In a recent article published in the journal Scientific Reports, researchers from the USA and the UK developed and tested a novel framework for assessing and forecasting collective urban heat exposure using smart city digital twins (SCDT). They integrated meteorological sensors, computer vision techniques, and time-series prediction models to predict and monitor heat stress and the affected people. Moreover, the research demonstrated the potential of SCDT to enhance public safety and mitigate the impact of heat exposure in urban environments.
Study: Urban Heat Exposure Assessment Using Smart City Digital Twins. Image Credit: bluefish_ds/Shutterstock
Background
Heat exposure is a serious issue for urban populations, especially in the context of climate change and the urban heat island effect. Heat exposure can cause acute illnesses and increase the risk of mortality, especially for vulnerable groups such as the elderly, infants, and patients with chronic diseases. Therefore, assessing and mitigating heat exposure is a prerequisite for creating healthy and sustainable cities.
However, most of the existing methods are limited by the spatial and temporal resolution of the data, the integration of human behavior information, and the predictive and decision-support capabilities. For example, many studies rely on static data sources, such as satellite imagery, census data, or land use data, which cannot capture the fine-scale and dynamic variations of heat exposure in urban spaces.
Moreover, few methods consider the effect of human movement and activity patterns on heat exposure, which can influence the number and location of people exposed to heat stress. Furthermore, most studies focus on describing the current or historical heat exposure patterns rather than forecasting the future heat exposure levels and providing proactive mitigation measures.
About the Research
In the present paper, the authors proposed an SCDT-based framework for collective urban heat exposure assessment and forecasting. An SCDT is a digital model of a city that runs in real-time, utilizes high spatial-temporal resolution data, conducts prediction and what-if scenario tests, integrates multi-source information and human dynamics, visualizes human-infrastructure interactions, and thus enables proactive city management.
The presented technique consists of three main components: data collection, data analysis, and data visualization. For data collection, the study implemented meteorological sensors and street cameras in two intersections in Columbus, Georgia, to acquire temperature, humidity, and passersby count data. These data were then integrated into a collective temperature humidity index (CTHI), which measures the heat stress and the number of people affected by heat exposure at each location.
For data analysis, the researchers employed a time-series prediction model and a crowd simulation model to predict future short-term CTHI values based on the data accumulated by the SCDT. The prediction model can also support heat exposure mitigation efforts by providing information on the potential occurrence and severity of extreme heat events. For data visualization, the researchers developed a web-based dashboard that displays the real-time and predicted CTHI values, as well as the meteorological and passersby data, for each location.
Research Findings
The performance and validity of the proposed framework were tested using data collected from August 16 to 22, 2020. The outcomes showed that the framework can effectively monitor and forecast the collective urban heat exposure with high spatiotemporal resolution and accuracy. It captured the heterogeneity and dynamics of heat exposure across different locations and times, as well as the influence of human movement and activity patterns. For example, it detected a significant increase in CTHI at one intersection due to a large-scale protest event on August 22, not reflected by conventional heat exposure indexes.
Additionally, applying the framework to the case study site in Columbus, Georgia, revealed spatiotemporal variations of heat exposure at a fine-grained scale and predicted future heat exposure with reasonable accuracy, even considering the impact of large and rare social events. This suggests that the framework could enhance public safety and mitigate the adverse effects of heat exposure in urban environments.
Applications
The new approach can provide city officials with a tool for discovering, predicting, and preventing community exposure to extreme heat by informing them of the locations and times of high heat exposure risk and the number of people affected.
Furthermore, it can assist city planners and managers in designing and implementing heat adaptation strategies, such as greening the built environment, shading and insulating buildings, and providing cooling facilities and services based on the fine-scale and dynamic heat exposure information. Additionally, it can raise public awareness and engagement on heat exposure issues, by providing citizens with real-time and personalized heat exposure alerts and recommendations.
Conclusion
In summary, the presented framework proved effective for collective heat exposure assessment and forecasting in urban areas. It could efficiently monitor and predict heat stress and the number of people affected by heat exposure in real time. Moreover, the authors showed the potential of SCDT to create healthy and sustainable cities.
The researchers acknowledged limitations and challenges and suggested some directions for future work. They recommended improving the individual-level heat exposure assessment, considering more social factors in heat exposure analysis, establishing thresholds for CTHI, and addressing the project management and governance issues in SCDT projects.