Next Article in Journal
Modeling Population Spatial-Temporal Distribution Using Taxis Origin and Destination Data
Previous Article in Journal
Normalized Difference Vegetation Index and Chlorophyll Content for Precision Nitrogen Management in Durum Wheat Cultivars under Semi-Arid Conditions
Article

Applying PCA to Deep Learning Forecasting Models for Predicting PM2.5

1
Department of Agricultural Economics and Rural Development, Seoul National University, Gwanak-ro 1, Gwanak-gu, Seoul 08826, Korea
2
Program in Agricultural and Forest Meteorology, Research Institute of Agriculture and Life Sciences, Seoul National University, 1 Gwanangno, Gwanak-gu, Seoul 08826, Korea
*
Author to whom correspondence should be addressed.
Academic Editor: Ali Elkamel
Sustainability 2021, 13(7), 3726; https://doi.org/10.3390/su13073726
Received: 5 March 2021 / Revised: 16 March 2021 / Accepted: 22 March 2021 / Published: 26 March 2021
(This article belongs to the Section Environmental Sustainability and Applications)
Fine particulate matter (PM2.5) is one of the main air pollution problems that occur in major cities around the world. A country’s PM2.5 can be affected not only by country factors but also by the neighboring country’s air quality factors. Therefore, forecasting PM2.5 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 PM2.5 concentrations in eight Korean cities through deep learning models. PM2.5 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 PM2.5 reduction policy in the country. View Full-Text
Keywords: principal components analysis (PCA); PM2.5; recurrent neural network RNN); long short-term memory (LSTM); bidirectional LSTM (BiLSTM); deep learning principal components analysis (PCA); PM2.5; recurrent neural network RNN); long short-term memory (LSTM); bidirectional LSTM (BiLSTM); deep learning
Show Figures

Figure 1

MDPI and ACS Style

Choi, S.W.; Kim, B.H.S. Applying PCA to Deep Learning Forecasting Models for Predicting PM2.5. Sustainability 2021, 13, 3726. https://doi.org/10.3390/su13073726

AMA Style

Choi SW, Kim BHS. Applying PCA to Deep Learning Forecasting Models for Predicting PM2.5. Sustainability. 2021; 13(7):3726. https://doi.org/10.3390/su13073726

Chicago/Turabian Style

Choi, Sang W., and Brian H.S. Kim 2021. "Applying PCA to Deep Learning Forecasting Models for Predicting PM2.5" Sustainability 13, no. 7: 3726. https://doi.org/10.3390/su13073726

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop