|
Forecasting the PM-10 using a deep neural network |
|---|---|
| รหัสดีโอไอ | |
| Creator | 1. Chinawat Chairungrueang 2. Rati Wongsathan |
| Title | Forecasting the PM-10 using a deep neural network |
| Publisher | Research and Development Office,Prince of Songkla University |
| Publication Year | 2564 |
| Journal Title | Songklanakarin Journal of Science and Technology (SJST) |
| Journal Vol. | 43 |
| Journal No. | 3 |
| Page no. | 687-695 |
| Keyword | deep neural network, PM-10, genetic algorithm, dropout, machine learning |
| URL Website | https://rdo.psu.ac.th/sjstweb/ |
| ISSN | 0125-3395 |
| Abstract | The air pollutants related to PM-10 are increasingly adversely affecting people in upper Northern Thailand, especiallyduring the annual dry season. Due to the highly nonlinear dynamics of PM-10 contributed by various factors, in this study a deepneural network (DNN) has been implemented as a tool forecasting PM-10 for air quality alerts. In its design, the time lags of PM10 and significant meteorology conditions, as well as the well-correlated fire-hotspots as major PM-10 sources in this area, areincluded in the predictor set. The training hyperparameters were optimized automatically by a genetic algorithm, whereas theDNNโs parameters were fine-tuned using back-propagation algorithm. Besides, regularization based on a dropout technique wasemployed to prevent over-fitting. In testing the proposed DNN-based PM-10 forecasting model outperformed the others. For oneday ahead forecasting it provides a good up to 85% accuracy. |
