Using High-Frequency Information and RH to Estimate AQI Based on SVR

Surveillance-image-based outdoor air quality monitoring

Air pollution threatens human health, necessitating effective and convenient air quality monitoring. Recently, there has been a growing interest in using camera images for air quality estimation. However, a major challenge has been nighttime detection due to the limited visibility of nighttime images. Here we present a hybrid deep learning model, capitalizing on the temporal continuity of air quality changes for estimating outdoor air quality from surveillance images. Our model, which integrates a convolutional neural network (CNN) and long short-term memory (LSTM), adeptly captures spatial-temporal image features, enabling air quality estimation at any time of day, including PM2.5 and PM10 concentrations, as well as the air quality index (AQI). Compared to independent CNN networks that solely extract spatial features, our model demonstrates superior accuracy on self-constructed datasets with R2 = 0.94 and RMSE = 5.11 μg m-3 for PM2.5, R2 = 0.92 and RMSE = 7.30 μg m-3 for PM10, and R2 = 0.94 and RMSE = 5.38 for AQI. Furthermore, our model excels in daytime air quality estimation and enhances nighttime predictions, elevating overall accuracy. Validation across diverse image datasets and comparative analyses underscore the applicability and superiority of our model, reaffirming its applicability and superiority for air quality monitoring.

A PM2.5 concentration estimation method based on multi-feature combination of image patches

An efficient, accurate and high-resolution PM_2.5 monitoring approach is critical to pollution control and public health. Here we propose an image-based method for PM_2.5 concentration estimation. The method combines the image features with other influence factors to inference PM_2.5, and an improved patchwise strategy is used in the processes of regression and prediction. The experimental results of the Shanghai scene dataset show that our method achieved a higher estimation accuracy with 0.88 at R² and 10.42 μg⋅m^-3 at RMSE, compared to other methods; the addition of the influence factors, such as relative humidity and photographing month, improve the accuracy, while the improved patchwise strategy significantly enhanced the predictive performance. Moreover, the results of two datasets at different times and location further demonstrate the effectiveness and applicability of the proposed method.