A framework for a comprehensive mobile data acquisition setting for the assessment of Urban Heat Island phenomenon

Abstract

The 39th ISARC was proudly hosted by the Department of Civil and Environmental Engineering at Universidad de los Andes. The 2022 ISARC has been the first-ever ISARC in Latin America and it was organized in collaboration

Performance Evaluation of MeteoTracker Mobile Sensor for Outdoor Applications

“…A key ensemble of this second category consists of mobile sensors suitable for measuring the thermo-hygrometric characteristics of the atmosphere on the move. The sensor suite is typically composed of a thermo-hygrometer or a thermo-logger, but examples of complete weather stations mounted on moving vehicles (Heusinkveld et al, 2014;Emery et al, 2021) or integration with automatic infrared cameras (Lindberg, 2007;Acosta et al, 2022) are also documented. Two main categories of sensors are also used: research-grade instrumentation designed for conventional weather stations and adapted for mobile use, and low-cost mobile sensors.…”

Demystifying the urban heat island phenomenon : through high-resolution urban data and machine learning

“…Hence, the data collection step consists of two main parts that can be conducted simultaneously: (1) the collection of the relevant cadastral datasets, and (2) the development of a mobile unit capable of capturing the required measurements. The previous work of the authors provides comprehensive explanations of the development of the mobile unit (Pena Acosta et al, 2022) and the publicly available datasets (Pena Acosta et al, 2021a). Nevertheless, both processes are briefly presented in the following subsections for the completeness of the paper.…”

“…Table 5.1 provides a summary of the dataset. Furthermore, as presented in the previous work of the authors (Pena Acosta et al, 2022) all features were scaled down to a street-level resolution. For this purpose, each street was defined by the road segment between two intersections.…”

“…Therefore, there is still a need for a more rigorous analysis of SUHI and CUHI using a high-volume, consistent dataset that can counter the effect of seasonal and contextual variabilities on UHI behavior. Should consistent temperature data be collected, the relationship between SUHI/CUHI and the urban planning design parameters can be easily studied using data-driven methods, as shown in the previous work of the authors (Pena Acosta et al, 2022). For instance, supervised learning approaches have been successfully applied to find correlations between urban geometries and the intensity of UHI (Chakraborty et al, 2020;Makido et al, 2016;Oukawa et al, 2022;Wang et al, 2020).…”

“…In previous studies, the authors demonstrated a systematic and rigorous data collection strategy that can address the problem of inconsistent data for the study of CUHI and SUHI fields (Pena Acosta et al, 2022;Pena Acosta, Vahdatikhaki, et al, 2023). Using consistent and well-structured street-level air and surface temperatures at the same spatiotemporal resolution enables the application of machine learning (ML) techniques to uncover hidden relationships between urban factors and temperature changes within the built environment.…”