摘要
An efficient, accurate and high-resolution PM2.5 monitoring approach is critical to pollution control and public health. Here we propose an image-based method for PM2.5 concentration estimation. The method combines the image features with other influence factors to inference PM2.5, 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 R-2 and 10.42 mu g.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.
学科与关键词
- Densely connected convolutional networks with attention long short-term memory for estimating PM2.5 values from imagesZhang, Bo; Geng, Ziyao; Zhang, Hanwen; Pan, Jianguo*JOURNAL OF CLEANER PRODUCTION, 2022, 333: 130101.被引 8
- Prediction of PM2.5 concentration based on weighted bagging and image contrast-sensitive featuresQiao, Junfei; He, Zengzeng*; Du, ShengliStochastic Environmental Research and Risk Assessment, 2020, 34(3-4): 561-573.被引 14
- Predicting ground-level PM2.5 concentrations in the Beijing-Tianjin-Hebei region: A hybrid remote sensing and machine learning approachLi, Xintong; Zhang, Xiaodong*Environmental Pollution, 2019, 249: 735-749.被引 54
