arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.07218cs.LGcs.CV
收藏

基于深度学习的物理感知下采样用于可扩展洪水建模

Physics-Aware Downsampling with Deep Learning for Scalable Flood Modeling

Google Research(谷歌研究院);Technion - Israel Institute of Technology(以色列理工学院)

Niv Giladi, Zvika Ben-Haim, Sella Nevo, Yossi Matias, Daniel Soudry

摘要:

背景:洪水是世界上最常见的自然灾害,影响到数亿人的生活。因此,洪水预报是一项至关重要的工作,通常使用物理水流模拟来实现,该模拟依赖于准确的地形高程图。然而,这样的模拟,基于求解偏微分方程,是计算上禁止的大规模。这种可扩展性问题通常使用高程地图的粗网格表示来缓解,尽管这种表示可能会扭曲关键的地形细节,导致模拟中的显著不准确。贡献:我们训练一个深度神经网络来执行地形地图的物理信息下采样:我们优化地形地图的粗网格表示,以便洪水预测将匹配精细网格解决方案。为了使学习过程成功,我们专门为此任务配置了一个数据集。我们证明,用这种方法,它是可能实现显着降低计算成本,同时保持一个准确的解决方案。本文附带了一个参考实现以及用于数据集复制的文档和代码。

英文摘要:

Background: Floods are the most common natural disaster in the world, affecting the lives of hundreds of millions. Flood forecasting is therefore a vitally important endeavor, typically achieved using physical water flow simulations, which rely on accurate terrain elevation maps. However, such simulations, based on solving partial differential equations, are computationally prohibitive on a large scale. This scalability issue is commonly alleviated using a coarse grid representation of the elevation map, though this representation may distort crucial terrain details, leading to significant inaccuracies in the simulation. Contributions: We train a deep neural network to perform physics-informed downsampling of the terrain map: we optimize the coarse grid representation of the terrain maps, so that the flood prediction will match the fine grid solution. For the learning process to succeed, we configure a dataset specifically for this task. We demonstrate that with this method, it is possible to achieve a significant reduction in computational cost, while maintaining an accurate solution. A reference implementation accompanies the paper as well as documentation and code for dataset reproduction.

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。

↑