Updates from our group
Full list of publications is here.
How can bidirectional information exchange be enhanced in urban digital twins, and support human-centric data and processes? Their key characteristic is the nearly real-time exchange of information, allowing adjustments to physical environments based on simulations and analytics within virtual models. Yet, achieving such interaction remains challenging, particularly regarding device deployment and infrastructure development. Embracing the concept of humans as sensors, this work develops a two-way framework based on the emerging concept of just-in-time adaptive interventions (JITAIs), exploring how urban digital twins can play a role in understanding and enhancing human comfort outdoors. Human comfort outdoors is inherently spatio-temporal and personalised, influenced by multisensory perception. The JITAIs framework involves collecting human comfort data and delivering interventions tailored to contextual and personal conditions. Thus, bidirectional information exchange will be established between humans and urban environments, thereby closing the loop in urban digital twins. A three-week campus experiment with 14 participants demonstrates this framework in two phases: (1) collecting comfort perception data and (2) delivering tailored interventions based on comfort perception and contextual features. End-of-day surveys reveal that 18.4% of responses indicated no behaviour change influenced by JITAIs, while 53.1% acknowledged their role in improving the understanding of outdoor comfort. The JITAIs framework is still nascent, but demonstrates an instance to close information loop in urban digital twins, as well as paves the way for future research. This novel work will facilitate human-centric urban digital twins and their multidisciplinary applications, such as planning comfortable walking routes.
Kevin Lynch’s concept of imageability describes how effectively an environment evokes a mental image in an observer’s mind, which consists of three components—“identity, structure, and meaning”—with the first two being the main components to build Lynch’s cognitive map. Although imageability has significantly influenced urban design and planning, and inspired numerous subsequent research, the “meaning” component has not been clearly studied. The rise of new urban data, particularly the booming availability of reviews of urban spaces on platforms such as TripAdvisor and Google, offers a valuable opportunity to incorporate the meaning into the imageability study. By adapting several open-source algorithms, this research efficiently extracts both objective (e.g. location, number of reviews) and subjective (e.g. ratings, review text) information from the online platform, proposing a novel approach to studying the meaning component through a fine-tuned BERT model. These data and methods enable this research to capture and categorize the meaning component for describing the image of the city, using Singapore as a case study. The results show that: (1) Lynch’s cognitive mapping approach could potentially be enhanced by incorporating the meaning into the study of imageability, it could amplify the existing nodes or landmarks, and create new “nodes”. (2) The proposed “meaning patch” could add new layers to structure of the city image by representing the shared meanings of multiple places, suggesting the potential to be studied as the sixth element to extend the existing imageability framework, and open new agenda for the future studies.
Achieving carbon neutrality is a critical yet elusive goal for many cities, hindered by limited understanding of the relationship between building emissions and their surroundings. To address this challenge, we present a generalizable open science framework that integrates building energy-consumption data, multi-modal geospatial inputs and graph deep learning to quantify building operating emissions and their links to urban form and socio-economic factors. Applying this approach to five cities with diverse climates and planning contexts—Melbourne, New York City (Manhattan), Seattle, Singapore and Washington DC—we demonstrate that our models explain 78.4% of the variation in building operating carbon emissions across cities, achieving state-of-the-art accuracy for urban-scale energy modelling. Our findings reveal strong connections between a city’s planning history and its building carbon profile, alongside stark inequalities where wealthier areas often exhibit the highest per capita emissions. Additionally, the relationship between urban density and building emissions is complex and city specific, with emissions extending beyond dense urban cores into suburban areas. To design effective decarbonization strategies, cities must consider how their planning histories, urban layouts and economic conditions shape current emissions patterns.
Humans can play a more active role in improving their comfort in the built environment if given the right information at the right place and time. This paper outlines the use of Just-in-Time Adaptive Interventions (JITAI) implemented in the context of the built environment to provide information that helps humans minimize the impact of heat and noise on their daily lives. This framework is based on the open-source Cozie iOS smartwatch platform. It includes data collection through micro-surveys and intervention messages triggered by environmental, contextual, and personal history conditions. An eight-month deployment of the method was completed in Singapore with 103 participants who submitted more than 12,000 micro-surveys and had more than 3,600 JITAI intervention messages delivered to them. A weekly survey conducted during two deployment phases revealed an overall increase in perceived usefulness ranging from 8%–19% over the first three weeks of data collection. For noise-related interventions, participants showed an overall increase in location changes ranging from 4%–11% and a 2%–17% increase in earphone use to mitigate noise distractions. For thermal comfort-related interventions, participants demonstrated a 3%–13% increase in adjustments to their location or thermostat to feel more comfortable. The analysis found evidence that personality traits (such as conscientiousness), gender, and environmental preferences could be factors in determining the perceived helpfulness of JITAIs and influencing behavior change. These findings underscore the importance of tailoring intervention strategies to individual traits and environmental conditions, setting the stage for future research to refine the delivery, timing, and content of intervention messages.
Recognising GeoAI as an emerging and rapidly evolving field that has been increasingly adopted in urban geography, this chapter provides an overarching overview of the GeoAI methods for urban analytics. It begins by revisiting the theoretical underpinnings of urban theory and mapping the evolution of urban spatial analytics, tracing the journey from traditional statistical methods to the cutting-edge AI-driven approaches reshaping the discipline today. Beyond examining the current state of GeoAI, the chapter also identifies current trending topics and investigates future directions for developing human-centric methodologies that prioritise the needs and experiences of urban residents. By emphasising the human dimension of urban analytics, the chapter seeks to contribute to the ongoing discourse on how GeoAI can be harnessed to enhance city governance, urban planning, and the overall quality of urban life.