camlab-ethz/GCE-RT

---
license: cc-by-nc-4.0
---

# Short Description

Based on the compressible Euler equations with gravitation, this dataset contains trajectories of the Rayleigh-Taylor problem, see https://arxiv.org/abs/2405.19101.
It also contains a passive tracer that is carried by the flow.

# Dimensions

The assembled NetCDF file has a **single** variable called *solution* with dimensionality
- 1260 (number of trajectories)
- 11 (time steps)
- 6 (density, horizontal velocity, vertical velocity, pressure, passive tracer, gravitational potential)
- 128 (x-dim)
- 128 (y-dim)

It was simulated on the unit square up to T=5 and saved as uniformly spaced in space and time.

# Train/Val/Test-split

1030/100/130 trajectories

# Download & Assembly

The dataset can be downloaded, e.g., via `huggingface-cli download`.

After download, the chunked data can be assembled into a single NetCDF file using the provided `assemble_data.py` script.
Use it as follows:
```bash
python assemble_data.py --input_dir . --output_file GCE-RT.nc
```

原始信息汇总

数据集概述

数据集内容

• 基于可压缩欧拉方程与重力作用，该数据集包含Rayleigh-Taylor问题的轨迹数据，详见arXiv论文。
• 数据集还包含一个随流体流动的被动示踪剂。

数据集结构

• 数据集为一个NetCDF文件，包含名为solution的单一变量，具有以下维度：
  • 1260个轨迹
  • 11个时间步长
  • 6个物理量（密度、水平速度、垂直速度、压力、被动示踪剂、重力势）
  • x方向128个点
  • y方向128个点

模拟细节

• 模拟在单位正方形区域内进行，时间上限为T=5，数据在空间和时间上均匀分布。

数据分割

• 数据集分为训练集、验证集和测试集，分别包含1030、100和130个轨迹。

数据下载与组装

• 数据可通过huggingface-cli download等方式下载。
• 下载后，使用提供的assemble_data.py脚本将分块数据组装成单一的NetCDF文件，命令如下： bash python assemble_data.py --input_dir . --output_file GCE-RT.nc