An integrated cyberGIS and machine learning framework for fine-scale prediction of Urban Heat Island using satellite remote sensing and urban sensor network data

Abstract

Due to climate change and rapid urbanization, Urban Heat Island (UHI), featuring significantly higher temperature in metropolitan areas than surrounding areas, has caused negative impacts on urban communities. Temporal granularity is often limited in UHI studies based on satellite remote sensing data that typically has multi-day frequency coverage of a particular urban area. This low temporal frequency has restricted the development of models for predicting UHI. To resolve this limitation, this study has developed a cyber-based geographic information science and systems (cyberGIS) framework encompassing multiple machine learning models for predicting UHI with high-frequency urban sensor network data combined with remote sensing data focused on Chicago, Illinois, from 2018 to 2020. Enabled by rapid advances in urban sensor network technologies and high-performance computing, this framework is designed to predict UHI in Chicago with fine spatiotemporal granularity based on environmental data collected with the Array of Things (AoT) urban sensor network and Landsat-8 remote sensing imagery. Our computational experiments revealed that a random forest regression (RFR) model outperforms other models with the prediction accuracy of 0.45 degree Celsius in 2020 and 0.8 degree Celsius in 2018 and 2019 with mean absolute error as the evaluation metric. Humidity, distance to geographic center, and PM2.5 concentration are identified as important factors contributing to the model performance. Furthermore, we estimate UHI in Chicago with 10-min temporal frequency and 1-km spatial resolution on the hottest day in 2018. It is demonstrated that the RFR model can accurately predict UHI at fine spatiotemporal scales with high-frequency urban sensor network data integrated with satellite remote sensing data.

Using unstable data from mobile phone applications to examine recent trajectories of retail centre recovery

“…We must however remain cautious of these trends, especially given they are based on exploratory analysis and modelling, which did not account directly for the impacts of seasonality, weather and holiday periods (Lyu et al, 2022 ; Rose & Dolega, 2022 ), and is based on trends for a subset of the major retail centres across the UK. Further research should seek to identify what additional knowledge can be generated about retail centre recovery by focusing on retail centres in London, or those ‘Small Local Centres’, which comprise the largest proportion of retail centres in the UK (Macdonald et al, 2022 ).…”

Predicting Urban Heat Island Mitigation with Random Forest Regression in Belgian Cities

“…The relationship between LST and related parameters have been previously analyzed using ordinary least square (OLS) regression and graphically weighted regression (Deilami et al 2018). Recent studies also have used machine learning in predicting changes in LST (Jato-Espino et al 2022;Lyu et al 2022). For example, Asadi et al (2020) use Artificial neural network (ANN) to predict changes in LST after implementing green roofs in Austin, Texas.…”

“…Although the parameters are comprehensive for the task, parameters influencing wind flow, such as frontal area index (FAI) could have enhanced the analysis (Wang et al 2021). Moreover, random forest (RF) regression has proven to be robust in predicting several scenarios (Jato-Espino et al 2022;Lyu et al 2022). Along with this, RF regression prediction is regarded as being unaffected by the multicollinearity and distribution of data (Matsuki et al 2016;Busato et al 2023).…”

Examine the environmental inequity impact of urban heat mitigation on redlining legacy: case study of Charlotte’s retrofitting, 2001–2020

“…At the conceptual level, there is a growing trend to incorporate the legacy of previous policies into the research framework (Grove et al, 2018;Wilson, 2020;Roberts et al, 2022) as the rapid urbanization has a profound impact on the urban environment, which is not only a historical legacy issue but also a current situation problem that urban management must face. Finally, at the methodological level, heat management increasingly relies on high spatiotemporal resolution (Eastin et al, 2018;Xu C. et al, 2022a;Lyu et al, 2022) and long-term (Xiong et al, 2022) remote sensing, as well as urban socio-economic data to conduct simulations based on objective changes and trends to enhance the specificity and effectiveness of urban heat management.…”