通过空间原子相互作用学习直接预测气体吸附
Jiyu Cui1, Fang Wu2,3,4, Wen Zhang2
1Key Laboratory of Biomass Chemical Engineering of Ministry of Education, College of Chemical and Biological Engineering, Zhejiang University, 310012, Hangzhou, China.
DeepSorption是一种新的深度学习模型,可以从原子结构直接准确地预测材料吸附性质. 这加速了用于可持续分离和碳捕获的材料的发现.
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
- 人工智能的人工智能
背景情况:
- 晶体多孔材料中的物理吸收是可持续分离,温室气体捕获和能量储存的关键.
- 目前选这些材料的方法很慢,由于缺乏先进的预测模型,缺乏精度.
研究的目的:
- 开发一个端到端的深度学习模型,用于准确和快速预测晶体多孔材料中的吸附.
- 为了使直接的结构吸附预测只使用原子坐标和元素类型.
主要方法:
- 介绍DeepSorption,一个空间原子交互学习网络.
- 开发Matformer模块以捕捉全球结构和局部原子相互作用.
- 使用原子坐标和化学元素类型作为预测的直接输入.
主要成果:
- 深度吸附实现了准确和快速的直接结构吸附预测.
- 该模型表明,与CGCNN和基于描述符的机器学习等现有方法相比,平均绝对误差减少了20-35%.
- 预测准确度超过了大法典蒙特卡洛模拟.
结论:
- 深度吸收 (DeepSorption) 为预测晶体材料的物理化学性质提供了一个通用框架.
- 该模型在原子间相互作用的基础上确保了广泛的适用性和理解.
- 为关键应用加速新型多孔材料的发现和设计.
更多相关视频
11:38In situ FTIR Spectroscopy as a Tool for Investigation of Gas/Solid Interaction: Water-Enhanced CO2 Adsorption in UiO-66 Metal-Organic Framework
Published on: February 1, 2020
07:23Experimental Study of the Relationship Between Particle Size and Methane Sorption Capacity in Shale
Published on: August 2, 2018
相关概念视频
Atomic Absorption Spectroscopy: Interference
Spectral interference occurs when signals from other elements or molecules overlap with the analyte signal, falsely elevating or masking the analyte's absorbance. This interference can be corrected using Zeeman,...
Predicting Molecular Geometry
Atomic Absorption Spectroscopy: Atomization Methods
Atomic Absorption Spectroscopy: Lab
Solutions containing organic solvents, such as low-molecular-mass alcohols, esters, or ketones, enhance absorbances by increasing...
Atomic Absorption Spectroscopy: Overview
When irradiated by EMR of a particular wavelength, these...
Gas Chromatography: Introduction
In GC, a sample is vaporized and mixed with an inert carrier gas (the mobile phase), which transports it through a...
