EAGER: XAISE: Explainable Artificial Intelligence for Science and Engineering
EAGER:XAISE:科学与工程领域的可解释人工智能
基本信息
- 批准号:2331329
- 负责人:
- 金额:$ 30万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2023
- 资助国家:美国
- 起止时间:2023-10-01 至 2025-09-30
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
The increasing availability of data from the first three paradigms of science (experiments, theory, and simulations), along with advances in artificial intelligence and machine learning (AI/ML) has offered unprecedented opportunities for accelerating scientific discoveries using data-driven science. In particular Deep Learning (DL) has emerged as a transformative technology for deriving insights from massive datasets in many scientific domains such as material science, life-science, drug design etc. However, interpretability and explainability of DL models remains a major issue and an open problem. The need for explainable AI is often crucial in science and engineering, with applications of national importance such as materials design, construction, transportation, health-sciences, energy storage, etc., where the cost of wrong decisions can be catastrophically large, making it critical to ensure that the model is not just quantitatively accurate but is in fact learning from the correct features, and learning things that make sense in an understandable manner. But an abstract view of explanability is extremely difficult, because explanation also requires context within the application domain. This project seeks to develop addresses explanability within the use of DL by incorporating and utilizing context from scientific application domains and by exploring traditional machine learning techniques. This project seeks to explore and investigate an approach of ML-DL integration to realize explainable AI in terms of the four NIST (National Institute of Standards and Technology) principles. The specific goals of this project are: to design, develop, and implement XAISE – a framework to enhance the explainability of AI models for science and engineering applications with minimal impact on accuracy; to adapt XAISE for heterogenous data types, e.g., numerical, images, etc.; to scale XAISE to be able to handle large, multi-dimensional data; and evaluate the applicability of XAISE for at least two application domains, including materials science and nanotechnology.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
来自前三种科学范式(实验、理论和模拟)的数据越来越多,沿着人工智能和机器学习(AI/ML)的进步,为使用数据驱动的科学加速科学发现提供了前所未有的机会。特别是深度学习(DL)已经成为一种变革性的技术,用于从许多科学领域(如材料科学,生命科学,药物设计等)的大量数据集中获得见解。然而,DL模型的可解释性和可解释性仍然是一个主要问题,也是一个悬而未决的问题。对可解释的人工智能的需求在科学和工程领域往往至关重要,其应用具有国家重要性,如材料设计,建筑,运输,健康科学,能源储存等,其中错误决策的成本可能是灾难性的,因此确保模型不仅在数量上准确,而且实际上从正确的特征中学习,并以可理解的方式学习有意义的东西至关重要。但是抽象地看待可扩展性是极其困难的,因为解释还需要应用程序域中的上下文。该项目旨在通过整合和利用科学应用领域的上下文以及探索传统的机器学习技术,在DL的使用中开发地址可重复性。该项目旨在探索和研究ML-DL集成的方法,以实现NIST(美国国家标准与技术研究所)四项原则的可解释AI。该项目的具体目标是:设计,开发和实施XAISE -一个框架,以增强科学和工程应用的AI模型的可解释性,同时对准确性的影响最小;使XAISE适应异构数据类型,例如,数字、图像等;扩展XAISE,使其能够处理大型多维数据;并评估XAISE在至少两个应用领域的适用性,包括材料科学和纳米技术。该奖项反映了NSF的法定使命,并通过使用基金会的知识价值和更广泛的影响审查标准进行评估,被认为值得支持。
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 }}
Alok Choudhary其他文献
MicroProcSim: A Software for Simulation of Microstructure Evolution
- DOI:
10.1007/s40192-025-00405-6 - 发表时间:
2025-06-23 - 期刊:
- 影响因子:2.500
- 作者:
Md Maruf Billah;Muhammed Nur Talha Kilic;Md Mahmudul Hasan;Zekeriya Ender Eger;Yuwei Mao;Kewei Wang;Alok Choudhary;Ankit Agrawal;Veera Sundararaghavan;Pınar Acar - 通讯作者:
Pınar Acar
Hybrid-LLM-GNN: integrating large language models and graph neural networks for enhanced materials property prediction
混合大语言模型与图神经网络:集成大语言模型和图神经网络以增强材料性能预测
- DOI:
10.1039/d4dd00199k - 发表时间:
2024-12-17 - 期刊:
- 影响因子:5.600
- 作者:
Youjia Li;Vishu Gupta;Muhammed Nur Talha Kilic;Kamal Choudhary;Daniel Wines;Wei-keng Liao;Alok Choudhary;Ankit Agrawal - 通讯作者:
Ankit Agrawal
A model for managing returns in a circular economy context: A case study from the Indian electronics industry
- DOI:
10.1016/j.ijpe.2022.108505 - 发表时间:
2022-07-01 - 期刊:
- 影响因子:10.000
- 作者:
Divya Choudhary;Fahham Hasan Qaiser;Alok Choudhary;Kiran Fernandes - 通讯作者:
Kiran Fernandes
Automated image segmentation for accelerated nanoparticle characterization
- DOI:
10.1038/s41598-025-01337-z - 发表时间:
2025-05-17 - 期刊:
- 影响因子:3.900
- 作者:
Alexandra L. Day;Carolin B. Wahl;Roberto dos Reis;Wei-keng Liao;Youjia Li;Muhammed Nur Talha Kilic;Chad A. Mirkin;Vinayak P. Dravid;Alok Choudhary;Ankit Agrawal - 通讯作者:
Ankit Agrawal
Dys-regulated phosphatidylserine externalization as a cell intrinsic immune escape mechanism in cancer
- DOI:
10.1186/s12964-025-02090-6 - 发表时间:
2025-03-11 - 期刊:
- 影响因子:8.900
- 作者:
Rachael Pulica;Ahmed Aquib;Christopher Varsanyi;Varsha Gadiyar;Ziren Wang;Trevor Frederick;David C. Calianese;Bhumik Patel;Kenneth Vergel de Dios;Victor Poalasin;Mariana S. De Lorenzo;Sergei V. Kotenko;Yi Wu;Aizen Yang;Alok Choudhary;Ganapathy Sriram;Raymond B. Birge - 通讯作者:
Raymond B. Birge
Alok Choudhary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('Alok Choudhary', 18)}}的其他基金
SHF: Medium: Collaborative Research: Scalable Algorithms for Spatio-temporal Data Analysis
SHF:中:协作研究:时空数据分析的可扩展算法
- 批准号:
1409601 - 财政年份:2014
- 资助金额:
$ 30万 - 项目类别:
Standard Grant
EAGER: Scalable Big Data Analytics
EAGER:可扩展的大数据分析
- 批准号:
1343639 - 财政年份:2013
- 资助金额:
$ 30万 - 项目类别:
Standard Grant
EAGER: Discovering Knowledge from Scientific Research Networks
EAGER:从科学研究网络中发现知识
- 批准号:
1144061 - 财政年份:2011
- 资助金额:
$ 30万 - 项目类别:
Standard Grant
Travel Support for Workshop: Reaching Exascale in this Decade to be Co-Located with International Conference on High-Performance Computing (HiPC 2010)
研讨会差旅支持:在这十年内达到百亿亿次规模,与高性能计算国际会议 (HiPC 2010) 同期举办
- 批准号:
1043085 - 财政年份:2010
- 资助金额:
$ 30万 - 项目类别:
Standard Grant
Collaborative Research: An Application Driven I/O Optimization Approach for PetaScale Systems and Scientific Discoveries
协作研究:针对 PetaScale 系统和科学发现的应用驱动 I/O 优化方法
- 批准号:
0938000 - 财政年份:2010
- 资助金额:
$ 30万 - 项目类别:
Standard Grant
Collaborative Research: Understanding Climate Change: A Data Driven Approach
合作研究:了解气候变化:数据驱动的方法
- 批准号:
1029166 - 财政年份:2010
- 资助金额:
$ 30万 - 项目类别:
Continuing Grant
Collaborative Research: CT-M: Hardware Containers for Software Components - Detection and Recovery at the Hardware/Software Interface
合作研究:CT-M:软件组件的硬件容器 - 硬件/软件接口的检测和恢复
- 批准号:
0830927 - 财政年份:2009
- 资助金额:
$ 30万 - 项目类别:
Continuing Grant
DC: Medium: Collaborative Research: ELLF: Extensible Language and Library Frameworks for Scalable and Efficient Data-Intensive Applications
DC:媒介:协作研究:ELLF:用于可扩展且高效的数据密集型应用程序的可扩展语言和库框架
- 批准号:
0905205 - 财政年份:2009
- 资助金额:
$ 30万 - 项目类别:
Standard Grant
Data- and Analytics Driven Fault-tolerance and Resiliency Strategies for Peta-Scale Systems
数据和分析驱动的千万亿级系统容错和弹性策略
- 批准号:
0956311 - 财政年份:2009
- 资助金额:
$ 30万 - 项目类别:
Standard Grant
Collaborative Research: Advanced Compiler Optimizations and Programming Language Enhancements for Petascale I/O and Storage
协作研究:针对 Petascale I/O 和存储的高级编译器优化和编程语言增强
- 批准号:
0833131 - 财政年份:2008
- 资助金额:
$ 30万 - 项目类别:
Standard Grant