Bridging accuracy and efficiency: Advancing mean radiant temperature measurement in Urban Ecology DOI

A. O. Benson,

Ben Crawford, J. M. Frank

и другие.

Research Square (Research Square), Год журнала: 2025, Номер unknown

Опубликована: Май 5, 2025

Abstract Extreme summertime heat is an increasing challenge for cities, highlighting the need accurate, spatially meaningful methods to measure and map in ways that reflect human thermal experiences inform land management decisions. Mean radiant temperature (Tmrt) a key metric assessing urban at hyper-local scales, yet its measurement remains technically challenging. In this study, we apply six-directional, gold standard method measuring Tmrt with globe thermometer-based approaches across multiple levels of spatial aggregation develop novel machine learning model trained on field data. Data were collected semi-arid city Colorado, USA, over two summers. Using measurements from residential parcels, show aggregated thermometer data—collected using low-cost, accessible sensor—can capture patterns landscapes reasonable accuracy. Our findings also indicate learning, combining six-directional data, offers promising potential improving both accuracy efficiency. These are particularly relevant planners working scale where adaptation strategies commonly applied, especially insightful cities those increasingly experiencing arid summer conditions due climate change. This work advances practical integrating comfort into landscape planning climate-resilient design.

Язык: Английский

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

и другие.

Energy and Buildings, Год журнала: 2025, Номер unknown, С. 115267 - 115267

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

3
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

и другие.

Building and Environment, Год журнала: 2025, Номер unknown, С. 112574 - 112574

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

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

Chujian Gu,

Yang Li,

Shi Chen

и другие.

Building and Environment, Год журнала: 2024, Номер unknown, С. 112112 - 112112

Опубликована: Сен. 1, 2024

Язык: Английский

Процитировано

9
Generative design of walkable urban cool spots using a novel heuristic GAN×GAN approach DOI

X. H. Li,

Weisheng Lu, Ziyu Peng

и другие.

Building and Environment, Год журнала: 2024, Номер 266, С. 112027 - 112027

Опубликована: Авг. 30, 2024

Язык: Английский

Процитировано

8
Study of Factors Influencing Thermal Comfort at Tram Stations in Guangzhou Based on Machine Learning DOI Creative Commons
Xin Chen, Hai Zhao,

Beini Wang

и другие.

Buildings, Год журнала: 2025, Номер 15(6), С. 865 - 865

Опубликована: Март 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.

Язык: Английский

Процитировано

1
Leveraging urban AI for high-resolution urban heat mapping: Towards climate resilient cities DOI
Abdulrazzaq Shaamala,

Niklas Tilly,

Tan Yiğitcanlar

и другие.

Environment and Planning B Urban Analytics and City Science, Год журнала: 2025, Номер unknown

Опубликована: Апрель 24, 2025

Urban heat island (UHI) effects are increasingly recognised as a significant challenge arising from urbanisation, leading to elevated temperatures within urban areas that pose risks public health and undermine the sustainability of cities. Effective UHI management requires high-resolution timely mapping temperature patterns guide interventions. Traditional methods for often lack spatial accuracy efficiency necessary detailed analysis, especially in complex environments. This study integrates artificial intelligence (Urban AI) by presenting U-Net model tailored metropolitan area Adelaide, South Australia. Trained on thermal data Australian Government Data Directory, captures pixel-level variations across diverse landscapes, including densely built areas, suburban zones, green spaces. Achieving low Mean Squared Error (MSE) 0.0029 processing each map less than 30 seconds, demonstrates exceptional computational efficiency. The model, an AI agent, offers scalable tool supporting real-time assessments facilitating targeted mitigation efforts. By bridging gap between advanced geospatial modelling practical planning, it enables data-driven decisions enhance climate resilience, optimise infrastructure, improve rapidly urbanising regions. approach highlights transformative potential addressing challenges, delivering precise actionable insights support sustainable climate-adaptive

Язык: Английский

Процитировано

1
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

и другие.

Опубликована: Апрель 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.

Язык: Английский

Процитировано

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

и другие.

International Journal of Thermal Sciences, Год журнала: 2024, Номер 209, С. 109519 - 109519

Опубликована: Ноя. 9, 2024

Язык: Английский

Процитировано

5
Performance Evaluation of Machine Learning Models for Predicting Energy Consumption and Occupant Dissatisfaction in Buildings DOI Creative Commons
Haidar Hosamo, Silvia Mazzetto

Buildings, Год журнала: 2024, Номер 15(1), С. 39 - 39

Опубликована: Дек. 26, 2024

This study evaluates the performance of 15 machine learning models for predicting energy consumption (30–100 kWh/m2·year) and occupant dissatisfaction (Percentage Dissatisfied, PPD: 6–90%), key metrics optimizing building performance. Ten evaluation metrics, including Mean Absolute Error (MAE, average prediction error), Root Squared (RMSE, penalizing large errors), coefficient determination (R2, variance explained by model), are used. XGBoost achieves highest accuracy, with an MAE 1.55 kWh/m2·year a PPD 3.14%, alongside R2 values 0.99 0.97, respectively. While these highlight XGBoost’s superiority, its margin improvement over LightGBM (energy MAE: 2.35 kWh/m2·year, 3.89%) is context-dependent, suggesting application in high-precision scenarios. ANN excelled at predictions, achieving lowest (1.55%) Percentage (MAPE: 4.97%), demonstrating ability to model complex nonlinear relationships. modeling advantage contrasts LightGBM’s balance speed making it suitable computationally constrained tasks. In contrast, traditional like linear regression KNN exhibit high errors (e.g., 17.56 17.89%), underscoring their limitations respect capturing complexities datasets. The results indicate that advanced methods particularly effective owing intricate relationships manage high-dimensional data. Future research should validate findings diverse real-world datasets, those representing varying types climates. Hybrid combining interpretability precision ensemble or neural be explored. Additionally, integrating techniques digital twin platforms could address real-time optimization challenges, dynamic behavior time-dependent consumption.

Язык: Английский

Процитировано

3
Research on Climate Response Strategies for Traditional Dwellings Based on Shapley Additive Explanations and Machine Learning DOI
Xinyi Zhang, Gongyu Hou, Dandan Wang

и другие.

Опубликована: Янв. 1, 2025

Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI

Язык: Английский

Процитировано

0