Stacked ResNet-LSTM and CORAL model for multi-site air quality prediction

Abstract

As the global economy is booming, and the industrialization and urbanization are being expedited, particulate matter 2.5 (PM2.5) turns out to be a major air pollutant jeopardizing public health. Numerous researchers are committed to employing various methods to address the problem of the nonlinear correlation between PM2.5 concentration and several factors to achieve more effective forecasting. However, a considerable space remains for the improvement of forecasting accuracy, and the problem of missing air pollution data on certain target areas also needs to be solved. Our research work is divided into two parts. First, this study presents a novel stacked ResNet-LSTM model to enhance prediction accuracy for PM2.5 concentration level forecast. As revealed from the experimental results, the proposed model outperforms other models such as boosting algorithms or general recurrent neural networks, and the advantage of feature extraction through residual network (ResNet) combined with a model stacking strategy is shown. Second, to solve the problem of insufficient air quality and meteorological data on some research areas, this study proposes the use of a correlation alignment (CORAL) method to carry out a prediction on the target area by aligning the second-order statistics between source area and target area. As indicated from the results, this model exhibits a considerable accuracy even in the absence of historical PM2.5 data in the target forecast area.

Deep-learning architecture for PM2.5 concentration prediction: A review

“…[ 118 ] 2022 Yangtze River Delta Region, China ResNet-LSTM H/S/T+1 5.47 3.89 - - Cheng et al. [ 119 ] 2022 Beijing, China SResCNN-LSTM D/S/T+5 40.67 23.74 - 0.80 Zhao et al. [ 120 ] 2019 Beijing/Tianjin, China STCNN-LSTM H/S/T+6 19.36 15.53 26.00 0.70 Qi et al.…”

“…Cheng et al. [ 119 ] proposed a fixed ResNet-LSTM that was designed to consider the spatial and temporal correlation of air quality data. Zhao et al.…”

Research on Fault Detection by Flow Sequence for Industrial Internet of Things in Sewage Treatment Plant Case

“…Figure 2 shows the network structure of the NFPBUL. and labelled the collection 𝐶 𝑙 [24]. After the training was completed, the NFPBUL module was used for the prediction purpose.…”

“…When the difference is below the threshold ε, several faults are predicted to occur, such as sensor disconnection, remote I/O module offline, etc., and the value of the network flow is set to −1. The calculation function of encoding is expressed in Equation ( 8 We trained the NFPBUL model with the data from the subsequence collection C d and labelled the collection C l [24]. After the training was completed, the NFPBUL module was used for the prediction purpose.…”

Research on Fault Detection by Flow Sequence Algorithm with Deep Learning Model for Industrial Internet of Things

“…Figure 2 shows the network structure of the NFPBUL. The NFPBUL model is trained by the subsequence set 𝐶 𝑑 and label set 𝐶 𝑙 [18]. The calculation formula for network flow prediction is shown as follows: , ()…”