Loading...
Please wait, while we are loading the content...
Similar Documents
Applying PCA to Deep Learning Forecasting Models for Predicting $PM_{2.5}$
| Content Provider | MDPI |
|---|---|
| Author | Choi, Sang Kim, Brian |
| Copyright Year | 2021 |
| Description | 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. |
| Starting Page | 3726 |
| e-ISSN | 20711050 |
| DOI | 10.3390/su13073726 |
| Journal | Sustainability |
| Issue Number | 7 |
| Volume Number | 13 |
| Language | English |
| Publisher | MDPI |
| Publisher Date | 2021-03-26 |
| Access Restriction | Open |
| Subject Keyword | Sustainability Characterization and Testing of Materials Principal Components Analysis (pca) Pm2.5 Recurrent Neural Network Rnn) Long Short-term Memory (lstm) Bidirectional Lstm (bilstm) Deep Learning |
| Content Type | Text |
| Resource Type | Article |
