论文标题
在海面的拉格朗日漂移模拟的深度学习
Deep learning for Lagrangian drift simulation at the sea surface
论文作者
论文摘要
我们解决了地球物理动力学中的拉格朗日漂移模拟，并探讨了深度学习方法，以在计算复杂性和错误传播方面克服基于最新模型和马尔可夫方法的已知限制。我们介绍了一种新颖的建筑，称为Driftnet，灵感来自Lagrangian Dynamics的Eulerian Fokker-Planck代表。在海面的拉格朗日漂移模拟的数值实验证明了漂移网络的相关性。最先进的计划。从漂移网络的完全跨跨度的性质中受益，我们通过神经反转探索如何诊断模型源性速度W.R.T.真正的漂流者轨迹。
We address Lagrangian drift simulation in geophysical dynamics and explore deep learning approaches to overcome known limitations of state-of-the-art model-based and Markovian approaches in terms of computational complexity and error propagation. We introduce a novel architecture, referred to as DriftNet, inspired from the Eulerian Fokker-Planck representation of Lagrangian dynamics. Numerical experiments for Lagrangian drift simulation at the sea surface demonstrates the relevance of DriftNet w.r.t. state-of-the-art schemes. Benefiting from the fully-convolutional nature of Drift-Net, we explore through a neural inversion how to diagnose modelderived velocities w.r.t. real drifter trajectories.
