Junjie Yu

Junjie Yu

Auto-generated profile, based on publicly available information

Junjie Yu

Department of Earth and Environmental Sciences The University of Manchester Manchester UK

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
21 April 2022 in Water Research
Verified
Journal Article
Closed access
JYJunjie Yu
Junjie Yu
HXHui Xu
Hui Xu
DWDongsheng Wang
Dongsheng Wang
HSHongyan Sun
Hongyan Sun
RJRuyuan Jiao
Ruyuan Jiao
SZShuo Zhang
Shuo Zhang

27 February 2025 in Environmental Modelling & Software
Verified
Journal Article
Open access
JYJunjie Yu
Junjie Yu
YSYuan Sun
Yuan Sun
SLSarah Lindley
Sarah Lindley
CJCaroline Jay
Caroline Jay
DTDavid O. Topping
David O. Topping
Zhonghua ZhengZhonghua Zheng
Zhonghua Zheng

1 December 2025 in Big Data and Earth System
Verified
Journal Article
Open access
JYJunjie Yu
Junjie Yu
Zhonghua ZhengZhonghua Zheng
Zhonghua Zheng
SLSarah Lindley
Sarah Lindley
LZLei Zhao
Lei Zhao
CWChi Wang
Chi Wang
KOKeith W. Oleson
Keith W. Oleson

13 August 2026 in Urban Climate
Verified
Journal Article
Open access
JYJunjie Yu
Junjie Yu
WLWenyuan Li
Wenyuan Li
LLLingcheng Li
Lingcheng Li
DKDivya Kumar
Divya Kumar
HSHongyu Sun
Hongyu Sun
Zhonghua ZhengZhonghua Zheng
Zhonghua Zheng

21 May 2025
Verified
Conference Paper
Open access
JXJiyang Xia
Jiyang Xia
FLFenghua Ling
Fenghua Ling
JYJunjie Yu
Junjie Yu
ZLZhenhui Li
Zhenhui Li
HZHongliang Zhang
Hongliang Zhang
Zhonghua ZhengZhonghua Zheng
Zhonghua Zheng
Understanding climate-driven risks in urban areas necessitates improved representation of urban climate processes in Earth system models (ESMs). Machine learning (ML) has emerged as a promising tool to enhance this representation by capturing complex, nonlinear relationships in urban surfaces-atmospheric processes. Although prior ML methods achieve considerable accuracy in emulating urban climate processes for ESMs, they may compromise by focusing on a single variable and not necessarily obeying the physical laws. In contrast, physics-guided ML integrated physical elements offers promise in overcoming the above limitations, while also showcasing potential for enhanced generalization. In this work, we present a multi-task physics-guided Transformer, named UCformer, to emulate nonlinear interactions between urban surfaces and atmospheric forcing, and to generalize urban climate dynamics over time. The architecture of UCformer incorporates physical and climatic knowledge, enabling it to achieve superior performance in urban climate multi-task estimations compared to baseline models. The investigation of urban surface parameters suggests that the thermal parameters have the most integrated impact on UCformer emulation skill, with radiation parameters ranking second. Additionally, an ablation study further examines the performance gains from specific components of the UCformer architecture, underscoring the significant potential of integrating physical and climatic knowledge to enhance urban climate modeling.

5 August 2026 in Earth's Future
Verified
Journal Article
Open access
PDF file
JYJunjie Yu
Junjie Yu
KOKeith W. Oleson
Keith W. Oleson
YQYue Qin
Yue Qin
LZLei Zhao
Lei Zhao
DTDavid O. Topping
David O. Topping
Zhonghua ZhengZhonghua Zheng
Zhonghua Zheng
Roof watering is a novel strategy for reducing air conditioning energy consumption and mitigating excess urban heat, yet its application is often constrained by water availability. To address this challenge, we propose an adaptation strategy that integrates rainwater harvesting tank with roof sprinkling to strengthen urban heat resilience. We develop a new module implemented in the Community Land Model Urban (CLMU) to evaluate the efficacy of the proposed strategy, whose parameters were further determined by a framework using multi‐objective optimization combined with a transformer‐based tabular foundation model. This integrated modeling framework enables the optimization of the proposed strategy and provides insights into its impacts on air conditioning energy consumption and its co‐benefits on the urban thermal environment. Results show that the temperature threshold for triggering sprinkling is a more important parameter than rainwater tank size or sprinkling intensity. The optimal strategies effectively reduce cooling energy demand, lower extreme temperatures, and decrease heatwave days. However, a trade‐off exists between rainwater tank size and the reduction in cooling energy consumption and heatwave days. Additionally, the energy saving is more pronounced under higher atmospheric temperatures. The implementation of the rainwater harvesting and roof sprinkling system in CLMU provides valuable insights for improving urban resilience and can be further coupled into Earth system model for large‐scale studies.