Parameterized Geometries Flows Over Periodic Hills Dataset

本数据集由弗吉尼亚理工学院和州立大学的研究团队创建，包含了对不同坡度周期性山丘流动的直接数值模拟数据。数据集涵盖了从初始分离到大规模分离的流动范围，旨在为数据驱动的湍流模型开发和验证提供系统且连续变化的流动条件。通过这些数据，研究者可以训练机器学习模型，预测基于平均流动特性的雷诺应力各向异性，从而推动未来数据驱动湍流模型的发展和比较。

This dataset was created by a research team from Virginia Polytechnic Institute and State University (Virginia Tech), and contains direct numerical simulation (DNS) data of periodic hill flows with varying slope gradients. The dataset covers a range of flow conditions spanning from incipient flow separation to large-scale flow separation, aiming to provide systematically and continuously varied flow conditions for the development and validation of data-driven turbulence models. Researchers can leverage this dataset to train machine learning models that predict Reynolds stress anisotropy based on mean flow characteristics, thereby advancing the development and benchmarking of future data-driven turbulence models.