While significant importance is given to establishing formal organizational and contractual hierarchies, existing project management techniques neglect the management of self-organizing networks in large-infrastructure projects. We offer a case-specific illustration of self-organization using network theory as an investigative lens. The findings have shown that these networks exhibit a high degree of sparseness, short path lengths, and clustering in dense “functional” communities around highly connected actors, thus demonstrating the small-world topology observed in diverse real-world self-organized networks. The study underlines the need for these non-contractual functions and roles to be identified and sponsored, allowing the self-organizing network the space and capacity to evolve.

The accurate measurement of human activity with high spatial and temporal granularity is crucial for understanding the structure and function of the built environment. With increasing mobile ownership, the Wi-Fi ‘probe requests’ generated by mobile devices can act as a cheap, scalable and real-time source of data for establishing such measures. The two major challenges we face in using these probe requests for estimating human activity are: filtering the noise generated by the uncertain field of measurement and clustering anonymised probe requests generated by the same devices together without compromising the privacy of the users. In this paper, we demonstrate that we can overcome these challenges by using class intervals and a novel graph-based technique for filtering and clustering the probe requests which in turn, enables us to reliably measure real-time pedestrian footfall at retail high streets.

Urban growth models are increasingly being used to generate scenarios within city and regional planning support systems (PSS). However, their usefulness in land use planning applications, particularly in city resilience planning, is not fully understood. Thus, we developed a cellular automata model using Metronamica PSS for the Greater Sydney region and assessed its usefulness as perceived by planning and policy practitioners. The study was implemented through a collaborative geodesign workshop where participants (n = 19) were guided to an understanding of the modelling process and to create and validate alternative policy scenarios for 2050 that reflected Business-As-Usual, Bushfire resilience, Flood resilience, and Combined resilience. We conducted two surveys and a SWOT analysis to assess the usefulness of the PSS and its outputs. We found that the PSS created credible scenarios using collaborative inputs from the participants. The PSS had perceived value for informing participants about land use changes in the resilience planning contexts with high flexibility and granularity. The plausibility of the scenario outputs, a usefulness parameter, was readily accepted, but the model’s transparency (another parameter) was seen as potentially inhibiting application in real-world planning. Future research should involve a broader audience, including the local community, in analysing the usefulness of PSS.

Planning for sustainable urban growth is a pressing challenge facing many cities. Investigating proposed changes to the built environment can provide planners and policymakers information to understand future urban development trends and related infrastructure requirements. It is in this context we have developed a novel urban analytics approach that utilises planning applications (PAs) data and Natural Language Processing (NLP) techniques to forecast the housing supply pipeline in Australia. Firstly, we implement a data processing pipeline which collects, geocodes, and filters PA data from local government websites and state planning portals to provide the first nationally available daily dataset of PAs that are currently under consideration. Secondly, we classify the collected PAs into four distinct urban development categories, selected based on the infrastructure planning and provisioning they require. We tested five model architectures and found that the fine-tuned DeBERTA-v3 model achieves the best performance with both accuracy and F1-score of 0.944. This demonstrates the suitability of fine-tuned Pre-trained Language Models (PLMs) in classifying PAs based on text in them. Finally, this model is applied to classify and map urban development trends in Australia’s two largest cities, Sydney and Melbourne across two time periods – between 2021 and 2022, and between 2023 and 2024. This mapping affirms a face-validation test of the classification model and demonstrates the utility of insights the generate for planning use case. Holistically, the paper demonstrates the potential for NLP to enrich urban analytics through the integration of previously inaccessible text data in planning applications into planning analysis and decisions.

Real estate markets are complex both in terms of structure and dynamics: they are both influenced by and influence almost all aspects of the economy and are equally vulnerable to the shocks experienced by the broader economy. Therefore, understanding the extent and nature of the impact of large-scale disruptive events such as natural disasters and economic financial downturns on the real estate market is crucial to policy makers and market stakeholders. In addition to anticipating and preparing for long-term effects, it has become imperative for stakeholders to monitor and manage the short-term effects as well due to the emergence of ‘PropTech’ and ‘platform real estate’. In this work, we explore the use of online, real-time dashboards which have been used extensively in the context of urban management, policymaking, citizen engagement and disaster response as an appropriate tool for the purpose of monitoring real estate markets. We describe the process of designing, building, and maintaining an operational dashboard for monitoring the residential real estate market in Australia during the COVID-19 pandemic in 2020. We detail the techniques and methods used in creating the dashboard and critically evaluate their feasibility and usefulness. Finally, we identify the major challenges in the process, such as the spatial and temporal availability and veracity of the real estate market data, and we identify possible avenues for consistent, high-quality data; methodology; and outputs for further research.