A Novel Deep Learning Model for Subway PM _2.5 Prediction Using Neighborhood Component Analysis and Convolutional Latent Variables

The accurate prediction of PM<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</sub> concentrations in indoor environments is vital for public health and environmental protection, given the significant risks posed by poor indoor air quality. This study proposes a novel approach using the benefits of deep learning and metric learning for forecasting PM<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</sub> concentrations. Our method integrates a 2-dimensional convolutional neural network, a latent variables model, and neighborhood component analysis, collectively forming the convolution latent variable-neighborhood component analysis (CLV-NCA) model. The 2-dimensional convolutional neural network extracts spatiotemporal features from the data, while the latent variables model reduces the model’s computational complexity by compressing these features. The neighborhood component analysis further enhances the model’s robustness, allowing it to adapt to the characteristics of various indoor environments and the complex nature of PM<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</sub> data. The effectiveness of the CLV-NCA model is validated using indoor air quality data, demonstrating significant improvements over conventional models. Compared with the traditional linear partial least squares 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 indoor air quality monitoring, providing a robust and efficient tool for PM<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</sub> prediction.