Multi-fidelity, active learning strategies for exciton transfer among adsorbed molecules

吸附分子之间激子转移的多保真主动学习策略

基本信息

项目摘要

New materials for photochemical applications are essential, e.g., for the further development of renewable energy devices. The development of such material is nowadays tackled by experiments and by computer-driven molecular simulations. Ideally, the full design process including material screening and optimizations could be done in-silico. This, however, requires time-efficient, high-accuracy and easy-to-use software for the analysis of photochemical properties of molecular aggregates or more precisely their excitonic properties. The long-term goal of this project is to develop methods that will make such an analysis feasible, noting that current molecular simulations by means of quantum mechanics / molecular mechanics (QM/MM) methods are prohibitively expensive. A promising tool to overcome the computational challenges is the use of cheap to evaluate machine learning models, replacing expensive quantum chemical calculations in the simulation pipeline. However, the practical long-term success of this tool can only be guaranteed, if such machine learning models indeed achieve high accuracy predictions at moderate costs for the generation of the quantum chemical training data and can be constructed in a (semi-)automatic way. In this project, we develop a multi-fidelity, active learning approach for exciton transfer within molecular aggregates. Multi-fidelity machine learning promises to strongly reduce the number of required highly accurate and thereby computationally expensive training samples by using hierarchies of training data obtained at different quantum chemical theory levels, basis set sizes, etc. Further technical improvements will be achieved in the automatic selection of best possible training calculations (active learning) and the constructions of bi-molecular models, i.e. machine learning models for properties that depend on two molecules. The overall approach is applied for the analysis of a light-harvesting material based on a molecular aggregate. As an example for such an aggregate, we focus on porphyrin molecules adsorbed on clay surfaces which experimentally have shown to posses interesting light-harvesting properties. While this model application will certainly gain from our novel contributions, our interest is to further share our expertise and tools on multi-fidelity molecular machine learning and on QM/MM simulations within the priority program and beyond.
用于光化学应用的新材料至关重要,例如,进一步发展可再生能源设备。这种材料的开发现在通过实验和计算机驱动的分子模拟来解决。理想情况下,包括材料筛选和优化在内的整个设计过程可以在计算机上完成。然而,这需要高效的时间,高精度和易于使用的软件来分析分子聚集体的光化学性质,或者更准确地说,它们的激子性质。该项目的长期目标是开发使这种分析可行的方法,注意到目前通过量子力学/分子力学(QM/MM)方法进行的分子模拟过于昂贵。克服计算挑战的一个有前途的工具是使用廉价的机器学习模型来评估,取代模拟管道中昂贵的量子化学计算。然而,只有这样的机器学习模型确实以适度的成本实现了量子化学训练数据生成的高精度预测,并且可以以(半)自动的方式构建,才能保证该工具的实际长期成功。在这个项目中,我们开发了一个多保真度,主动学习方法的激子转移分子聚集体。多保真度机器学习通过使用在不同量子化学理论水平、基组大小等获得的训练数据的层次结构,有望大大减少所需的高度准确且因此计算昂贵的训练样本的数量。在自动选择最佳可能的训练计算方面将实现进一步的技术改进(主动学习)和双分子模型的构建,即用于依赖于两个分子的性质的机器学习模型。的整体方法被应用于基于分子聚集体的捕光材料的分析。作为这样的聚集体的一个例子,我们专注于吸附在粘土表面的卟啉分子,实验已经显示出有趣的捕光特性。虽然这个模型应用肯定会从我们的新贡献中获益,但我们的兴趣是进一步分享我们在多保真度分子机器学习和QM/MM模拟方面的专业知识和工具。

项目成果

期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

Professor Dr. Ulrich Kleinekathöfer其他文献

Professor Dr. Ulrich Kleinekathöfer的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

{{ truncateString('Professor Dr. Ulrich Kleinekathöfer', 18)}}的其他基金

Molecular modeling of spectroscopy and quantum phenomena in light-harvesting complexes
光捕获复合物中光谱和量子现象的分子建模
  • 批准号:
    226668712
  • 财政年份:
    2012
  • 资助金额:
    --
  • 项目类别:
    Research Grants
Simulation of ion transport and substrate translocation through nanopores
模拟通过纳米孔的离子传输和底物易位
  • 批准号:
    135618365
  • 财政年份:
    2009
  • 资助金额:
    --
  • 项目类别:
    Research Grants
Effects of time-dependent perturbations on the electron transport through single molecules
时间相关扰动对单分子电子传输的影响
  • 批准号:
    24982018
  • 财政年份:
    2006
  • 资助金额:
    --
  • 项目类别:
    Priority Programmes
Ab initio description of the quantum mechanics in light-harvesting complexes of purple bacteria
紫色细菌光捕获复合物中量子力学的从头计算
  • 批准号:
    18592143
  • 财政年份:
    2005
  • 资助金额:
    --
  • 项目类别:
    Research Grants
Brownian Dynamics Simulations including Explicit Atoms for Modeling Transport through Nanopores
布朗动力学模拟,包括用于模拟纳米孔传输的显式原子
  • 批准号:
    452270316
  • 财政年份:
  • 资助金额:
    --
  • 项目类别:
    Research Grants
Molecular modeling of charge transfer in heme-containing systems: a time-dependent view
含血红素系统中电荷转移的分子建模:时间依赖性观点
  • 批准号:
    533004272
  • 财政年份:
  • 资助金额:
    --
  • 项目类别:
    Research Grants
Computational nanopore redesign for the sensing of chiral peptide isomers
用于传感手性肽异构体的计算纳米孔重新设计
  • 批准号:
    539124018
  • 财政年份:
  • 资助金额:
    --
  • 项目类别:
    Research Grants
Excitation Energy Transfer in a Photosynthetic System with more than 100 Million Atoms
超过 1 亿个原子的光合作用系统中的激发能量转移
  • 批准号:
    466761712
  • 财政年份:
  • 资助金额:
    --
  • 项目类别:
    Research Grants

相似海外基金

Mechanisms for the high fidelity of translesion synthesis by Y-family DNA polymerases in human cells
人类细胞中 Y 家族 DNA 聚合酶高保真度跨损伤合成的机制
  • 批准号:
    10550540
  • 财政年份:
    2023
  • 资助金额:
    --
  • 项目类别:
Feasibility and fidelity of a gross motor-based physical activity intervention on cognitive variables in preschool-age children from low socioeconomic backgrounds
基于大运动的身体活动干预对来自低社会经济背景的学龄前儿童认知变量的可行性和保真度
  • 批准号:
    10591140
  • 财政年份:
    2023
  • 资助金额:
    --
  • 项目类别:
The CHESS (Community, Home-based Education, Screening Services) Strategy to increase cervical cancer control access for HIV positive women in Nigeria
CHESS(社区、家庭教育、筛查服务)战略旨在增加尼日利亚艾滋病毒阳性妇女获得宫颈癌控制的机会
  • 批准号:
    10693963
  • 财政年份:
    2022
  • 资助金额:
    --
  • 项目类别:
The Development and Evaluation of Enhanced Digital-Chemosensory-Based Olfactory Training for Remote Management of Substance Use Disorders (EDITOR)
用于药物使用障碍远程管理的增强型数字化学感应嗅觉训练的开发和评估(编辑)
  • 批准号:
    10469912
  • 财政年份:
    2022
  • 资助金额:
    --
  • 项目类别:
The CHESS (Community, Home-based Education, Screening Services) Strategy to increase cervical cancer control access for HIV positive women in Nigeria
CHESS(社区、家庭教育、筛查服务)战略旨在增加尼日利亚艾滋病毒阳性妇女获得宫颈癌控制的机会
  • 批准号:
    10541349
  • 财政年份:
    2022
  • 资助金额:
    --
  • 项目类别:
Transforming adolescent mental health through accessible, scalable, technology-supported small-group instruction
通过可获取、可扩展、技术支持的小组教学改变青少年心理健康
  • 批准号:
    10705076
  • 财政年份:
    2022
  • 资助金额:
    --
  • 项目类别:
Family Inclusive Childhood Obesity Treatment designed for Low Income and Hispanic Families
专为低收入和西班牙裔家庭设计的家庭包容性儿童肥胖治疗
  • 批准号:
    10460619
  • 财政年份:
    2021
  • 资助金额:
    --
  • 项目类别:
Digital adherence technologies to facilitate completion of short-course tuberculosis preventive therapy among people living with HIV
数字依从技术可促进艾滋病毒感染者完成短期结核病预防治疗
  • 批准号:
    10681475
  • 财政年份:
    2021
  • 资助金额:
    --
  • 项目类别:
Developing And Testing An Implementation Strategy For Active Learning To Promote Physical Activity In Children
制定和测试主动学习的实施策略以促进儿童的体育活动
  • 批准号:
    10396507
  • 财政年份:
    2021
  • 资助金额:
    --
  • 项目类别:
High Fidelity Dynamic Aeroelasticity Response Analysis and Active Vibration Attenuation and Control of High Precision Ground Antennas Subject to Aerodynamic Gust
气动阵风作用下高精度地面天线的高保真动态气动弹性响应分析及主动减振与控制
  • 批准号:
    530880-2018
  • 财政年份:
    2021
  • 资助金额:
    --
  • 项目类别:
    Collaborative Research and Development Grants
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了