Accessibility is the ease of reaching opportunities (goods, services, activities, and destinations). Accessibility of desirable locations such as households and commercial locations, is typically scaffolded by land use patterns and transportation infrastructure. It can reflect people’s travel convenience, cities’ viability, sustainability, and mitigate the negative effects on the environment and public safety. Consequently, it is recognized as a fundamental principle in urban sustainable development policies worldwide. In the literature, most of the studies have used a static or partially dynamic approach with a single mode such as a car or public transportation by using conventional models. These “static” models assume that household locations are static and that transportation supply and opportunities for social practice activities are fixed in time and space, which can lead to biased or even misleading assumptions in accessibility models. Therefore, the aim of this study is to evaluate the impact of dynamic spatial accessibility through Mode-Dependent Accessibility (MDA) on the location choice behaviors of urban activities such as households and commercialin the City of Wuhan, China. This study employed the Mode-Dependent Travel Demand Model (M-TDM) to measure the impact of short-term MDA on household and commercial activities for the years 2012 and 2015. Additionally, an integrated spatial economic (ISE) model such as PECAS (Production, Exchange, Consumption, Allocation, System) in order to investigate location preferences of urban activities over space and time. Regarding household and commercial location choice, the ISE modeling results revealed that households and commercial activities are sensitive to MDA, especially using transit. The ISE method predicted that the R² for household and commercial location choice models was 0.84 to 0.90 for transit-based accessibility, whereas the R² for logsum-based static models was 0.48 to 0.72. In addition, their findings suggest that highly accessible locations that are well served by auto are more appealing for household and commercial activities. The findings of this study will help urban planners, transportation planners, and policymakers take into account the dynamic nature of short-term MDA when zoning and allocating urban activities and public amenities, instead of using static accessibility.

In recent years, accessibility has been considered a vital policy objective in the development of a sustainable transportation system. Accessibility can make a significant contribution to quality of life. The accessibility of desirable locations, such as households and commercial locations, is usually underpinned by land use patterns and transportation infrastructure. The accessibility of different activities is largely determined by the spatial distribution of activities and associated transport networks in a metropolitan area. In order to examine how location choice behaviors of urban activities influence urban forms and land use patterns, accessibility has been used extensively to consider the impact of both the spatial distribution of opportunities (e.g., employment or services) and the transport cost of reaching them. However, in most cases, only those static/aggregate accessibility terms that are represented by the “logsum” of all available transport modes have traditionally been used in urban transport planning and modeling analysis. In this study, according to urban activities, several Integrated Spatial Economic (ISE) models i.e., PECAS (Production, Exchange, Consumption, Allocation, System) models were developed to study the relationship between dynamic, Time-Dependent Accessibility (TDA) and the location choice behavior of urban activities in the City of Wuhan, China. The developed models were then used as tools to investigate the impact of dynamic/disaggregate short-term TDA on location choice behaviors of various urban activities such as households and commercial. Regarding the household location choice, the ISE modeling results revealed that urban households living in the downtown area of the City of Wuhan were sensitive to TDA to employment centers, especially during the morning peak time. In addition, commercial services prefer locations that offer a high level of accessibility during off-peak times. Based on the results of this study, it is recommended that planning exercises, such as the development of zoning and the allocation of urban activities and public facilities, pay more attention to dynamic, short-term TDA, which is essential for urban sectors to carry out daily activities, than their static, composite accessibility counterparts.

Anomalous urban mobility pattern refers to abnormal human mobility flow in a city. Anomalous urban mobility pattern detection is important in the study of urban mobility. In this paper, a framework is proposed to identify anomalous urban mobility patterns based on taxi GPS trajectories and Point of Interest (POI) data. In the framework, functional regions are first generated based on the distribution of POIs by the DBSCAN clustering algorithm. A Weighted Term Frequency-Inverse Document Frequency (WTF-IDF) method is proposed to identify function values in each region. Then, the Origin-Destination (OD) of trips between functional regions is extracted from GPS trajectories to detect anomalous urban mobility patterns. Mobility vectors are established for each time interval based on the OD of trips and are classified into clusters by the mean shift algorithm. Abnormal urban mobility patterns are identified by processing the mobility vectors. A case study in the city of Wuhan, China, is conducted; the experimental results show that the proposed method can effectively identify daily and hourly anomalous urban mobility patterns.

The interactive relationship between transportation and land use has become more difficult to understand and predict, due to the economic boom and corresponding fast-paced proliferation of private transportation and land-development activities. A lack of coordination between transportation and land-use planning has created an imbalanced provision of transportation infrastructure and land-use patterns; this is indicated by places where a high-density land-development pattern is supported by a low-capacity transport system or vice versa. With this, literature suggests that Mixed Land-Use (MLU) developments have the potential to provide relevant solutions for urban sustainability, smart growth, inclusive public transit use, and efficient land-use. Therefore, this study employed deep neural network models—Long Short-Term Memory (LSTM), and Multilayer Perceptron (MLP)—for forecasting the effect of transportation supply on the MLU pattern at the parcel level in the Jiang’an District, Wuhan, China. The findings revealed a strong relationship between the supply of public transportation and MLU. Moreover, the study results indicated that MLU is widely available in areas with high accessibility, high density, and proximity to the city center. The forecasting results from the MLP and LSTM models showed an average error of 5.55–7.36% and 3.62–4.28% for mixed use, respectively, while most of their 90th percentile errors were less than 13.73% and 10.46% for mixed use, respectively. The proposed models and the findings from this study should be useful for stakeholders and policy makers for more precise forecasting of MLU at the urban level.

Activity-based travel demand modeling (ABTDM) has often been viewed as an advanced approach, due to its higher fidelity and better policy sensitivity. However, a review of the literature indicates that no study has been undertaken to investigate quantitatively the differences and accuracy between an ABTDM approach and a traditional four-step travel demand model. In this paper we provide a comparative analysis against each step – trip generation, trip distribution, mode split, and network assignment – between an ABTDM developed using travel diary data from the Tampa Bay Region in Florida and the Tampa Bay Regional Planning Model (TBRPM), an existing traditional four-step model for the same area. Results show salient differences between the TBRPM and the ABTDM, in terms of modeling performance and accuracy, in each of the four steps. For example, trip production rates calculated from the travel diary data are found to be either double or a quarter less than those used in the TBRPM. On the other hand, trip attraction rates computed from activity-based travel simulations are found to be either more than double or one tenth less than those used in the TBRPM. The trip distribution curves from the two models are similar, but both average and peak trip lengths of the two are significantly different. Mode split analyses show that the TBRPM may underestimate driving trips and fail to capture any usage of alternative modes, such as taxi and nonmotorized (e.g., walking and bicycling) modes. In addition, the ABTDMs are found to be less capable of reproducing observed traffic counts when compared to the TBRPM, most likely due to not considering external and through trips. The comparative results presented can help transportation engineers and planners better understand the strengths and weaknesses of the two types of model and this should assist decision-makers in choosing a better modeling tool for their planning initiatives.

Wind energy is widely distributed in China as a renewable energy source. Aiming to alleviate the issues resulting from fossil fuel consumption faced by developing and developed countries (e.g., climate change) and to meet development needs, this study innovatively proposed methods for the location selection of wind farms and wind turbines in port areas based on the fuzzy comprehensive evaluation method. Considering that the wind turbine location is crucial to wind power generation, this paper focuses on locating wind turbines within a specific set of sea ports. The primary objectives of this paper are to evaluate the potential of wind power generation under different port scenarios and develop a method for assessing the potential of wind energy resources in wind farm areas. Firstly, a method is proposed for identifying the boundaries of wind farms in the port areas and locating wind turbines at sea ports. Furthermore, this study used the National Aeronautics and Space Administration (NASA) wind speed database to test the proposed method with the real-world wind power projects of the Ports of Tianjin, Shanghai, Xiamen, Shenzhen, and Hainan, which are top ports within five major coastal port clusters in China. It is found that the potential power generation capacity of the wind power farms at the above ports is 30.71 GWh, 19.82 GWh, 16.72 GWh, 29.45 GWh, and 24.42 GWh, respectively. Additionally, sensitive results for different types of wind turbines are conducted in the following experiment. The results of this study are fundamental for enriching the research of evaluating wind energy resources of sea ports and promoting the development and use of clean energy in practical environments. Further, the method proposed in this study is essential for optimizing the location and construction of wind turbines, which may help ports in adopting a low-carbon and green development path, thereby mitigating air pollution, and promoting sustainable development.