论文标题
来自有限数据的重力电流重建的物理信息的神经网络
Physics-informed neural networks for gravity currents reconstruction from limited data
论文作者
论文摘要
本工作调查了使用有限的数据的3D重建物物理学神经网络（PINN）的使用。在Pinn上下文中，流场是通过训练神经网络重建的，该神经网络的目标函数会惩罚网络预测与观察到的数据之间的不匹配，并使用自动分化嵌入基础方程。这项研究依赖于规范锁交换配置的高保真数值实验。这使我们可以在几个训练数据库中定量基准测试PINNS重建功能，以模仿最新的实验测量技术的密度和速度。值得注意的是，采用光衰减技术（LAT）进行空间平均密度测量。根据两个标准，提出了针对PINS进行流动重建的最佳实验设置：实现复杂性和推断场的准确性。
The present work investigates the use of physics-informed neural networks (PINNs) for the 3D reconstruction of unsteady gravity currents from limited data. In the PINN context, the flow fields are reconstructed by training a neural network whose objective function penalizes the mismatch between the network predictions and the observed data and embeds the underlying equations using automatic differentiation. This study relies on a high-fidelity numerical experiment of the canonical lock-exchange configuration. This allows us to benchmark quantitatively the PINNs reconstruction capabilities on several training databases that mimic state-of-the-art experimental measurement techniques for density and velocity. Notably, spatially averaged density measurements by light attenuation technique (LAT) are employed for the training procedure. An optimal experimental setup for flow reconstruction by PINNs is proposed according to two criteria : the implementation complexity and the accuracy of the inferred fields.
