IDEAS home Printed from https://ideas.repec.org/a/gam/jsusta/v13y2021i7p3726-d525013.html
   My bibliography  Save this article

Applying PCA to Deep Learning Forecasting Models for Predicting PM 2.5

Author

Listed:
  • Sang Won Choi

    (Department of Agricultural Economics and Rural Development, Seoul National University, Gwanak-ro 1, Gwanak-gu, Seoul 08826, Korea)

  • Brian H. S. Kim

    (Department of Agricultural Economics and Rural Development, Seoul National University, Gwanak-ro 1, Gwanak-gu, Seoul 08826, Korea
    Program in Agricultural and Forest Meteorology, Research Institute of Agriculture and Life Sciences, Seoul National University, 1 Gwanangno, Gwanak-gu, Seoul 08826, Korea)

Abstract

Fine particulate matter (PM 2.5 ) is one of the main air pollution problems that occur in major cities around the world. A country’s PM 2.5 can be affected not only by country factors but also by the neighboring country’s air quality factors. Therefore, forecasting PM 2.5 requires collecting data from outside the country as well as from within which is necessary for policies and plans. The data set of many variables with a relatively small number of observations can cause a dimensionality problem and limit the performance of the deep learning model. This study used daily data for five years in predicting PM 2.5 concentrations in eight Korean cities through deep learning models. PM 2.5 data of China were collected and used as input variables to solve the dimensionality problem using principal components analysis (PCA). The deep learning models used were a recurrent neural network (RNN), long short-term memory (LSTM), and bidirectional LSTM (BiLSTM). The performance of the models with and without PCA was compared using root-mean-square error (RMSE) and mean absolute error (MAE). As a result, the application of PCA in LSTM and BiLSTM, excluding the RNN, showed better performance: decreases of up to 16.6% and 33.3% in RMSE and MAE values. The results indicated that applying PCA in deep learning time series prediction can contribute to practical performance improvements, even with a small number of observations. It also provides a more accurate basis for the establishment of PM 2.5 reduction policy in the country.

Suggested Citation

  • Sang Won Choi & Brian H. S. Kim, 2021. "Applying PCA to Deep Learning Forecasting Models for Predicting PM 2.5," Sustainability, MDPI, vol. 13(7), pages 1-30, March.
  • Handle: RePEc:gam:jsusta:v:13:y:2021:i:7:p:3726-:d:525013
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2071-1050/13/7/3726/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2071-1050/13/7/3726/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Thanongsak Xayasouk & HwaMin Lee & Giyeol Lee, 2020. "Air Pollution Prediction Using Long Short-Term Memory (LSTM) and Deep Autoencoder (DAE) Models," Sustainability, MDPI, vol. 12(6), pages 1-17, March.
    2. Axel Gedeon Mengara Mengara & Younghak Kim & Younghwan Yoo & Jaehun Ahn, 2020. "Distributed Deep Features Extraction Model for Air Quality Forecasting," Sustainability, MDPI, vol. 12(19), pages 1-19, September.
    3. Judy A. Franklin, 2006. "Recurrent Neural Networks for Music Computation," INFORMS Journal on Computing, INFORMS, vol. 18(3), pages 321-338, August.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Irene Nandutu & Marcellin Atemkeng & Nokubonga Mgqatsa & Sakayo Toadoum Sari & Patrice Okouma & Rockefeller Rockefeller & Theophilus Ansah-Narh & Jean Louis Ebongue Kedieng Fendji & Franklin Tchakount, 2022. "Error Correction Based Deep Neural Networks for Modeling and Predicting South African Wildlife–Vehicle Collision Data," Mathematics, MDPI, vol. 10(21), pages 1-31, October.
    2. Paola Ortiz-Grisales & Julián Patiño-Murillo & Eduardo Duque-Grisales, 2021. "Comparative Study of Computational Models for Reducing Air Pollution through the Generation of Negative Ions," Sustainability, MDPI, vol. 13(13), pages 1-13, June.
    3. Jun Zhang & Shenghao Zhao & Chaonan Peng & Xianming Gong, 2022. "Spatial Heterogeneity of the Recovery of Road Traffic Volume from the Impact of COVID-19: Evidence from China," Sustainability, MDPI, vol. 14(21), pages 1-20, November.
    4. Yufei Fang & Zhiguang Shan, 2022. "How to Promote a Smart City Effectively? An Evaluation Model and Efficiency Analysis of Smart Cities in China," Sustainability, MDPI, vol. 14(11), pages 1-23, May.
    5. Longhui Fu & Qibang Wang & Jianhui Li & Huiran Jin & Zhen Zhen & Qingbin Wei, 2022. "Spatiotemporal Heterogeneity and the Key Influencing Factors of PM 2.5 and PM 10 in Heilongjiang, China from 2014 to 2018," IJERPH, MDPI, vol. 19(18), pages 1-20, September.
    6. Jie Zhao & Linjiang Yuan & Kun Sun & Han Huang & Panbo Guan & Ce Jia, 2022. "Forecasting Fine Particulate Matter Concentrations by In-Depth Learning Model According to Random Forest and Bilateral Long- and Short-Term Memory Neural Networks," Sustainability, MDPI, vol. 14(15), pages 1-18, August.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Chih‐Hsuan Wang & Chia‐Rong Chang, 2023. "Forecasting air quality index considering socioeconomic indicators and meteorological factors: A data granularity perspective," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 42(5), pages 1261-1274, August.
    2. Hossein Jalali & Farshid Keynia & Faezeh Amirteimoury & Azim Heydari, 2024. "A Short-Term Air Pollutant Concentration Forecasting Method Based on a Hybrid Neural Network and Metaheuristic Optimization Algorithms," Sustainability, MDPI, vol. 16(11), pages 1-17, June.
    3. Endah Kristiani & Hao Lin & Jwu-Rong Lin & Yen-Hsun Chuang & Chin-Yin Huang & Chao-Tung Yang, 2022. "Short-Term Prediction of PM 2.5 Using LSTM Deep Learning Methods," Sustainability, MDPI, vol. 14(4), pages 1-29, February.
    4. Xue-Bo Jin & Wen-Tao Gong & Jian-Lei Kong & Yu-Ting Bai & Ting-Li Su, 2022. "PFVAE: A Planar Flow-Based Variational Auto-Encoder Prediction Model for Time Series Data," Mathematics, MDPI, vol. 10(4), pages 1-17, February.
    5. Eric Hitimana & Gaurav Bajpai & Richard Musabe & Louis Sibomana & Jayavel Kayalvizhi, 2021. "Implementation of IoT Framework with Data Analysis Using Deep Learning Methods for Occupancy Prediction in a Building," Future Internet, MDPI, vol. 13(3), pages 1-19, March.
    6. Paulo S. G. de Mattos Neto & Manoel H. N. Marinho & Hugo Siqueira & Yara de Souza Tadano & Vivian Machado & Thiago Antonini Alves & João Fausto L. de Oliveira & Francisco Madeiro, 2020. "A Methodology to Increase the Accuracy of Particulate Matter Predictors Based on Time Decomposition," Sustainability, MDPI, vol. 12(18), pages 1-33, September.
    7. Abdullah H. Al-Nefaie & Theyazn H. H. Aldhyani, 2023. "Predicting CO 2 Emissions from Traffic Vehicles for Sustainable and Smart Environment Using a Deep Learning Model," Sustainability, MDPI, vol. 15(9), pages 1-21, May.
    8. Fatin Nadiah Yussof & Normah Maan & Mohd Nadzri Md Reba, 2021. "LSTM Networks to Improve the Prediction of Harmful Algal Blooms in the West Coast of Sabah," IJERPH, MDPI, vol. 18(14), pages 1-14, July.
    9. Axel Gedeon Mengara Mengara & Eunyoung Park & Jinho Jang & Younghwan Yoo, 2022. "Attention-Based Distributed Deep Learning Model for Air Quality Forecasting," Sustainability, MDPI, vol. 14(6), pages 1-34, March.
    10. Junyoung Jeong & Keuntae Cho, 2024. "Proposing Machine Learning Models Suitable for Predicting Open Data Utilization," Sustainability, MDPI, vol. 16(14), pages 1-23, July.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jsusta:v:13:y:2021:i:7:p:3726-:d:525013. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.