MPF.2021.2.8

This dataset contains the MPF.2021.2.8 data used to train the m3gnet model reported in `https://arxiv.org/abs/2202.02450` <br> I have split the dataset into two pickle files. To load the data, you can use example code as below. <br> ``` import pickle with open('block_0_cif.p', 'rb') as f: data = pickle.load(f) <br> with open('block_1_cif.p', 'rb') as f: data.update(pickle.load(f)) ``` <br> where `data` will be a dictionary with `material_id` as the key and an inner dictionary as the value. <br> The inner dictionary contains the snapshots of this `material_id`, with the following keys. ``` - structure - energy - force - stress - id ``` The `structure` is a list of cif files generated by pymatgen. <br> Each id in the `id` list is of format `material_id-calc_id-ionic_step_id`, where `calc_id` is 0 (second) or 1 (first) in the double relaxation process. <br> The `stress` here is the raw output from VASP, meaning that it is really the negative stress using the convention in our paper. Hence to train the model, please multiply stress with -0.1 (kBa to GPa and change sign) <br> The units for energy, force and stress in the data are eV, eV/A, and kBa. Remember to convert the stress to GPa and take the negative sign to work with m3gnet training.

本数据集包含用于训练论文`https://arxiv.org/abs/2202.02450`中报道的m3gnet模型的MPF.2021.2.8数据集。本数据集已被拆分为两个Pickle格式文件，加载数据可使用如下示例代码：
python
import pickle
with open('block_0_cif.p', 'rb') as f:
data = pickle.load(f)
with open('block_1_cif.p', 'rb') as f:
data.update(pickle.load(f))

其中`data`为以`material_id`（材料ID）作为键、内部字典作为值的字典。该内部字典存储了对应`material_id`的结构快照，包含以下键：

- structure：晶体结构
- energy：能量
- force：受力
- stress：应力
- id：ID列表

其中`structure`为由pymatgen生成的CIF（晶体信息文件，Crystallographic Information Framework）文件列表。`id`列表中的每个ID格式为`material_id-calc_id-ionic_step_id`（其中`ionic_step_id`为离子步ID），其中`calc_id`在双弛豫过程中取值为0（第二次弛豫）或1（第一次弛豫）。
此处的`stress`为VASP的原始输出结果，按照本文的研究约定，该输出实际为负应力。因此若要训练模型，请将应力值乘以-0.1以完成单位转换（将kBa（千巴）转换为GPa（吉帕斯卡））并修正符号。
数据中能量、受力与应力的单位分别为eV（电子伏特）、eV/Å（电子伏特每埃）与kBa（千巴）。请务必将应力转换为GPa（吉帕斯卡）并取反符号，以适配m3gnet模型的训练。

搜集汇总

背景与挑战

背景概述

该数据集包含用于训练m3gnet模型的材料数据，以字典形式存储，包含结构、能量、力、应力等关键信息，需注意单位转换和符号处理。数据来源于VASP计算，适用于功能材料和物理性质研究。