探索精确的机器学习模型,快速估计各种能量材料的稳定性
Qiaolin Gou1, Jing Liu1, Haoming Su1
1College of Chemistry, Sichuan University, Chengdu 610064, China.
iScience
|March 25, 2024
概括
开发精确的机器学习模型对于能量材料 (EMs) 是至关重要的. 这项研究引入了一种新的XGBoost模型来预测键解离能 (BDE),增强各种EMS的稳定性评估.
科学领域:
- 材料科学 材料科学 材料科学
- 计算化学计算化学
- 化学工程是化学工程的重要组成部分.
背景情况:
- 高能量和低灵敏度是新能源材料 (EMs) 的关键目标.
- 目前缺乏准确和快速的方法来评估各种EM的稳定性.
- 键解离能 (BDE) 是评估电磁稳定性的关键参数.
研究的目的:
- 开发一个高度准确的机器学习 (ML) 模型来预测EM的BDE.
- 为培训和验证ML模型建立可靠和代表性的数据集.
- 改进EM稳定性的表征和预测.
主要方法:
- 使用778种实验能量化合物和量子力学计算构建了一个全面的BDE数据集.
- 开发一种混合特征表示,将本地债券信息与全球结构特征相结合.
- 应用对差分回归作为数据增强技术,以增强数据集多样性并减少错误.
- 使用XGBoost算法用于ML预测模型.
主要成果:
- XGBoost模型实现了BDE的高预测准确性,R2为0.98和平均绝对误差 (MAE) 为8.8kJ mol-1.1.
- 混合特征表示有效地捕获了BDE预测的基本特征.
- 配对差异回归提高了模型的稳定性和数据的实用性.
- 开发的模型显著优于其他竞争性ML模型.
结论:
- 开发的ML模型提供了一种快速而准确的方法,通过BDE预测来评估EM稳定性.
- 这种方法有助于设计和发现具有更好的安全性和性能特征的新能源材料.
- 该方法为能量材料的计算选提供了一个有价值的工具.
更多相关视频
08:47Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
Published on: February 9, 2024
1.4K
10:25Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements
Published on: June 28, 2016
10.6K
相关概念视频
Strain-Energy Density
400
Understanding the strain energy density in materials under axial load is crucial for evaluating their mechanical behavior and durability. When a rod is subjected to such a load, it elongates and stores energy, known as strain energy, as potential energy within the material. This energy is measured in terms of energy per unit volume.
In the elastic region of a material, the relationship between the stress and the strain is linear and follows Hooke's Law. The strain energy density in this...
In the elastic region of a material, the relationship between the stress and the strain is linear and follows Hooke's Law. The strain energy density in this...
400
Atomic Emission Spectroscopy: Overview
2.1K
Atomic emission spectroscopy (AES) is an analytical technique used to determine the elemental composition of a sample by analyzing the light emitted from excited atoms. In AES, atoms in a sample are excited to higher energy levels by thermal energy from high-temperature sources, such as plasma, arcs, or sparks. When these excited atoms return to lower energy states, they emit light at specific wavelengths characteristic of each element. The resulting atomic emission spectrum, which consists of...
2.1K
Survival Tree
84
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
84
Atomic Emission Spectroscopy: Lab
161
AES is a powerful analytical technique, especially effective when used with plasma sources, producing abundant spectra in characteristic emission lines. The Inductively Coupled Plasma (ICP), in particular, yields superior quantitative analytical data due to its high stability, low noise, low background, and minimal interferences under optimal experimental conditions. However, newer air-operated microwave sources are emerging as promising alternatives that could be more cost-effective than...
161
