The research of traffic revitalization index can provide support for the formulation and adjustment of policies related to urban management, epidemic prevention and resumption of work and production. This paper proposes a deep model for the prediction of urban Traffic Revitalization Index (DeepTRI). The DeepTRI builds model for the data of COVID-19 epidemic and traffic revitalization index for major cities in China. The location information of 29 cities forms the topological structure of graph. The Spatial Convolution Layer proposed in this paper captures the spatial correlation features of the graph structure. The special Graph Data Fusion module distributes and fuses the two kinds of data according to different proportions to increase the trend of spatial correlation of the data. In order to reduce the complexity of the computational process, the Temporal Convolution Layer replaces the gated recursive mechanism of the traditional recurrent neural network with a multi-level residual structure. It uses the dilated convolution whose dilation factor changes according to convex function to control the dynamic change of the receptive field and uses causal convolution to fully mine the historical information of the data to optimize the ability of long-term prediction. The comparative experiments among DeepTRI and three baselines (traditional recurrent neural network, ordinary spatial–temporal model and graph spatial–temporal model) show the advantages of DeepTRI in the evaluation index and resolving two under-fitting problems (under-fitting of edge values and under-fitting of local peaks).

No abstract

Taxi flow forecast is significant for planning transportation and allocating basic transportation resources. The flow forecast in the urban adjacent area is different from the fixed-point flow forecast. Their data are more complex and diverse, which make them more challenging to forecast. This paper introduces a deep spatial–temporal forecast (DeepSTF) model for the flow forecasting of urban adjacent area, which divides the urban into grids and makes it have a graph structure. The model builds a spatial–temporal calculation block, which uses graph convolutional network to extract spatial correlation feature and uses two-layer temporal convolutional networks to extract time-dependent feature. Based on the theory of dilation convolution and causal convolution, the model overcomes the under-fitting phenomenon of other models when calculating with rapidly changing data. In order to improve the accuracy of prediction, we take weather as an implicit factor and let it participate in the feature calculation process. A comparison experiment is set between our model and the seven existing traffic flow forecast models. The experimental results prove that the model has better the capabilities of long-term traffic prediction and performs well in various evaluation indicators.

Inorganic hydrated salt phase change materials (PCMs) have the advantages of large latent heat, wide source range, and no poison, and they are widely used in the field of building energy conservation. In this study, sodium sulfate decahydrate (SSD) and sodium acetate trihydrate (SAT) were prepared into binary eutectic hydrated salt (EHS) by the melt blending method. The EHS was respectively impregnated into porous adsorption materials, such as attapulgite and expanded perlite, to prepare two shape-stabilized phase change materials (SSPCMs) by the vacuum impregnation method. The chemical structure, crystal phase, and combination mode of eutectic salts and SSPCMs were determined by Fourier transform infrared spectroscopy and X-ray diffraction techniques. The results show that there is no chemical reaction between porous adsorption materials and eutectic salt but a physical combination. Scanning electron microscopy results show that the eutectic is well-adsorbed in the porous structure of attapulgite or expanded perlite. Differential scanning calorimetry results show that, when the molar ratio of SSD/SAT is 0.71:0.29, the phase transition temperature of EHS is 28.5 °C and the phase transition enthalpy is 128.1 J/g. Borax (1.5 wt %) can effectively reduce the subcooling of binary EHS from 10.8 to 0.7 °C. Adding 25 wt % attapulgite can completely adsorb the PCMs; the phase change enthalpy is 92.1 J/g; and after 200 cycles, the enthalpy decreases by 24.6%. Encapsulated by polyurethane, the enthalpy value of SSPCMs only decreases by 10.4% after 200 thermal cycles, showing that the thermal stability is significantly improved.

Predicting the nature of each urban functional region based on the transfer rate of empty cars plays a crucial role in constructing smart cities and urban planning. The transfer rate of empty cars describes the probability of a taxi driving from one region to another without any passengers. It can reflect the main driving directions of taxies and the main flow directions of people among different urban functional regions. Although current researches have focused on the functional regions divided by remote sensing satellite images, there is almost no discussion on determining the nature of the region through taxi behaviour. The authors consider using taxi behaviour to classify urban functional regions. Besides, the attentional spatio-temporal model (Attentional Gated Recurrent Unit, AGRU) is introduced in the work. The AGRU consists of three modules, which are the spatial feature extraction module, the temporal feature extraction module, and the attentional pooling mechanism. The model has been evaluated on the data set provided by Didi Chuxing and it has been compared with some typical models. The experimental results show that the AGRU can reflect spatio-temporal information, and its attentional pooling mechanism can distinguish whether a region is the place of departure or the destination.