文章摘要
基于UNet-KAN-SR模型的城市积涝高效智能预报
Efficient Intelligent Urban Inundation Forecasting Based on UNet-KAN-SR
投稿时间:2025-08-16  修订日期:2026-01-02
DOI:
中文关键词: 城市内涝预测  深度学习  时空预测  超分辨率模型  北京城市副中心
英文关键词: urban waterlogging forecasting  deep learning  spatio-temporal prediction  super-resolution model  Beijing Municipal Administrative Center
基金项目:国家自然科学基金项目(面上项目,重点项目,重大项目),国家重点基础研究发展计划(973计划)
作者单位邮编
陈耀明 香港大学土木工程系 999077
李瑞栋* 清华大学水利水电工程系 100084
陈骥 香港大学土木工程系 
倪广恒 清华大学水利水电工程系 
摘要点击次数: 15
全文下载次数: 0
中文摘要:
      伴随着全球气候变化,在经历高速城镇化进程之后,城市积涝灾害趋多趋强,使得快速积涝预测成为研究热点问题。相较于传统数值模拟,基于深度学习的人工智能模拟方法能有效提升计算效率,但因GPU计算显存有限而易遭遇模型训练瓶颈。鉴于此,本研究提出了一种基于UNet-KAN-SR模型的城市积涝高效智能预报方法,先利用UNet-KAN模块学习低分辨率积涝分布的时空演变规律,后利用超分辨率SR模块与高分辨率下垫面信息,逐步将低分辨率积涝分布映射为高分辨率积涝分布,从而利用时空解耦在保障时空模拟精度的同时有效降低智能模型训练的计算资源需求。测试降雨情景的验证结果表明,UNet-KAN-SR模型能在3分钟内完成未来3小时积涝分布预报,均方根误差为9 cm、命中率达0.84,具备较高的计算精度与效率。相较于已有智能模型常用的卷积层,UNet-KAN-SR模型引入的KAN层可显著提升模型对积涝时空演变过程的非线性建模能力,使均方根误差降低10%。此外,本研究发现高分辨率下垫面信息能显著提升智能模型对积涝分布的预测能力且不同类型的下垫面信息所能取得的提升幅度相近,由此说明在构建智能模型时,可通过优选输入下垫面特征组合,有效提升模型训练速度并控制建模成本,实现高效智能预报。
英文摘要:
      With global climate change and accelerating urbanization, urban waterlogging disasters have be-come increasingly frequent and severe, making rapid waterlogging forecasting a key research focus. Compared with traditional numerical simulation methods, deep-learning-based artificial intelligence (AI) models can significantly improve computational efficiency. However, they often encounter training bottlenecks due to limited GPU memory. To address this, this study proposes an efficient AI urban waterlogging forecasting model named as UNet-KAN-SR. This model first employs the UNet-KAN module to efficiently simulate the spatio-temporal evolution of waterlogging over low-resolution grids, and then leverages the SR (super-resolution) module, along with high-resolution surface information, to progressively map the low-resolution waterlogging distribution to high-resolution distribution. This spatiotemporal decoupling strategy can ensure simulation accuracy while substantially reducing the computational resources required for training AI models. Experi-mental results demonstrate that the UNet-KAN-SR model can simulate a 3-hour waterlogging dis-tribution within 3 minutes, achieving a root mean square error (RMSE) of 9 cm and a probability of detection (POD) of 0.84, demonstrating high accuracy and computational efficiency. Further analy-sis reveals that the integration of the KAN module can significantly enhance the model’s capability to capture nonlinear flood dynamics when compared with common CNN modules, reducing RMSE by 10%. Furthermore, this study finds that incorporating high-resolution features, such as surface topography, building coverage ratio, and land use, can significantly improve the simulation perfor-mance but performance improvement is similar under different feature combinations. This indicates that by optimizing the combination of input features during AI model construction, training speed can be enhanced, modeling costs controlled, and efficient intelligent forecasting achieved.
  查看/发表评论  下载PDF阅读器
关闭