Lei Shu

Prof. Dr. Lei Shu

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 May 2024 in Renewable and Sustainable Energy Reviews
Verified
Journal Article
Closed access
LSLei Shu
Lei Shu
YMYunjeong Mo
Yunjeong Mo
Dong ZhaoDong Zhao
Dong Zhao

31 May 2023 in Buildings
Verified
Journal Article
Open access
PDF file
LSLei Shu
Lei Shu
Dong ZhaoDong Zhao
Dong Zhao
This research presents a comprehensive review of the research on smart urban energy retrofit decision-making. Based on the analysis of 91 journal articles over the past decade, the study identifies and discusses five key categories of approaches to retrofit decision-making, including simulation, optimization, assessment, system integration, and empirical study. While substantial advancements have been made in this field, opportunities for further growth remain. Findings suggest directions for future research and underscore the importance of interdisciplinary collaboration, data-driven evaluation methodologies, stakeholder engagement, system integration, and robust and adaptable retrofit solutions in the field of urban energy retrofitting. This review provides valuable insights for researchers, policymakers, and practitioners interested in advancing the state of the art in this critical area of research to facilitate more effective, sustainable, and efficient solutions for urban energy retrofits.

22 November 2024 in Energy and Buildings
Verified
Journal Article
Closed access
LSLei Shu
Lei Shu
THTianzhen Hong
Tianzhen Hong
KSKaiyu Sun
Kaiyu Sun
Dong ZhaoDong Zhao
Dong Zhao

16 April 2025 in Energy and Buildings
Verified
Journal Article
Closed access
LSLei Shu
Lei Shu
Dong ZhaoDong Zhao
Dong Zhao
WZWanni Zhang
Wanni Zhang
HLHan Li
Han Li
THTianzhen Hong
Tianzhen Hong

13 November 2025 in Buildings
Verified
Journal Article
Open access
PDF file
LSLei Shu
Lei Shu
AYArmin Yeganeh
Armin Yeganeh
Dong ZhaoDong Zhao
Dong Zhao
Conventional approaches to building energy retrofit decision-making struggle to generalize across diverse building characteristics, climate conditions, and occupant behaviors, and often lack interpretability. Generative AI, particularly Large Language Models (LLMs), offers a promising solution because they learn from extensive, heterogeneous data and can articulate inferences in transparent natural language. However, their capabilities in retrofit decision-making remain underexplored. This study evaluates six widely used LLMs on two objectives: determining the retrofit measure that maximizes CO2 reduction (a technical task) and minimizes the payback period (a sociotechnical task). We assessed performance across accuracy, consistency, sensitivity, and reasoning. The evaluation used 400 residential buildings from a nationwide, simulation-based database. The results reveal that LLMs vary across cases, with consistently strong technical-task performance but notably weaker performance on the sociotechnical one, highlighting limitations in handling complex economic and contextual trade-offs. The models consistently identify a near-optimal solution for the technical task (Top-5 accuracy reaching 92.8%), although their ability to pinpoint the single best option is limited (Top-1 accuracy reaching 54.5%). While models approximate engineering logic by prioritizing location and geometry, their reasoning processes are oversimplified. These findings suggest LLMs are promising for technical advisory tools but not yet reliable for standalone retrofit decision-making.

1 January 2025 in Journal of Civil Engineering Education
Verified
Journal Article
Closed access
Dong ZhaoDong Zhao
Dong Zhao
ZCZhiting Chen
Zhiting Chen
GBGeorge Berghorn
George Berghorn
LSLei Shu
Lei Shu
CACornelia Asiedu-Kwakyewaa
Cornelia Asiedu-Kwakyewaa