High-Throughput Screening of Photocatalytic Metal–Organic Frameworks for CO2 Reduction Using Relational Data Extraction and Hierarchical Machine Learning

工作流程 人工智能 机器学习 化学 推论 降维 光催化 还原(数学) 卷积神经网络 计算机科学 数据挖掘 图形 人工神经网络 关系数据库 校准 深度学习 参考数据 标识符
作者
Xiao Niu,Yan Liu,Yong Cui,Jianwen Jiang
出处
期刊:Journal of the American Chemical Society [American Chemical Society]
标识
DOI:10.1021/jacs.6c14994
摘要

Abstract Photocatalytic carbon dioxide reduction (CO2RR) over metal–organic frameworks (MOFs) is governed by both framework features and reaction conditions, which complicate catalyst discovery and render general design rules difficult to establish. In this study, we develop a synergistic machine-learning workflow to integrate literature data extraction, electronic-property prediction, and hierarchical classification for prioritizing MOF photocatalysts. First, a literature-derived record-level data set containing catalyst compositions, structural descriptors, reaction conditions, and catalytic outcomes was curated through large language model (LLM)-assisted relation extraction followed by manual verification. Then, a transfer-learning crystal graph convolutional neural network (CGCNN) model was trained for band gap prediction at the Heyd-Scuseria-Ernzerhof screened hybrid functional (HSE06) level, achieving a mean absolute error (MAE) of 0.31 eV against reference HSE06 calculations. Subsequently, a physically constrained multitask framework was employed to predict electron affinity (EA) and ionization potential (IP) for thermodynamic prescreening. Three record-level classifiers were constructed for activity screening (C1), performance classification (C2), and product selectivity prediction (C3). When applied to the Computation-Ready, Experimental (CoRE) MOF database under standardized gas- and liquid-phase inference settings, the workflow prioritized 639 primary candidates, with most assigned to CO formation. Probability calibration and applicability-domain analysis further identified 166 of these candidates (25.98%) as a more stringent calibrated, in-domain subset. Overall, this study provides a practical data-driven workflow for condition-resolved prioritization of MOF photocatalysts and analysis of descriptor-level trends associated with photocatalytic CO2RR.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Hw完成签到,获得积分10
刚刚
虞山小王子完成签到,获得积分20
刚刚
1秒前
研友_VZG7GZ的应助被平常的雁凡采纳,获得10
1秒前
马家沟大水鸭完成签到,获得积分10
1秒前
RegSequ完成签到,获得积分10
1秒前
阿申爱乐的应助被CharlieMason820采纳,获得30
2秒前
无极微光的应助被lolly采纳,获得20
2秒前
kukuluo完成签到,获得积分10
2秒前
2秒前
爱学习的小i完成签到 ,获得积分10
2秒前
tuoeryao完成签到,获得积分10
2秒前
ccshi完成签到,获得积分10
2秒前
3秒前
NexusExplorer的应助被欣喜紫霜采纳,获得10
3秒前
丁一完成签到,获得积分0
3秒前
una完成签到 ,获得积分10
3秒前
花开花落花无悔完成签到 ,获得积分10
3秒前
3秒前
czy完成签到,获得积分10
4秒前
封似狮完成签到,获得积分10
4秒前
yu完成签到,获得积分10
4秒前
4秒前
卢某某发布了新的文献求助10
4秒前
4秒前
追悟完成签到,获得积分10
4秒前
QTMX完成签到,获得积分20
4秒前
4秒前
宋宋syi完成签到 ,获得积分10
4秒前
科研通AI6.3的应助被无字诉题采纳,获得10
4秒前
ZiZi完成签到 ,获得积分10
5秒前
Firsterchao的应助被tszjw168采纳,获得10
5秒前
桃桃完成签到,获得积分10
6秒前
chancute完成签到,获得积分10
6秒前
方方完成签到,获得积分10
6秒前
兴奋代芙完成签到,获得积分10
7秒前
7秒前
Ken发布了新的文献求助10
7秒前
pw发布了新的文献求助10
7秒前
在水一方的应助被YJT采纳,获得10
8秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Social Psychology in the Real World 600
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8180488
求助须知:如何正确求助?哪些是违规求助? 9570437
关于积分的说明 21812406
捐赠科研通 7776516
什么是DOI,文献DOI怎么找? 3433277
关于科研通互助平台的介绍 2557516
邀请新用户注册赠送积分活动 2479162