机器学习 预测离子电池电解质中的物理化学性质,使用主动学习应用到图形神经网络
Debojyoti Das1, Debdutta Chakraborty2
1Department of Chemistry and Biochemistry, Texas Tech University, Lubbock, Texas, USA.
Journal of computational chemistry
|December 26, 2024
概括
这项研究使用图形神经网络的积极学习来预测离子电池的性能,降低计算成本并改善电解质发现.
科学领域:
- 材料科学 材料科学 材料科学
- 计算化学的计算化学
- 储能 储能 储能 储能 储能 储能
背景情况:
- 准确预测物理化学性质对于优化离子电池 (LIB) 性能至关重要.
- 像密度函数理论 (DFT) 这样的传统方法对于大规模选是计算密集的.
研究的目的:
- 开发一种高效,准确的方法,使用主动学习和图形神经网络 (GNN) 来预测LIB属性.
- 为了降低在LIBs中的材料发现的计算成本和数据要求.
主要方法:
- 在图形神经网络 (GNN) 上应用主动学习来进行属性预测.
- 使用LIBE和MPcules数据集进行模型培训和验证.
- 为了模型的可解释性,使用了夏普利添加式解释 (SHAP).
主要成果:
- 在预测电子能量 (R-平方: 0.9977,MAE: 9.66 Ha) 和平均振动频率 (R-平方: 0.957,MAE: 13.94 cm-1) 中取得了高精度.
- 积极学习有效地减少了所需的训练数据大小,同时保持了预测准确性.
- SHAP分析确定了影响预测的关键特征,例如原子数和旋转倍数.
结论:
- 积极学习增强的GNN模型为预测LIB属性提供了可扩展和准确的解决方案.
- 这种方法加速了新型电解质的发现,以提高LIB性能.
- 该方法增强了计算材料科学中的预测能力和可解释性.
相关概念视频
01:07End Point Prediction: Gran Plot
169
A Gran plot is used to predict the equivalence volume or endpoint of a potentiometric or acid-base titration without reaching the endpoint. Typically, titration data is collected as a function of the titrant's volume up to a point less than the equivalence volume and then transformed into a linear format. The straight line is extended to the x-axis, indicating the necessary titrant volume to achieve the equivalence point.
For potentiometric titration, the Gran plot is created by plotting...
For potentiometric titration, the Gran plot is created by plotting...
169
03:12Batteries and Fuel Cells
26.6K
A battery is a galvanic cell that is used as a source of electrical power for specific applications. Modern batteries exist in a multitude of forms to accommodate various applications, from tiny button batteries such as those that power wristwatches to the very large batteries used to supply backup energy to municipal power grids. Some batteries are designed for single-use applications and cannot be recharged (primary cells), while others are based on conveniently reversible cell reactions that...
26.6K
02:54Trends in Lattice Energy: Ion Size and Charge
23.5K
An ionic compound is stable because of the electrostatic attraction between its positive and negative ions. The lattice energy of a compound is a measure of the strength of this attraction. The lattice energy (ΔHlattice) of an ionic compound is defined as the energy required to separate one mole of the solid into its component gaseous ions. For the ionic solid sodium chloride, the lattice energy is the enthalpy change of the process:
23.5K