Journals / Atmospheric Pollution Research / 2020 / Cilt: 11 - Sayı: 6

Hourly PM2.5concentration forecasting based on feature extraction andstacking-driven ensemble model for the winter of the Beijing-Tianjin-Hebeiarea

Pages
110–121
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Case study of hourly PM2.5concentration forecasting in the Beijing-Tianjin-Hebei area during the winter substantiates that: (1) application of input selection methods is beneficial tosatisfactory forecasting results; (2) the forecasting performance of the Stacking-driven ensemble model is farbetter than any single models composing of it; (3) the proposed model can tackle highly complicated and ex-tremely high concentration PM2.5data, which is feasible to PM2.5concentration forecasting during the winter;(4) the proposed model with small forecasting error, strong generalization performance, as well robust fore-casting ability is potential in the early air warning systems.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Precise forecasting of hourly PM2.5concentration is essential for its monitoring and controlling, especially for thewinter of the Beijing-Tianjin-Hebei area as severe haze episode occurs frequently.
📊
Key Findings & Data:Therefore, this paper exploresan hourly PM2.5concentration forecasting technique based on the Stacking-driven ensemble model and twokinds of input selection methods.
💡
Conclusion & Impact:Case study of hourly PM2.5concentration forecasting in the Beijing-Tianjin-Hebei area during the winter substantiates that: (1) application of input selection methods is beneficial tosatisfactory forecasting results; (2) the forecasting performance of the Stacking-driven ensemble model is farbetter than any single models composing of it; (3) the proposed model can tackle highly complicated and ex-tremely high concentration PM2.5data, which is feasible to PM2.5concentration forecasting during the winter;(4) the proposed model with small forecasting error, strong generalization performance, as well robust fore-casting ability is potential in the early air warning systems.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters

Özet

Precise forecasting of hourly PM2.5concentration is essential for its monitoring and controlling, especially for thewinter of the Beijing-Tianjin-Hebei area as severe haze episode occurs frequently. Therefore, this paper exploresan hourly PM2.5concentration forecasting technique based on the Stacking-driven ensemble model and twokinds of input selection methods. Firstly, the partial autocorrelation function (PACF) is employed to selectfeatures of time-lagged factors, meanwhile, Spearman correlation coefficient is introduced to extract latentfeatures of exogenous factors, jointly determining the input of the forecasting model. Subsequently, a two-layerStacking-driven ensemble model is formed as the prediction model to enhance the feature representation andinformation utilization capacities. Among this ensemble model, BPNN, IBPNN, and ELM are used as base-modelwhile LSSVR is the meta-model. Moreover, four-fold cross-validation is carried out in each base-models to en-hance the generalization performance of the model. Finally, the output of each base-model is new input for meta-model to acquire ultimate forecasting values. Case study of hourly PM2.5concentration forecasting in the Beijing-Tianjin-Hebei area during the winter substantiates that: (1) application of input selection methods is beneficial tosatisfactory forecasting results; (2) the forecasting performance of the Stacking-driven ensemble model is farbetter than any single models composing of it; (3) the proposed model can tackle highly complicated and ex-tremely high concentration PM2.5data, which is feasible to PM2.5concentration forecasting during the winter;(4) the proposed model with small forecasting error, strong generalization performance, as well robust fore-casting ability is potential in the early air warning systems.

🔖

Cite This Article

SUN, W., Lİ, Z. (2020). Hourly PM2.5concentration forecasting based on feature extraction andstacking-driven ensemble model for the winter of the Beijing-Tianjin-Hebeiarea. Atmospheric Pollution Research, Cilt: 11 - Sayı: 6, 110–121. https://ajindex.com/articles/153287

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (13)

  1. Almaraashi, M., 2018. Investigating the impact of feature selection on the prediction ofsolar radiation in different locations in Saudi Arabia. Appl. Soft Comput. 66,250–263.
  2. Anenberg, S.C., Schwartz, J., Shindell, D., Amann, M., Faluvegi, G., Klimont, Z.,Emberson, L., 2012. Global air quality and health co-benefits of mitigating near-termclimate change through methane and black carbon emission controls. Environ. HealthPerspect. 120 (6), 831–839.
  3. Bai, Y., Li, Y., Zeng, B., Li, C., Zhang, J., 2019a. Hourly PM2.5 concentration forecastusing stacked autoencoder model with emphasis on seasonality. J. Clean. Prod. 224,739–750.
  4. Bai, Y., Zeng, B., Li, C., Zhang, J., 2019b. An ensemble long short-term memory neuralnetwork for hourly PM2.5concentration forecasting. Chemosphere 222, 286–294.
  5. Bai, N., Khazaei, M., van Eeden, S.F., Laher, I., 2007. The pharmacology of particulatematter air pollution-induced cardiovascular dysfunction. Pharmacol. Ther. 113 (1),16–29.
  6. Bi, J., Huang, J., Hu, Z., Holben, B.N., Guo, Z., 2014. Investigating the aerosol optical andradiative characteristics of heavy haze episodes in Beijing during January of 2013. J.Geophys. Res. Atmos. 119 (16), 9884–9900.
  7. Cai, S., Wang, Y., Zhao, B., Wang, S., Chang, X., Hao, J., 2017. The impact of the“airpollution prevention and control action plan”on PM2.5concentrations in Jing-Jin-Jiregion during 2012–2020. Sci. Total Environ. 580, 197–209.
  8. Chen, Y., Ebenstein, A., Greenstone, M., Li, H., 2013. Evidence on the impact of sustainedexposure to air pollution on life expectancy from China's Huai River policy. Proc.Natl. Acad. Sci. Unit. States Am. 110 (32), 12936–12941.
  9. Dotse, S.Q., Petra, M.I., Dagar, L., De Silva, L.C., 2018. Application of computationalintelligence techniques to forecast daily PM10 exceedances in Brunei Darussalam.Atmos. Pollut. Res. 9 (2), 358–368.
  10. Drucker, H., Burges, C.J., Kaufman, L., Smola, A.J., Vapnik, V., 1997. Support vectorregression machines. In: Advances in Neural Information Processing Systems, pp.155–161 0262100657; 978-026210065-6.
  11. Feng, C., Cui, M., Hodge, B.M., Zhang, J., 2017. A data-driven multi-model methodologywith deep feature selection for short-term wind forecasting. Appl. Energy 190,1245–1257.
  12. Freeman, B.S., Taylor, G., Gharabaghi, B., Thé, J., 2018. Forecasting air quality timeseries using deep learning. J. Air Waste Manag. Assoc. 68 (8), 866–886.
  13. Ghadimi, N., Akbarimajd, A., Shayeghi, H., Abedinia, O., 2018. Two stage forecast enginewith feature selection techni