arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.08482cs.CVcs.NE
收藏

一种用于平均辐射温度建模的多模态物理信息神经网络方法

A Multimodal Physics-Informed Neural Network Approach for Mean Radiant Temperature Modeling

School of Computing and Augmented Intelligence, Arizona State University(亚利桑那州立大学计算与增强智能学院);College of Architecture, Kuwait University(科威特大学建筑学院);School of Arts, Media and Engineering, Arizona State University(亚利桑那州立大学艺术、媒体与工程学院)

Pouya Shaeri, Saud AlKhaled, Ariane Middel

AI总结:

本文提出一种融合短波与长波辐射建模的多模态物理信息神经网络方法,利用气象、建成环境和鱼眼图像遮阳数据提升平均辐射温度预测精度,最佳配置RMSE为3.50、$R^2$为0.88,优于传统深度学习模型。

摘要:

室外热舒适性是城市宜居性的关键决定因素,尤其是在炎热沙漠气候中,极端高温对公共健康、能源消耗和城市规划构成挑战。平均辐射温度($T_{mrt}$)是评估室外热舒适性的关键参数,特别是在辐射动态显著影响人体热暴露的城市环境中。传统的$T_{mrt}$估算方法依赖于现场测量和计算模拟,两者均资源密集。本研究引入了一种物理信息神经网络(PINN)方法,将短波和长波辐射建模与深度学习技术相结合。通过利用包含气象数据、建成环境特征以及鱼眼图像衍生的遮阳信息的多模态数据集,我们的模型在保持物理一致性的同时提高了预测精度。我们的实验结果表明,所提出的PINN框架优于传统深度学习模型,最佳配置实现了3.50的RMSE和0.88的$R^2$。该方法凸显了物理信息机器学习在弥合计算建模与实际应用之间差距方面的潜力,为城市热舒适性评估提供了一种可扩展且可解释的解决方案。

英文摘要:

Outdoor thermal comfort is a critical determinant of urban livability, particularly in hot desert climates where extreme heat poses challenges to public health, energy consumption, and urban planning. Mean Radiant Temperature ($T_{mrt}$) is a key parameter for evaluating outdoor thermal comfort, especially in urban environments where radiation dynamics significantly impact human thermal exposure. Traditional methods of estimating $T_{mrt}$ rely on field measurements and computational simulations, both of which are resource intensive. This study introduces a Physics-Informed Neural Network (PINN) approach that integrates shortwave and longwave radiation modeling with deep learning techniques. By leveraging a multimodal dataset that includes meteorological data, built environment characteristics, and fisheye image-derived shading information, our model enhances predictive accuracy while maintaining physical consistency. Our experimental results demonstrate that the proposed PINN framework outperforms conventional deep learning models, with the best-performing configurations achieving an RMSE of 3.50 and an $R^2$ of 0.88. This approach highlights the potential of physics-informed machine learning in bridging the gap between computational modeling and real-world applications, offering a scalable and interpretable solution for urban thermal comfort assessments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑