A Novel Deep Learning Model for Subway PM2.5 Prediction Using Neighborhood Component Analysis and Convolutional Latent Variables

The accurate prediction of PM2.5 concentrations in indoor environments is vital for public health and environmental protection, given the significant risks posed by poor indoor air quality (IAQ). This study proposes a novel approach using the benefits of deep learning and metric learning for forecasting PM2.5 concentrations. Our method integrates a 2-D convolutional neural network (CNN), a latent variables model, and neighborhood component analysis (NCA), collectively forming the convolution latent variable-NCA (CLV-NCA) model. The 2-D CNN extracts spatiotemporal features from the data, while the latent variables model reduces the model’s computational complexity by compressing these features. The NCA further enhances the model’s robustness, allowing it to adapt to the characteristics of various indoor environments and the complex nature of PM2.5 data. The effectiveness of the CLV-NCA model is validated using IAQ data, demonstrating significant improvements over conventional models. Compared with the traditional linear partial least squares (PLSs) model, the proposed CLV-NCA model demonstrates approximately twice the accuracy, resulting in a 51.50% reduction in prediction error. This research contributes to the advancement of soft measurement modeling in IAQ monitoring, providing a robust and efficient tool for PM2.5 prediction.