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 2512.17877physics.ao-phcs.LGphysics.flu-dyn
收藏

通过自动微分动态核心学习垂直坐标

Learning vertical coordinates via automatic differentiation of a dynamical core

Centre pour l’étude et la simulation du climat à l’échelle régionale (ESCER), Département des Sciences de la Terre et de l’Atmosphère, Université du Québec à Montréal(区域气候研究与模拟中心(ESCER)、地球科学与大气科学系、魁北克大学蒙特利尔分校);PIMS, Department of Computer Science, University of Saskatchewan(PIMS、计算机科学系、萨斯喀彻温大学);Department of Mathematics and Statistics, Memorial University of Newfoundland(数学与统计学系、纽芬兰纪念大学)

Tim Whittaker, Seth Taylor, Elsa Cardoso-Bihlo, Alejandro Di Luca, Alex Bihlo

AI总结:

本研究提出了一种基于自动微分的可学习垂直坐标系统,用于优化大气模型中的网格结构,减少计算误差并提高数值稳定性。

摘要:

地形跟随坐标在大气模型中常常会将其网格结构印刻在解中,尤其是在陡峭地形上,扭曲的坐标层会产生虚假的水平和垂直运动。标准方法,如混合或SLEVE坐标,通过使用由启发式尺度参数控制的解析衰减函数来减轻这些误差,这些参数通常通过手动调整和事前固定。在本工作中,我们提出了一种框架,将参数化的垂直坐标系统作为可学习的组件嵌入到可微的动态核心中。我们开发了一个端到端的可微数值求解器,用于在阿拉卡瓦C网格上求解二维非静力 Euler 方程,并引入了一种基于积分变换神经网络的 NEUral Vertical Enhancement(NEUVE)地形跟随坐标,该坐标保证单调性。我们方法的一个关键特点是使用自动微分来计算精确的几何度量项,从而消除与有限差分坐标导数相关的截断误差。通过将模拟误差通过时间积分与参数化耦合,我们的公式找到了一种在底层物理和数值计算方面都优化的网格结构。使用几个标准测试,我们证明这些学习的坐标在非线性统计基准中将均方误差降低了1.4到2倍,并在陡峭地形上消除了虚假的垂直速度条纹。

英文摘要:

Terrain-following coordinates in atmospheric models often imprint their grid structure onto the solution, particularly over steep topography, where distorted coordinate layers can generate spurious horizontal and vertical motion. Standard formulations, such as hybrid or SLEVE coordinates, mitigate these errors by using analytic decay functions controlled by heuristic scale parameters that are typically tuned by hand and fixed a priori. In this work, we propose a framework to define a parametric vertical coordinate system as a learnable component within a differentiable dynamical core. We develop an end-to-end differentiable numerical solver for the two-dimensional non-hydrostatic Euler equations on an Arakawa C-grid, and introduce a NEUral Vertical Enhancement (NEUVE) terrain-following coordinate based on an integral transformed neural network that guarantees monotonicity. A key feature of our approach is the use of automatic differentiation to compute exact geometric metric terms, thereby eliminating truncation errors associated with finite-difference coordinate derivatives. By coupling simulation errors through the time integration to the parameterization, our formulation finds a grid structure optimized for both the underlying physics and numerics. Using several standard tests, we demonstrate that these learned coordinates reduce the mean squared error by a factor of 1.4 to 2 in non-linear statistical benchmarks, and eliminate spurious vertical velocity striations over steep topography.

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。

↑