Applications In Urban Studies Research Articles

Content-location relationships: a framework to explore correlations between space-based and place-based user-generated content

The use of social media and location-based networks through GPS-enabled devices provides geospatial data for a plethora of applications in urban studies. However, the extent to which information found in geo-tagged social media activity corresponds to the spatial context is still a topic of debate. In this article, we developed a framework aimed at retrieving the thematic and spatial relationships between content originated from space-based (Twitter) and place-based (Google Places and OSM) sources of geographic user-generated content based on topics identified by the embedding-based BERTopic model. The contribution of the framework lies on the combination of methods that were selected to improve previous works focused on content-location relationships. Using the city of Lisbon (Portugal) to test our methodology, we first applied the embedding-based topic model to aggregated textual data coming from each source. Results of the analysis evidenced the complexity of content-location relationships, which are mostly based on thematic profiles. Nonetheless, the framework can be employed in other cities and extended with other metrics to enrich the research aimed at exploring the correlation between online discourse and geography.

Advances and Review of Machine Learning Applications in Urban Studies from 2005 to 2020

Machine learning, as a new method for data mining and problem prediction, has been widely used in various fields of urban studies in recent years, which requires a periodical summary of relevant literature. Start with data types, selection and preprocessing, this paper introduces the characteristics and applicability of various machine learning algorithms, and analyzes the cross-fields, hot spots, frontiers and trends of machine learning and urban studies from 2005 to 2020 by using Citespace. Second, focusing on the application of supervised machine learning algorithms from relevant literature in the past five years, a review is made from four main aspects including urban traffic, urban ecology, physical geography, human geography, and the tentative explorations of unsupervised learning, semi-supervised learning and reinforcement learning method in urban studies are unscrambled as well. Finally, the advantages of machine learning methods are summarized, and it􀆳s proposed that the application potential of various machine learning methods in multiple fields and perspectives of urban research should be explored in the future, and the cutting-edge trend of efficient combination of intelligent technology and methods with urban research should be grasped.

From policy to institution: Implementing land reform in Dar es Salaam’s unplanned settlements

Tanzania led the wave of land reform in sub-Saharan Africa, promoting ‘institutional fixes’ of property rights to stimulate urban development and poverty alleviation. Since 2005, the Residential Licence programme has offered short-term leases to around 180,000 households in the unplanned settlements of Dar es Salaam. However, the rate of title acquisition has been moderate to low, as in much of urban Africa. To understand the demand for land titles, this paper adopts an institutional approach and a novel analytic framework examining social expectations around the Residential Licence and their effects on choices of formalisation. Primary data was collected through a two-round survey with 1363 and 243 respondents, respectively. The paper finds that landholders have conditional preferences for formalisation based on the behaviour of their neighbours and the advice of other landholders, local leaders and higher-level government. Interactions between state and non-state actors generate social expectations that compliance with the programme is low and the government is not committed to enforcing interim property rights. These beliefs discourage choices of formalisation and transform the Residential Licence into an ‘empty’ institution, which fails to embed in social practice. The study contributes to the literature on land tenure formalisation by examining the interaction of state and social forces in the implementation of land reform and by proposing a complex understanding of the demand for tenure formalisation, underpinned by collective choice considerations. Additionally, the paper offers a methodological contribution by adopting a novel method for institutional analysis with further potential applications in urban studies and geographic research.

ACCESSIBILITY IN TRANSPORTATION AND LAND USE PLANNING

Accessibility represents a measurement of the spatial distribution of opportunities attended by a transportation system. This study aims to assess the state of knowledge of accessibility by identifying its main applications in urban studies. In this regard, we conducted a Systematic Literature Review (SLR) along with a bibliometric analysis and identified 10 themes of study arranged according to the intrinsic characteristics of 120 selected publications from the last two decades. The data extraction and synthesis allowed us to relate 82 publications into 19 applications in urban studies of accessibility measures. The results showed the flexibility and potential of using accessibility measures as an evaluation and decision-making tool for urban studies, especially in promoting equity and socioeconomic territory justice. The study pointed out the raising of new themes related to aspects of urban land use, equity, quality of life, and transit systems. The availability and quality of data are the main factors in selecting variables. It is expected that future researches could explore contributions provided by the advancement of ICTs, especially in the Global South.

Refining trip starting and ending locations when estimating travel-demand at large urban scale

Demand estimation is an important step for multiple applications in urban studies. However, the level of accuracy required depends on the objective of the study. In dynamic traffic microsimulation, the estimation of demand needs to be accurate, as it is intended to describe individuals' trips on a very small-scale. In this case, poor estimation of trip initiation, path, and endings could result in the wrong estimation of the city-block scale's traffic state. Estimating demand at a large-scale with high-resolution is not only very challenging because it requires a large volume of data from multiple sources, but the underlying mathematical problem is considerable and thus hard to solve.In this paper, we address the issue of trip starts and ends when modeling large perimeters. We propose to enhance the location of trip initiation and termination by merging heterogeneous and large public datasets. To do so, we develop a series of algorithms that identify fine-mesh areas where trips could reliably start or end and we share the estimated demand within these sub-areas, following the distribution of trip purposes (Home, Work, Shop, etc.).The method is deployed in Lyon city, France, and validated on an extraction of it. Micro-simulation results show that the demand, once accurately distributed, changes the overall network's performance, confirming the significant influence of trip endings and starts on the overall traffic dynamics.

Study of Hourly Variability of Association between Land Use Parameters and CO-Pollutant Using LUR Model in Tehran

The models of the association between land use and air pollution have wide applications in urban studies, but the land-use role and its different parameters effective on the variability of air pollution concentration in various hours can be used for more accurate Spatio-temporal prediction of pollution. In this study, to make Spatio-temporal prediction of CO pollutants using hourly land-use regression (LUR), the effective parameters on Spatio-temporal variation of this pollutant are investigated during the day and night. The hourly data are collected from 21 air pollution monitoring stations for the summer in Tehran and the predictive parameters including density and distance from different variables such as road network, vegetation, elevation, and different land-use are generated in the geographic information system (GIS). A general model and 8 hourly models are created at 3 am, 6 am, 9 am, 12 noon, 3 pm, 6 pm and 12 midnight. The coefficient of determination (R2) of the created model is equal to 0.7898, and it shows that the model has an outstanding performance. By analyzing the generated hourly models, because of the differences in the parameters used in these models, it is denoted that both temporal variability and spatial variability play effective roles in forming the models during the day and night. The coefficient of determination (R2) of the hourly models ranges from 0.51 to 0.92 in which the lowest one and the highest one are related to the noon hours’ models and the nocturnal hours’ models, respectively. The parameters including local access roads and official/commercial areas have the most effect on increasing CO pollutants during the day and night, and the parameters including green space, sports, and medical centers lead to the locations with lower CO pollutants concentration.

Development of ‘3D City Models’ using IRS Satellite Data

Urban models are computer-based solutions used for testing theories about spatial location and interaction between land uses and related activities. They also provide digital environments for testing the consequences of physical planning policies on the future form of cities. Earlier, 3D city models were prepared using stereo aerial photography, topographic data and conventional surveying. The geospatial information was extracted using either visual or digital classification techniques. Presently the 3D city models is prepared with the help of ALTM data along with very high resolution imagery, which is costly and time consuming. As alternatives, Cartosat-1 stereo data of the order of 2.5 m resolution, it becomes more practical and economical to generate digital surface model (DSM) with an accuracy of 4 m. Cartosat-II data with 1 m resolution fused with LISS-IV data give high resolution images for building footprint extraction. The availability of high resolution Cartosat-I stereo satellite data assists urban planners and municipal authorities to create a model and visualize the urban space in three dimensions. 3D visualization models have a variety of applications in urban studies. The studies includes urban morphological mapping, disaster management, updation, virtual reality and generation of fly through etc. The primary interest of the planners is not limited towards the extraction of urban features from satellite data. Planners also have interest in creation of 3D models of buildings and terrain surface for detailed urban planning. Therefore, to develop 3D city models 2.5 m Cartosat-1 stereo data fused with 1 m merged product of Cartosat-II and LISS-IV to create DSM and building footprints respectively. Keeping the significance of use of stereo satellite data, an attempt has been made to generate a 3D building model for Ahmedabad and Hyderabad cities. The 3D building model generated by employing geoinformatics techniques with Level of Details (LOD-1). The primary aim of this study was to develop geoinformatics techniques for the extraction of urban features based on object oriented classification techniques with level of details 1 (LOD-1) using photogrammetric DEM. This paper discusses all these techniques and their usefulness in 3D city modeling exercises.