一个可解释和可转移的深度学习框架,用于通过整合视觉转换器和U-Net来进行时空城市洪水预测
Jingyu Qiu1, Lei Cheng1, Lihao Zhou1
1State Key Laboratory of Water Resources Engineering and Management, Wuhan University, Wuhan 430072, China; Hubei Provincial Key Lab of Water System Science for Sponge City Construction, Wuhan University, Wuhan 430072, China.
Water research
|February 9, 2026
概括
一个新的混合深度学习模型,ViTUN,提高了城市洪水预测的准确性和可转移性. 该框架改善了实时预测,以更好地管理洪水风险和预警系统.
科学领域:
- 环境科学 环境科学
- 人工智能的人工智能
- 水文学的水文学
背景情况:
- 城市洪水是由于气候变化和城市化而日益严重的威胁.
- 当前的预测模型在复杂的城市环境中缺乏物理可信性和可转移性.
研究的目的:
- 推出ViTUN,这是一个混合深度学习框架,结合了Vision Transformer和U-Net.
- 为了捕捉不同条件下的时空洪水传播特征.
- 提高城市洪水预测模型的准确性和可转移性.
主要方法:
- 开发了ViTUN,这是一个混合深度学习框架,集成了Vision Transformer和U-Net.
- 使用水力动力学模拟数据对中国岳阳市的城市洪水进行培训和评估ViTUN.
- 使用Grad-CAM进行模型解释性分析.
主要成果:
- 在城市洪水水深预测方面,ViTUN显著优于U-Net (例如,CSI高10.2%,MAE低53.7%).
- 维表现出强大的可转移到未经培训的地区,平均R2为0.940.
- 解释性分析显示,ViTUN专注于关键的洪水地区和城市特征.
结论:
- 维为城市洪水预测提供了一个快速,可解释和可转移的解决方案.
- 该模型具有实时预警和有效的洪水风险管理的巨大潜力.
- 维推进了水文危险评估中的数据驱动方法.
相关概念视频
Responses to Drought and Flooding
12.1K
Water plays a significant role in the life cycle of plants. However, insufficient or excess of water can be detrimental and pose a serious threat to plants.
12.1K
Vision
60.3K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
60.3K
Color Vision
1.5K
Color perception begins in the retina, the light-sensitive layer at the back of the eye. Two main theories explain how colors are seen: the trichromatic theory and the opponent-process theory. The trichromatic theory, proposed by Thomas Young in 1802 and extended by Hermann von Helmholtz in 1852, suggests that color vision is based on three types of cone receptors in the retina. These cones are sensitive to different but overlapping ranges of wavelengths corresponding to red, blue, and green.
1.5K
Predicting Molecular Geometry
46.1K
VSEPR Theory for Determination of Electron Pair Geometries
46.1K
Bacterial Transformation
60.1K
In 1928, bacteriologist Frederick Griffith worked on a vaccine for pneumonia, which is caused by Streptococcus pneumoniae bacteria. Griffith studied two pneumonia strains in mice: one pathogenic and one non-pathogenic. Only the pathogenic strain killed host mice.
Griffith made an unexpected discovery when he killed the pathogenic strain and mixed its remains with the live, non-pathogenic strain. Not only did the mixture kill host mice, but it also contained living pathogenic bacteria that...
Griffith made an unexpected discovery when he killed the pathogenic strain and mixed its remains with the live, non-pathogenic strain. Not only did the mixture kill host mice, but it also contained living pathogenic bacteria that...
60.1K
Prediction Intervals
3.4K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
3.4K


