Corrigendum: Exploring the Spatial Heterogeneity of Residents' Marginal Willingness to Pay for Clean Air in Shanghai.

[This corrects the article DOI: 10.3389/fpubh.2021.791575.].

Impact Evaluation of Cyberattacks on Connected and Automated Vehicles in Mixed Traffic Flow and Its Resilient and Robust Control Strategy.

Connected and automated vehicles (CAVs) present significant potential for improving road safety and mitigating traffic congestion for the future mobility system. However, cooperative driving vehicles are more vulnerable to cyberattacks when communicating with each other, which will introduce a new threat to the transportation system. In order to guarantee safety aspects, it is also necessary to ensure a high level of information quality for CAV. To the best of our knowledge, this is the first investigation on the impacts of cyberattacks on CAV in mixed traffic (large vehicles, medium vehicles, and small vehicles) from the perspective of vehicle dynamics. The paper aims to explore the influence of cyberattacks on the evolution of CAV mixed traffic flow and propose a resilient and robust control strategy (RRCS) to alleviate the threat of cyberattacks. First, we propose a CAV mixed traffic car-following model considering cyberattacks based on the Intelligent Driver Model (IDM). Furthermore, a RRCS for cyberattacks is developed by setting the acceleration control switch and its impacts on the mixed traffic flow are explored in different cyberattack types. Finally, sensitivity analyses are conducted in different platoon compositions, vehicle distributions, and cyberattack intensities. The results show that the proposed RRCS of cyberattacks is robust and can resist the negative threats of cyberattacks on the CAV platoon, thereby providing a theoretical basis for restoring the stability and improving the safety of the CAV.

A novel Encoder-Decoder model based on read-first LSTM for air pollutant prediction.

Accurate air pollutant prediction allows effective environment management to reduce the impact of pollution and prevent pollution incidents. Existing studies of air pollutant prediction are mostly interdisciplinary involving environmental science and computer science where the problem is formulated as time series prediction. A prevalent recent approach to time series prediction is the Encoder-Decoder model, which is based on recurrent neural networks (RNN) such as long short-term memory (LSTM), and great potential has been demonstrated. An LSTM network relies on various gate units, but in most existing studies the correlation between gate units is ignored. This correlation is important for establishing the relationship of the random variables in a time series as the stronger is this correlation, the stronger is the relationship between the random variables. In this paper we propose an improved LSTM, named Read-first LSTM or RLSTM for short, which is a more powerful temporal feature extractor than RNN, LSTM and Gated Recurrent Unit (GRU). RLSTM has some useful properties: (1) enables better store and remember capabilities in longer time series and (2) overcomes the problem of dependency between gate units. Since RLSTM is good at long term feature extraction, it is expected to perform well in time series prediction. Therefore, we use RLSTM as the Encoder and LSTM as the Decoder to build an Encoder-Decoder model (EDSModel) for pollutant prediction in this paper. Our experimental results show, for 1 to 24 h prediction, the proposed prediction model performed well with a root mean square error of 30.218. The effectiveness and superiority of RLSTM and the prediction model have been demonstrated.

Exploring the Spatial Heterogeneity of Residents' Marginal Willingness to Pay for Clean Air in Shanghai.

Previous studies have paid little attention to the spatial heterogeneity of residents' marginal willingness to pay (MWTP) for clean air at a city level. To fill this gap, this study adopts a geographically weighted regression (GWR) model to quantify the spatial heterogeneity of residents' MWTP for clean air in Shanghai. First, Shanghai was divided into 218 census tracts and each tract was the smallest research unit. Then, the impacts of air pollutants and other built environment variables on housing prices were chosen to reflect residents' MWTP and a GWR model was used to analyze the spatial heterogeneity of the MWTP. Finally, the total losses caused by air pollutants in Shanghai were estimated from the perspective of housing market value. Empirical results show that air pollutants have a negative impact on housing prices. Using the marginal rate of transformation between housing prices and air pollutants, the results show Shanghai residents, on average, are willing to pay 50 and 99 Yuan/m2 to reduce the mean concentration of PM2.5 and NO2 by 1 µg/m3, respectively. Moreover, residents' MWTP for clean air is higher in the suburbs and lower in the city center. This study can help city policymakers formulate regional air management policies and provide support for the green and sustainable development of the real estate market in China.