The urban heat island (UHI) is a crucial factor in developing sustainable cities and societies. Appropriate data collection, analysis, and prediction are essential first steps in studying the effects of the UHI. This research systematically reviewed the papers related to the UHI that have used on-site data collection in the United States and Canada and the papers related to predicting and analyzing this effect in these regions. To achieve this goal, this study extracted 330 articles from Scopus and Web of Science and, after selecting the papers, reviewed 30 papers in detail from 1998 to 2023. The findings of this paper indicated a methodological shift from traditional sensors and data loggers towards more innovative and customized technologies. Concurrently, this research reveals a growing trend in using machine learning, moving from supportive to direct predictive roles and using techniques like neural networks and Bayesian networks. Despite the maturation of UHI research due to these developments, they also present challenges in technology complexity and data integration. The review emphasizes the need for future research to focus on accessible, accurate technologies. Moreover, interdisciplinary approaches are crucial for addressing UHI challenges in an era of climate change.

In volume visualization, users can interactively explore the three-dimensional data by specifying color and opacity mappings in the transfer function (TF) or adjusting lighting parameters, facilitating meaningful interpretation of the underlying structure. However, rendering large-scale volumes demands powerful GPUs and high-speed memory access for real-time performance. While existing novel view synthesis (NVS) methods offer faster rendering speeds with lower hardware requirements, the visible parts of a reconstructed scene are fixed and constrained by preset TF settings, significantly limiting user exploration. This paper introduces inverse volume rendering via Gaussian splatting (iVR-GS), an innovative NVS method that reduces the rendering cost while enabling scene editing for interactive volume exploration. Specifically, we compose multiple iVR-GS models associated with basic TFs covering disjoint visible parts to make the entire volumetric scene visible. Each basic model contains a collection of 3D editable Gaussians, where each Gaussian is a 3D spatial point that supports real-time scene rendering and editing. We demonstrate the superior reconstruction quality and composability of iVR-GS against other NVS solutions (Plenoxels, CCNeRF, and base 3DGS) on various volume datasets. The code is available at https://github.com/TouKaienn/iVR-GS.

Life Cycle Assessment (LCA) is an essential tool for quantifying the environmental burdens of products and processes, critical for advancing sustainability goals. Central to the effectiveness of LCA is the Life Cycle Inventory (LCI) phase, which requires reliable data to reflect the environmental footprint of products accurately. However, LCA practitioners often encounter data gaps that can compromise the assessment’s accuracy. To address this, we explore the integration of Machine Learning (ML) to enhance LCA data quality, particularly in the LCI stages B to D, which focus on product use, end-of-life, and beyond-life phases. This chapter introduces a novel framework that leverages ML to overcome LCI data challenges, emphasizing reducing the embodied carbon of construction products. We extract existing data from the Environment Product Declaration online library and apply natural language processing to interpret this unstructured data. Subsequently, we employ a random forest algorithm, a robust ensemble tree-based ML method, to refine the data analysis. We present a pilot study that validates the feasibility of our ML-enhanced framework. The incorporation of ML addresses the voluminous data in LCA. It augments the analytical capacity, thereby improving the precision and reliability of both LCI and Life Cycle Impact Assessment (LCIA) datasets. Consequently, our approach yields higher quality LCA outcomes, offering a more reliable basis for environmental impact evaluation. In summary, the successful application of ML in this research bridges the critical data gap in LCI for construction products, paving the way for a more sustainable industry through improved accuracy in environmental impact assessments and more informed decision-making in green product innovation.

Monitoring microclimate variables within cities with high resolution and accuracy is crucial for enhancing urban resilience to climate change. Assessing intra-urban characteristics is essential for ensuring satisfactory living standards. This paper presents a comprehensive methodology for studying urban heat islands (UHIs) on a university campus, emphasizing the importance of multi-modal and multi-temporal data collection. The methodology integrates mobile surveys, stationary sensor networks, and drone-based thermal imaging, providing a detailed analysis of temperature variations within urban microenvironments. The preliminary findings confirm the presence of a UHI on the campus and identify several hotspots. This comprehensive approach enhances the accuracy and reliability of UHI assessments, offering a cost-effective, fine-resolution approach that facilitates more effective urban planning and heat mitigation strategies.