Dr Ziqi Li

2025

1. Where England’s cities are growing: Evidence from big building footprint data and explainable AI

   Xinyi Yuan, Ziqi Li, Anahid Basiri, and 1 more author

   Habitat International, Sep 2025

   Abs

   Urban development is shaped by demographic and socio-economic factors, while simultaneously influencing these dynamics. Understanding these complex relationships is essential for informed urban planning, yet previous research has struggled with fine-scale analysis over large areas due to data and methodological limitations. This study overcomes these challenges by leveraging high-resolution building footprint data and eXplainable AI (XAI). Focusing on England between 2017 and 2023, we first quantify and map the extent of new urban development and further model it as a function of population density, ethnic composition, and the Index of Multiple Deprivation (IMD) using machine-learning algorithms. We then interpret the best-performing model with SHAP values and reveal a substantial nonlinear correlation between these demographic and socio-economic factors and new urban development. This analytical framework offers a novel, scalable, interpretable approach to fine-grained urban analysis, and, for the first time, provides a nationwide quantitative assessment of how population density, ethnic composition, and deprivation jointly shape urban development in England, thereby supporting evidence-based and equitable planning and policymaking.

2. Exploring a diagnostic test for missingness at random

   Dominick Sutton, Anahid Basiri, and Ziqi Li

   Mathematics, May 2025

   Abs

   Missing data remain a challenge for researchers and decision-makers due to their impact on analytical accuracy and uncertainty estimation. Many studies on missing data are based on randomness, but randomness itself is problematic. This makes it difficult to identify missing data mechanisms and affects how effectively the missing data impacts can be minimized. The purpose of this paper is to examine a potentially simple test to diagnose whether the missing data are missing at random. Such a test is developed using an extended taxonomy of missing data mechanisms. A key aspect of the approach is the use of single mean imputation for handling missing data in the test development dataset. Changing this to random imputation from the same underlying distribution, however, has a negative impact on the diagnosis. This is aggravated by the possibility of high inter-variable correlation, confounding, and mixed missing data mechanisms. The verification step uses data from a high-quality real-world dataset and finds some evidence-in one case-that the data may be missing at random, but this is less persuasive in the second case. Confidence in these results, however, is limited by the potential influence of correlation, confounding, and mixed missingness. This paper concludes with a discussion of the test’s merits and finds that sufficient uncertainties remain to render it unreliable, even if the initial results appear promising.

3. Construction enthusiasts versus demolition giants: insights from building footprint data in England

   Xinyi Yuan, Ziqi Li, Ana Basiri, and 1 more author

   Environment and Planning B: Urban Analytics and City Science, Jan 2025

   Abs

   This study uses building footprint data from the Ordnance Survey MasterMap to analyze construction and demolition activities across England from 2017 to 2023. By comparing the Topographic Object Identifiers (TOIDs) of each building between years, we identified newly constructed and demolished buildings, quantified changes, and used the bivariate color maps to visualize spatial patterns across England and within its five major cities. The study highlights the effectiveness of building footprint data in providing insights into urban changes and development trajectories, which are vital for urban planners and policymakers to understand dynamic urban processes and inform decision-making toward sustainable urban development.

2023

1. Scalable 3D mapping of cities using computer vision and signals of opportunity

   Anahid Basiri, Terence Lines, and Miguel Fidel Pereira

   International Journal of Geographical Information Science, Jul 2023

   Abs

   Three-dimensional (3D) maps are used extensively in a variety of applications, from air and noise pollution modelling to location-based services such as 3D mapping-aided Global Navigation Satellite Systems (GNSS), and positioning and navigation for emergency service personnel, unmanned aerial vehicles and autonomous vehicles. However, the financial cost associated with creating and updating 3D maps using the current state-of-the-art methods such as laser scanning and aerial photogrammetry are prohibitively expensive. To overcome this, researchers have proposed using GNSS signals to create 3D maps. This paper advances that family of methods by proposing and implementing a novel technique that avoids the difficult step of directly classifying GNSS signals into line-of-sight and non-line-of-sight classes by utilising edge detection techniques adapted from computer vision. This prevents classification biases and increases the range of environments in which GNSS-based 3D mapping methods can be accurately deployed. Being based on the patterns of blockage and attenuation of GNSS signals that are freely and globally available to receive by many mobile phones, makes the proposed technique a free, scalable and accessible solution. This paper also identifies some key indicators affecting data collection scalability and efficiency of the 3D mapping solution.

2021

1. 3D map creation using crowdsourced GNSS data

   Terence Lines, and Anahid Basiri

   Computers, Environment and Urban Systems, Sep 2021

   Abs

   3D maps are increasingly useful for many applications such as drone navigation, emergency services, and urban planning. However, creating 3D maps and keeping them up-to-date using existing technologies, such as laser scanners, is expensive. This paper proposes and implements a novel approach to generate 2.5D (otherwise known as 3D level-of-detail (LOD) 1) maps for free using Global Navigation Satellite Systems (GNSS) signals, which are globally available and are blocked only by obstacles between the satellites and the receivers. This enables us to find the patterns of GNSS signal availability and create 3D maps. The paper applies algorithms to GNSS signal strength patterns based on a boot-strapped technique that iteratively trains the signal classifiers while generating the map. Results of the proposed technique demonstrate the ability to create 3D maps using automatically processed GNSS data. The results show that the third dimension, i.e. height of the buildings, can be estimated with below 5 metre accuracy, which is the benchmark recommended by the CityGML standard.

2. Identifying urban functional areas and their dynamic changes in Beijing: using multiyear transit smart card data

   Zijia Wang, Haixu Liu, Yadi Zhu, and 5 more authors

   Journal of Urban Planning and Development, Jun 2021

   Abs

   A growing number of megacities have been experiencing changes to their landscape due to rapid urbanization trajectories and travel behavior dynamics. Therefore, it is of great significance to investigate the distribution and evolution of a city’s urban functional areas over different periods of time. Although the smart card automated fare collection system is already widely used, few studies have used smart card data to infer information about changes in urban functional areas, particularly in developing countries. Thus, this research aims to delineate the dynamic changes that have occurred in urban functional areas based on passengers’ travel patterns, using Beijing as a case study. We established a Bayesian framework and applied a Gaussian mixture model derived from transit smart card data in order to gain insight into passengers’ travel patterns at station level and then identify the dynamic changes in their corresponding urban functional areas. Our results show that Beijing can be clustered into five different functional areas based on the analysis of corresponding transit station functions: multimodal interchange hub and leisure area; residential area; employment area; mixed but mainly residential area; and mixed residential and employment area. In addition, we found that urban functional areas have experienced slight changes between 2014 and 2017. The findings can be used to inform urban planning strategies designed to tackle urban spatial structure issues, as well as guiding future policy evaluation of urban landscape pattern use.

2019

1. Simulating and Modeling the Signal Attenuation of Wireless Local Area Network for Indoor Positioning

   Terence Lines, and Anahid Basiri

   Nov 2019

   Abs

   Location is a key filter for mobile services, including navigation or advertising. However, positioning and localization inside buildings and in indoor spaces, where users spend most of their time and where the signals of the most widely-used positioning system, i.e. Global Navigation Satellite Systems such as GPS (Global Positioning System), are not available, can be challenging. In this regard, Wireless Local Area Networks (WLAN), e.g. Wi-Fi, can be used for positioning purposes by using a WLAN-enabled device, e.g. a smartphone, to measure and match the Received Signal Strength (RSS) of a signal broadcast by an access point. The challenges of this approach are that accurate maps of RSS are required, and that measuring RSS can be affected by many factors, including the dynamics of the environment and the orientation and type of a device. This paper provides a path-loss model to produce RSS maps automatically from floor plans and introduces an agent-based simulation approach to investigate different positioning methods. This provides a pathway to reduce the time and effort associated with WLAN positioning research.

2. Signal Attenuation Modelling in WLAN Positioning

   Terry Lines, and Anahid Basiri

   Oct 2019

   Abs

   Wireless Local Area Networks (WLAN), as the most widely used indoor positioning technology, can localise users by measuring the Received Signal Strength (RSS) from multiple Access Points (AP). The challenges of this approach are that measuring RSS can be easily affected by several parameters, including how the users hold the device, e.g. device orientation, and that accurate maps of RSS are required. This paper (A) introduces a bell-curve model of signal attenuation from orientation, allowing more accurate RSS measurement, and (B) identifies collinearity issues with a path-loss model used to automatically create RSS maps, suggesting a simpler and more robust alternative.

2016

1. Quality assessment of OpenStreetMap data using trajectory mining

   Anahid Basiri, Mike Jackson, Pouria Amirian, and 5 more authors

   Geo-Spatial Information Science, Oct 2016

   Abs

   OpenStreetMap (OSM) data are widely used but their reliability is still variable. Many contributors to OSM have not been trained in geography or surveying and consequently their contributions, including geometry and attribute data inserts, deletions, and updates, can be inaccurate, incomplete, inconsistent, or vague. There are some mechanisms and applications dedicated to discovering bugs and errors in OSM data. Such systems can remove errors through user-checks and applying predefined rules but they need an extra control process to check the real-world validity of suspected errors and bugs. This paper focuses on finding bugs and errors based on patterns and rules extracted from the tracking data of users. The underlying idea is that certain characteristics of user trajectories are directly linked to the type of feature. Using such rules, some sets of potential bugs and errors can be identified and stored for further investigations.