Air Particulate Matter (PM2.5) Concentration Prediction in Kuwait Using Vision Transformer

Globally, air pollution has become one of the most concerning problems that affect the quality of human life. In Kuwait, one of the most prominent air pollutants is particulate matter 2.5 (PM2.5), which is a mixture of many inhalable particles that can cause various health issues. Predicting PM2.5 concentration levels is crucial to start taking actions against this concerning problem. This study aims to develop a robust deep learning model to forecast PM2.5 future concentrations in Kuwait. Missing values in the time-series were handled by employing different data imputation techniques. Furthermore, dimensionality reduction was implemented on the imputed datasets using principal component analysis (PCA), reducing the number of features from 11 to 4. Each of the imputed datasets was presented in time domain, frequency domain, and as principal components. Two data visualization techniques were employed including line graph images and spectrograms. Images typically possess rich visual patterns, allowing for extracting valuable features and hence, enhancing forecasting results. These images were then fed to a hybrid model that consists of a vision transformer (ViT) and Bidirectional Long Short-Term Memory (BiLSTM), taking full advantage of both models. The results revealed outstanding performance of our model, achieving the lowest Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE) values of 0.0191, 0.0031, and 0.0562, respectively. To assess the generalizability of our model, it was tested against an open-source dataset collected in Northern Ireland. Evaluation results demonstrated reductions up to 97.8%, 99.7%, and 94.55% in MAE, MSE, and RMSE, when compared with previous work, respectively.
 

Supervisor: Prof. Imtiaz Ahmad
Convener: Dr. Sa'ed Abed
Examination Committee: Dr. Mahmoud Ben Naser