An adaptive adjacency matrix-based graph convolutional recurrent network for air quality prediction.

In recent years, air pollution has become increasingly serious and poses a great threat to human health. Timely and accurate air quality prediction is crucial for air pollution early warning and control. Although data-driven air quality prediction methods are promising, there are still challenges in studying spatial-temporal correlations of air pollutants to design effective predictors. To address this issue, a novel model called adaptive adjacency matrix-based graph convolutional recurrent network (AAMGCRN) is proposed in this study. The model inputs Point of Interest (POI) data and meteorological data into a fully connected neural network to learn the weights of the adjacency matrix thereby constructing the self-ringing adjacency matrix and passes the pollutant data with this matrix as input to the Graph Convolutional Network (GCN) unit. Then, the GCN unit is embedded into LSTM units to learn spatio-temporal dependencies. Furthermore, temporal features are extracted using Long Short-Term Memory network (LSTM). Finally, the outputs of these two components are merged and air quality predictions are generated through a hidden layer. To evaluate the performance of the model, we conducted multi-step predictions for the hourly concentration of PM2.5, PM10 and O3 at Fangshan, Tiantan and Dongsi monitoring stations in Beijing. The experimental results show that our method achieves better predicted effects compared with other baseline models based on deep learning. In general, we designed a novel air quality prediction method and effectively addressed the shortcomings of existing studies in learning the spatio-temporal correlations of air pollutants. This method can provide more accurate air quality predictions and is expected to provide support for public health protection and government environmental decision-making.

Effects of Lime Powder on the Properties of Portland Cement-Sulphoaluminate Cement Composite System at Low Temperature.

In order to reduce the risk of early freezing damage to cement-based materials in winter construction, lime powder was used to improve the properties of the Portland cement-sulphoaluminate cement (PC-CSA) composite system at low temperatures. In this study, the effects of lime powder dosage on the properties of a PC-CSA blended system with two proportions (PC:CSA = 9:1 and 7:3) at -10 °C were investigated, and the mechanisms of improvement were revealed. The results showed that the compressive strength of the PC-CSA composite system was effectively improved, and the setting time was shortened by the addition of lime powder. Lime powder could effectively act as an early heating source in the PC-CSA composite system, as the maximum temperature of samples exposed to sub-zero temperatures was increased and the time before dropping to 0 °C was prolonged by the addition of lime powder. The extra CH generated by the hydration of lime powder provided an added hydration path for C4A3S¯, which accelerated the formation of AFt at each stage. Frozen water as well as the early frost damage were effectively decreased by lime powder because of the faster consumption of free water at an early stage. The modification of the hydration products also contributed to the denseness of the microstructure.