique:
received: 12 05 2020
accepted: 21 05 2021
entrez: 8 6 2021
pubmed: 9 6 2021
medline: 9 6 2021
Statut: epublish

Résumé

In this paper, we propose a real-time prediction model that can respond to particulate matters (PM) in the air, which are an indication of poor air quality. The model applies interpolation to air quality and weather data and then uses a Convolutional Neural Network (CNN) to predict PM concentrations. The interpolation transforms the irregular spatial data into an equally spaced grid, which the model requires. This combination creates the interpolated CNN (ICNN) model that we use to predict PM10 and PM2.5 concentrations. The PM10 and PM2.5 evaluation results show an effective prediction performance with an R-squared higher than 0.97 and a root mean square error (RMSE) of approximately 16% of the standard deviation. Furthermore, both PM10 and PM2.5 prediction models forecast high concentrations with high reliability, with a probability of detection higher than 0.90 and a critical success index exceeding 0.85. The proposed ICNN prediction model achieves a high prediction performance using spatio-temporal information and presents a new direction in the prediction field.

Identifiants

pubmed: 34099763
doi: 10.1038/s41598-021-91253-9
pii: 10.1038/s41598-021-91253-9
pmc: PMC8185114
doi:

Types de publication

Journal Article Research Support, Non-U.S. Gov't

Langues

eng

Sous-ensembles de citation

IM

Pagination

11952

Références

Koo, Y. S., Choi, D. R., Kwon, H. Y., Jang, Y. K. & Han, J. S. Improvement of PM10 prediction in East Asia using inverse modeling. Atmos. Environ. 106, 318–328 (2015).
doi: 10.1016/j.atmosenv.2015.02.004
Beeson, W. L., Abbey, D. E. & Knutsen, S. F. Long-term concentrations of ambient air pollutants and incident lung cancer in California adults: Results from the AHSMOG study: Adventist Health Study on Smog. Environ. Health Perspect. 106(12), 813–823 (1998).
pubmed: 9831542 pmcid: 1533247
Raaschou-Nielsen, O., Andersen, Z. J. & Beelen, R. Air pollution and lung cancer incidence in 17 European cohorts: Prospective analyses from the European Study of Cohorts for Air Pollution Effects (ESCAPE). Lancet Diabetes Endocrinol. 3(18), 925–927 (2015).
Pope, C. A. & Dockery, D. W. Acute health effects of PM10 pollution on symptomatic and asymptomatic children. Am. Rev. Respir. Dis. 145(5), 1123–1128 (1992).
pubmed: 1586057 doi: 10.1164/ajrccm/145.5.1123
Gilmour, P. S. et al. Adverse health effects of PM10 particles: Involvement of iron in generation of hydroxyl radical. Occup. Environ. Med. 53(12), 817–822 (1996).
pubmed: 8994401 pmcid: 1128615 doi: 10.1136/oem.53.12.817
Hong, Y. C., Leem, J. H., Ha, E. H. & Christiani, D. C. PM10 exposure, gaseous pollutants, and daily mortality in Inchon, South Korea. Environ. Health Perspect. 107(11), 873–878 (1999).
pubmed: 10544154 pmcid: 1566699
Cesaroni, G. et al. Long term exposure to ambient air pollution and incidence of acute coronary events: Prospective cohort study and meta-analysis in 11 european cohorts from the escape project. BMJ 348, 7412 (2014).
doi: 10.1136/bmj.f7412
Massimo, S. Long-term exposure to ambient air pollution and incidence of cerebrovascular events: Results from 11 European Cohorts within the ESCAPE Project. Environ. Health Perspect. 122(9), 919–925 (2014).
doi: 10.1289/ehp.1307301
Wilson, R., Spengler, J. D. Particles in Our Air: Concentrations and Health Effects. Harvard University Press (1996).
Wang, F. et al. Ambient concentrations of particulate matter and hospitalization for depression in 26 Chinese cities: A case-crossover study. Environ. Int. 114, 115–122 (2018).
pubmed: 29500987 doi: 10.1016/j.envint.2018.02.012
Youn-Hee, L. et al. Air pollution and symptoms of depression in elderly adults. Environ. Heal. Perspect 120(7), 1023–1028 (2014).
Güler, N. & Güneri Işçi, Ö. The regional prediction model of PM10 concentrations for Turkey. Atmos. Res. 180, 64–77 (2016).
doi: 10.1016/j.atmosres.2016.05.018
Grivas, G. & Chaloulakou, A. Artificial neural network models for prediction of PM10 hourly concentrations, in the Greater Area of Athens, Greece. Atmos. Environ. 40(7), 1216–1229 (2006).
doi: 10.1016/j.atmosenv.2005.10.036
Zhou, Y. et al. Multi-output support vector machine for regional multi-step-ahead PM2.5 forecasting. Sci. Total Environ. 651, 230–240 (2019).
pubmed: 30243160 doi: 10.1016/j.scitotenv.2018.09.111
Lv, B., Cobourn, W. G. & Bai, Y. Development of nonlinear empirical models to forecast daily PM2.5 and ozone levels in three large Chinese cities. Atmos. Environ. 147, 209–223 (2016).
doi: 10.1016/j.atmosenv.2016.10.003
Cobourn, W. G. An enhanced PM2.5 air quality forecast model based on nonlinear regression and back-trajectory concentrations. Atmos. Environ. 44(25), 3015–3023 (2010).
doi: 10.1016/j.atmosenv.2010.05.009
Deng, F., Ma, L., Gao, X. & Chen, J. The MR-CA models for analysis of pollution sources and prediction of PM 2.5. IEEE Trans. Syst. Man Cybern. Syst. 49(4), 814–820 (2019).
doi: 10.1109/TSMC.2017.2721100
Zhao, J., Deng, F., Cai, Y. & Chen, J. Long short-term memory - Fully connected (LSTM-FC) neural network for PM2.5 concentration prediction. Chemosphere 220, 486–492 (2019).
pubmed: 30594800 doi: 10.1016/j.chemosphere.2018.12.128
Vlachogianni, A., Kassomenos, P., Karppinen, A., Karakitsios, S. & Kukkonen, J. Evaluation of a multiple regression model for the forecasting of the concentrations of NOx and PM10 in Athens and Helsinki. Sci. Total Environ. 409(8), 1559–1571 (2011).
pubmed: 21277004 doi: 10.1016/j.scitotenv.2010.12.040
Ivanov, A. & Gocheva-Ilieva, S. Short-time particulate matter PM10 forecasts using predictive modeling techniques. AIP Conf. Proc. 1561(1), 209–218 (2013).
doi: 10.1063/1.4827230
Brunelli, U., Piazza, V., Pignato, L., Sorbello, F. & Vitabile, S. Two-days ahead prediction of daily maximum concentrations of SO2, O3, PM10, NO2, CO in the urban area of Palermo, Italy. Atmos. Environ. 41(14), 2967–2995 (2007).
doi: 10.1016/j.atmosenv.2006.12.013
Oprea, M., Mihalache, S. F. & Popescu, M. Computational intelligence-based PM2.5 air pollution forecasting. Int. J. Comput. Commun. Control. 12, 365–380 (2017).
doi: 10.15837/ijccc.2017.3.2907
Jiang, D. et al. Progress in developing an ANN model for air pollution index forecast. Atmos. Environ. 38(40), 7055–7064 (2004).
doi: 10.1016/j.atmosenv.2003.10.066
Tsai, Y. T., Zeng, Y. R., Chang, Y. S. Air pollution forecasting using RNN with LSTM. IEEE International Symposium on Dependable, Auton. Secure Comput. 1068–1073 (2018).
Park, J., Yoo, S., Kim, K., Gu, Y., Lee, K., Son, U. PM10 density forecast model using long short term memory. International Conference on Ubiquitous and Future Networks, ICUFN. 576–581 (2017).
García-Nieto, P. J. S. L., García-Gonzalo, E. & Cos Juez, F. J. PM10 concentration forecasting in the metropolitan area of Oviedo (Northern Spain) using models based on SVM, MLP, VARMA and ARIMA: A case study. Sci. Total Environ. 621, 753–761 (2018).
pubmed: 29202286 doi: 10.1016/j.scitotenv.2017.11.291
Kong, S. et al. Spatial and temporal variation of phthalic acid esters (PAEs) in atmospheric PM10 and PM2.5 and the influence of ambient temperature in Tianjin, China. Atmos. Environ. 74, 199–208 (2013).
doi: 10.1016/j.atmosenv.2013.02.053
Kuhns, H. et al. Vehicle-based road dust emission measurement - Part II: Effect of precipitation, wintertime road sanding, and street sweepers on inferred PM 10 emission potentials from paved and unpaved roads. Atmos. Environ. 37(32), 4573–4582 (2003).
doi: 10.1016/S1352-2310(03)00529-6
Grundström, M., Hak, C., Chen, D., Hallquist, M. & Pleijel, H. Variation and co-variation of PM10, particle number concentration, NOx and NO2 in the urban air—Relationships with wind speed, vertical temperature gradient and weather type. Atmos. Environ. 120, 317–327 (2015).
doi: 10.1016/j.atmosenv.2015.08.057
Grivas, G., Chaloulakou, A., Samara, C. & Spyrellis, N. Spatial and temporal variation of PM 10 mass concentrations within the greater area of Athens, Greece. Water. Air. Soil Pollut. 158(1), 357–371 (2004).
doi: 10.1023/B:WATE.0000044859.84066.09
Hooyberghs, J., Mensink, C., Dumont, G., Fierens, F. & Brasseur, O. A neural network forecast for daily average PM10 concentrations in Belgium. Atmos. Environ. 39(18), 3279–3289 (2005).
doi: 10.1016/j.atmosenv.2005.01.050
Gryparis, A., Dimakopoulou, K., Pedeli, X. & Katsouyanni, K. Spatio-temporal semiparametric models for NO2 and PM10 concentration levels in Athens, Greece. Sci. Total Environ. 479–480(1), 21–30 (2014).
pubmed: 24531337 doi: 10.1016/j.scitotenv.2014.01.075
Ma, X., Dai, Z., He, Z., Na, J., Wang, Y., Wang, Y. Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction. Sensors. 17(4), 818 (2017).
doi: 10.3390/s17040818 pmcid: 5422179
Ke, J. et al. Hexagon-based convolutional neural network for supply-demand forecasting of ride-sourcing services. IEEE Trans. Intell. Transp. Syst. 20(11), 4160–4173 (2019).
doi: 10.1109/TITS.2018.2882861
Wen, C. et al. A novel spatiotemporal convolutional long short-term neural network for air pollution prediction. Sci. Total Environ. 654, 1091–1099 (2019).
pubmed: 30841384 doi: 10.1016/j.scitotenv.2018.11.086
Li, L., Losser, T., Yorke, C. & Piltner, R. Fast inverse distance weighting-based spatiotemporal interpolation: A web-based application of interpolating daily fine particulate matter PM2.5 in the contiguous U.S. using parallel programming and k-d Tree. Int. J. Environ. Res. Public Health 11(9), 9101–9141 (2014).
pubmed: 25192146 pmcid: 4199009 doi: 10.3390/ijerph110909101
Li, J. & Heap, A. D. A review of comparative studies of spatial interpolation methods in environmental sciences: Performance and impact factors. Ecol. Inform. 6(3–4), 228–241 (2011).
doi: 10.1016/j.ecoinf.2010.12.003
Lu, G. Y. & Wong, D. W. An adaptive inverse-distance weighting spatial interpolation technique. Comput. Geosci. 34(9), 1044–1055 (2008).
doi: 10.1016/j.cageo.2007.07.010
LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521(7553), 436–444 (2015).
pubmed: 26017442 doi: 10.1038/nature14539
Pohlmann, J. T., Leitner, D. W. A Comparison of Ordinary Least Squares and Logistic Regression. Ohio Journal of Science. 103(5), 118-125 (2003).
Stone, M. & Brooks, R. J. Continuum regression: Cross-validated sequentially constructed prediction embracing ordinary least squares, partial least squares and principal components regression. J. R. Stat. Soc. Ser. B 52(2), 237–258 (1990).
Hochreiter, S. & Schmidhuber, J. Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997).
pubmed: 9377276 doi: 10.1162/neco.1997.9.8.1735
Qin, D. et al. A novel combined prediction scheme based on CNN and LSTM for urban PM2.5 concentration. IEEE Access 7, 20050–20059 (2019).
doi: 10.1109/ACCESS.2019.2897028
Qi, Y., Li, Q., Karimian, H. & Liu, D. A hybrid model for spatiotemporal forecasting of PM 2.5 based on graph convolutional neural network and long short-term memory. Sci. Total Environ. 664, 1–10 (2019).
pubmed: 30743109 doi: 10.1016/j.scitotenv.2019.01.333
Stafoggia, M. et al. Estimation of daily PM10 concentrations in Italy (2006–2012) using finely resolved satellite data, land use variables and meteorology. Environ. Int. 99, 234–244 (2017).
pubmed: 28017360 doi: 10.1016/j.envint.2016.11.024
Chaloulakou, A., Assimacopoulos, D. & Lekkas, T. Forecasting daily maximum ozone concentrations in the Athens Basin. Environ. Monit. Assess. 56(1), 97–112 (1999).
doi: 10.1023/A:1005943201063
Doswell, C. A., Davies-Jones, R. & Keller, D. L. On summary measures of skill in rare event forecasting based on contingency tables. Weather Forecast. 5(4), 576–585 (1990).
doi: 10.1175/1520-0434(1990)005<0576:OSMOSI>2.0.CO;2
Wilks, D. S. Statistical Methods in the Atmospheric Sciences. Academic Press (2000).
Fu, X. et al. Source, transport and impacts of a heavy dust event in the Yangtze River Delta, China, in 2011. Atmos. Chem. Phys. 14(3), 1239–1254 (2014).
doi: 10.5194/acp-14-1239-2014
Park, S. U., Choe, A. & Park, M. S. A simulation of Asian dust events observed from 20 to 29 December 2009 in Korea by using ADAM2. Asia-Pac. J. Atmos. Sci. 49(1), 95–109 (2013).
doi: 10.1007/s13143-013-0011-4

Auteurs

Sangwon Chae (S)

Department of Business Administration, Korea Polytechnic University, 237 Sangidaehak-ro, Siheung-si, 15073, Gyeonggi-do, Republic of Korea.

Joonhyeok Shin (J)

Department of Business Administration, Korea Polytechnic University, 237 Sangidaehak-ro, Siheung-si, 15073, Gyeonggi-do, Republic of Korea.

Sungjun Kwon (S)

Department of Business Administration, Korea Polytechnic University, 237 Sangidaehak-ro, Siheung-si, 15073, Gyeonggi-do, Republic of Korea.

Sangmok Lee (S)

Department of Business Administration, Korea Polytechnic University, 237 Sangidaehak-ro, Siheung-si, 15073, Gyeonggi-do, Republic of Korea.

Sungwon Kang (S)

Korea Environment Institute, 370, Sicheong-daero, Sejong-si, 30147, Republic of Korea.

Donghyun Lee (D)

Department of Business Administration, Korea Polytechnic University, 237 Sangidaehak-ro, Siheung-si, 15073, Gyeonggi-do, Republic of Korea. madeby2@gmail.com.

Classifications MeSH