Using Artificial Intelligence for Predicting Universal Thermal Climate Index Based on Different Urban Conditions: A Comparative Study of Machine Learning Models DOI
Omid Veisi, Alireza Attarhay Tehrani,

Beheshteh Gharaei

et al.

Published: Jan. 1, 2024

Our research aims to investigate using Artificial Intelligence (AI) methods forecast the Universal Thermal Climate Index (UTCI) in different metropolitan environments. We used several AI models, such as Neural Networks (ANNs), Random Forests (RF), and Gradient Boosting Regressors (GBR), examine data from many cities throughout globe. objective was gain insights into influence of urban architecture on thermal comfort. The emphasizes strong associations between design factors building density, green space ratio, UTCI results, showcasing potential planning climate adaptation. This study focuses two main challenges: computing requirements algorithms limits available imposes. accessible limited a certain set locations rows. Despite these challenges, ANN model achieved notable level precision (MSE=0.008 R2 Score 97), thereby robustness artificial intelligence environmental modeling. To summarize, incorporating procedures may greatly boost our capacity promote comfort settings, therefore contributing development more sustainable habitable cities.

Language: Английский

Machine learning based thermal comfort prediction in office spaces: Integrating SMOTE and SHAP methods DOI
Yiliang Li, Feng Gao, Jiayue Yu

et al.

Energy and Buildings, Journal Year: 2025, Volume and Issue: unknown, P. 115267 - 115267

Published: Jan. 1, 2025

Language: Английский

Citations

1
Study of Factors Influencing Thermal Comfort at Tram Stations in Guangzhou Based on Machine Learning DOI Creative Commons
Xin Chen, Hai Zhao,

Beini Wang

et al.

Buildings, Journal Year: 2025, Volume and Issue: 15(6), P. 865 - 865

Published: March 10, 2025

As global climate change intensifies, the frequency and severity of extreme weather events continue to rise. However, research on semi-outdoor transitional spaces remains limited, transportation stations are typically not fully enclosed. Therefore, it is crucial gain a deeper understanding environmental needs users in these spaces. This study employs machine learning (ML) algorithms SHAP (SHapley Additive exPlanations) methodology identify rank critical factors influencing outdoor thermal comfort at tram stations. We collected microclimatic data from Guangzhou, along with passenger feedback, construct comprehensive dataset encompassing parameters, individual perceptions, design characteristics. A variety ML models, including Extreme Gradient Boosting (XGB), Light Machine (LightGBM), Categorical (CatBoost), Random Forest (RF), K-Nearest Neighbors (KNNs), were trained validated, analysis facilitating ranking significant factors. The results indicate that LightGBM CatBoost models performed exceptionally well, identifying key determinants such as relative humidity (RH), air temperature (Ta), mean radiant (Tmrt), clothing insulation (Clo), gender, age, body mass index (BMI), location space occupied past 20 min prior waiting (SOP20). Notably, significance physical parameters surpassed physiological behavioral provides clear strategic guidance for urban planners, public transport managers, designers enhance while offering data-driven approach optimizing promoting sustainable development.

Language: Английский

Citations

1
Optimizing personal comfort: Short-term personalized heating impact on sanitation workers' thermo-physiological responses DOI

Chujian Gu,

Yang Li,

Shi Chen

et al.

Building and Environment, Journal Year: 2024, Volume and Issue: unknown, P. 112112 - 112112

Published: Sept. 1, 2024

Language: Английский

Citations

8
Generative design of walkable urban cool spots using a novel heuristic GAN×GAN approach DOI

X. H. Li,

Weisheng Lu,

Ziyu Peng

et al.

Building and Environment, Journal Year: 2024, Volume and Issue: 266, P. 112027 - 112027

Published: Aug. 30, 2024

Language: Английский

Citations

6
Skills of Statistical Learning Algorithms in Thermal Stress Assessment Compared with the Expert Judgement Inherent to the Universal Thermal Climate Index (UTCI) DOI Open Access
Peter Bröde,

Dusan Fiala,

Bernhard Kampmann

et al.

Published: April 26, 2024

The objective of this paper was to verify the applicability statistical learning (SL) compared human reasoning with respect Universal Thermal Climate Index (UTCI), a complex tool for assessment outdoor thermal stress. UTCI is an equivalent temperature index based on 48-dimensional output advanced model thermoregulation formed by 12 variables at four consecutive 30-minute intervals, which were calculated 105642 conditions from extreme cold heat. Comparing performance SL algorithms results accomplished international endeavor involving more than 40 experts 23 countries, we found that random forests and k-nearest neighbors closely predicted values, but clustering applied after dimension reduction (principal component analysis t-distributed stochastic neighbor embedding) inadequate risk in relation stress categories. This indicates potential supportive role SL, as it will not (yet) fully replace bio-meteorological expert knowledge.

Language: Английский

Citations

5
Machine learning-based assessment of thermal comfort for the elderly in warm environments: Combining the XGBoost algorithm and human body exergy analysis DOI
Mengyuan He,

Hong Liu,

Shan Zhou

et al.

International Journal of Thermal Sciences, Journal Year: 2024, Volume and Issue: 209, P. 109519 - 109519

Published: Nov. 9, 2024

Language: Английский

Citations

4
Unveiling Differential Impacts of Multidimensional Urban Morphology on Heat Island Effect Across Local Climate Zones: Interpretable CatBoost-SHAP Machine Learning Model DOI
Qiqi Liu,

Hang Tian,

Yunfei Wu

et al.

Building and Environment, Journal Year: 2025, Volume and Issue: unknown, P. 112574 - 112574

Published: Jan. 1, 2025

Language: Английский

Citations

0
Quantifying the Carbon Reduction Potential of Urban Parks Under Extreme Heat Events Using Interpretable Machine Learning: A Case Study of Jinan, China DOI Creative Commons

Lemin Yu,

Wenjun Li,

C. Zheng

et al.

Atmosphere, Journal Year: 2025, Volume and Issue: 16(1), P. 79 - 79

Published: Jan. 14, 2025

Greenhouse gas emissions are primary drivers of climate change, and the intensification extreme heat urban island effects poses serious threats to ecosystems, public health, energy consumption. This study systematically evaluated carbon reduction potential 369 parks in Jinan during events using land surface temperature (LST) retrieval, combined with CatBoost + SHAP machine learning methods. Results indicate that LST ranged from 1.77 °C 59.44 °C, 278 exhibited significant cooling effects, collectively saving 2943 tons CO2 per day—offsetting 11.28% city’s fossil fuel emissions. Small parks, such as community demonstrated higher carbon-saving efficiency (CSE), while large ecological showed greater intensity (CSI). CSE was strongly correlated vegetation coverage surrounding population density, increasing when index within 0.3–0.7 density 0–5000 or 15,000–22,500 people. CSI influenced by evapotranspiration park geometric form, significantly area exceeded 250 hectares 2.5–6.0. However, elevation albedo negatively impacted both metrics, lowest observed 150 m surpassed 18%.

Language: Английский

Citations

0
Decadal assessment of local climate utilizing meteorological analysis and observation data: Thermal environment changes in the Tokyo area DOI
Xiang Wang,

Hongyuan Jia,

Keisuke Nakao

et al.

Sustainable Cities and Society, Journal Year: 2025, Volume and Issue: unknown, P. 106138 - 106138

Published: Jan. 1, 2025

Language: Английский

Citations

0
One-point-reference-based approach for multi-indoor microclimate prediction based on dynamic-environmental factors DOI
Mallika Kliangkhlao,

Panachat Aiamnam,

Kasidit Boonchai

et al.

Journal of Building Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 111945 - 111945

Published: Jan. 1, 2025

Language: Английский

Citations

0