AI Institute: Artificial Intelligence for Environmental Sciences (AI2ES)
AI Institute: Artificial Intelligence for Environmental Sciences (AI2ES)
批准号:
2019758
负责人:
Amy McGovern
金额:
$1999.86万
依托单位国家:
美国
项目类别:
Cooperative Agreement
财政年份:
2020
资助国家:
美国
项目状态:
未结题
起止时间:
2020-09-01 至 2025-08-31
中文摘要
天气模式、海洋、海平面上升和灾害风险的变化放大了人工智能和环境科学(ES)加速研究的必要性。AI Institute:AI Intelligence for Environmental Science(AI2ES)是一个融合的多部门研究所,将人工智能、大气科学、海洋科学和风险通信领域的研究人员聚集在一起,开发用户驱动的值得信赖的人工智能,以解决迫切的环境问题的各种数据和研究需求。AI2ES利用学术界、政府和私营行业的专门合作伙伴关系,倍增研究所在值得信赖的人工智能、专家系统和风险沟通方面的开创性集成研究的战略影响和社会效益。通过直接接触环境科学家和风险管理人员,AI2ES将提高国家对恶劣天气和海洋现象的理解,将拯救生命和财产,并将提高社会对气候变化的适应能力。作为一家国家人工智能研究院,AI2ES将人工智能研究人员、环境科学家和风险沟通研究人员聚集在一起,协同工作,为人工智能、社会科学和环境科学的基础科学进步做出贡献。AI2ES的研究人员正在研究新的可信人工智能技术,包括物理约束的机器学习、时空数据的模型解释和可视化、不确定性量化以及对抗数据的稳健性。在环境科学方面,AI2ES大大加强了对大影响大气和海洋科学现象的理解和预测,时间尺度从几个小时到几个月不等。整合坚实的风险沟通理论框架将使AI2ES符合专家和专业最终用户的需求,同时提高风险沟通社区对风险沟通方法如何影响专家对基于人工智能的方法的信任以及他们将这些方法整合到他们的工作流程中的意愿的理解。AI2ES通过其教育和劳动力发展活动进一步服务于社会。该研究所致力于通过深度整合的活动培养一支熟练和多样化的未来劳动力队伍,这些活动通过令人兴奋的新计划,如旨在向未来劳动力所需的新专家教授人工智能证书计划,促进教育,扩大参与,并为未来的人工智能专家做准备。该学院致力于扩大参与,为美国不同地区代表性不足的学生建立一个渠道,从德克萨斯州南部的一所HSI(TAMU Corpus Christi)及其合作伙伴社区学院德尔玛学院开始,同时在全国范围内推广。AI2ES还与私营行业合作伙伴以及与国家大气研究中心(NCAR)的合作,为代表不足的群体创建了一个新颖的实习和指导计划,并为所有年龄段开发了独特的劳动力再培训模块,使用户能够学习针对所有人熟悉的环境应用的人工智能。AI2ES正在提供研究和未来的劳动力,以交付所需的进步,以可信地预测、理解和沟通全国关注的高影响环境危害。该奖项反映了NSF的法定使命,并通过使用基金会的智力优势和更广泛的影响审查标准进行评估,被认为值得支持。
英文摘要
Changes in weather patterns, oceans, sea level rise, and disaster risk amplify the need for accelerated research in both AI and Environmental Science (ES). The AI Institute: Artificial Intelligence for Environmental Sciences (AI2ES) is a convergent, multi-sector institute that brings together researchers in AI, atmospheric science, ocean science, and risk communication to develop user-driven trustworthy AI that addresses the diverse data and research needs of pressing environmental concerns. AI2ES leverages dedicated partnerships in academia, government, and private industry to multiply the strategic impact and societal benefit of the institute’s groundbreaking integrated research in trustworthy AI, ES, and risk communication. By directly engaging environmental scientists and risk managers, AI2ES will improve the Nation’s understanding of severe weather and ocean phenomena, will save lives and property, and will increase societal resilience to climate change. As a National AI Research Institute, AI2ES brings together AI researchers, environmental scientists, and risk communication researchers to work synergistically, contributing to fundamental scientific advances in AI, social science, and environmental science. Researchers at AI2ES are investigating novel trustworthy AI techniques including techniques for physically-constrained machine learning, model interpretation and visualization for spatiotemporal data, uncertainty quantification, and robustness with adversarial data. In environmental science, AI2ES is significantly enhancing the understanding and prediction of high-impact atmospheric and ocean science phenomena at time scales ranging from hours to months. Integration of a solid theoretical framework for risk communication will grounds AI2ES in expert and professional end users’ needs, while simultaneously improving the risk communication community’s understanding of how risk communication approaches influence experts’ trust in AI-based methods and their willingness to integrate them into their workflow. AI2ES further serves society through its education and workforce development activities. The institute is dedicated to developing a skilled and diverse future workforce through deeply integrated activities that advance education, broaden participation and prepare future AI experts through exciting new programs such as AI certificate programs aimed at teaching AI to new experts needed in the workforce of the future. The institute is committed to broadening participation by creating a pipeline for underrepresented students in different parts of the country, starting at an HSI in South Texas (TAMU Corpus Christi) and its partner community college, Del Mar College, with a concurrent national outreach. AI2ES also engages private industry partners as well as collaboration with the National Center for Atmospheric Research (NCAR) to create a novel internship and mentoring program for underrepresented groups and develop unique workforce retraining modules for all ages that will engage users in learning AI for environmental applications familiar to all. AI2ES is providing both the research and the future workforce to deliver the advances needed for trustworthy prediction, understanding, and communication of the high-impact environmental hazards that are of concern to the entire country.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.
期刊论文(21)
专著(0)
科研奖励(0)
会议论文
登录
查看更多内容
Controlled Abstention Neural Networks for Identifying Skillful Predictions for Regression Problems
用于识别回归问题的熟练预测的受控弃权神经网络
DOI:
10.1029/2021ms002575
发表时间:
2021
期刊:
Journal of Advances in Modeling Earth Systems
影响因子:
6.8
作者:
[Barnes, Elizabeth A., Barnes, Randal J.]
通讯作者:
Barnes, Randal J.
Development and Investigation of GridRad-Severe, a Multiyear Severe Event Radar Dataset
多年严重事件雷达数据集 GridRad-Severe 的开发和研究
DOI:
10.1175/mwr-d-23-0017.1
发表时间:
2023
期刊:
Monthly Weather Review
影响因子:
3.2
作者:
[Murphy, Amanda M., Homeyer, Cameron R., Allen, Kiley Q.]
通讯作者:
Allen, Kiley Q.
DOI:
10.1017/eds.2022.7
发表时间:
2021-03
期刊:
Environmental Data Science
影响因子:
--
作者:
[Antonios Mamalakis;I. Ebert‐Uphoff;E. Barnes]
通讯作者:
Antonios Mamalakis;I. Ebert‐Uphoff;E. Barnes
Using deep learning to emulate and accelerate a radiative-transfer model
使用深度学习来模拟和加速辐射传输模型
DOI:
10.1175/jtech-d-21-0007.1
发表时间:
2021
期刊:
Journal of Atmospheric and Oceanic Technology
影响因子:
2.2
作者:
[Lagerquist, Ryan, Turner, David, Ebert-Uphoff, Imme, Stewart, Jebb, Hagerty, Venita]
通讯作者:
Hagerty, Venita
Diagnosing Storm Mode with Deep Learning in Convection-Allowing Models
利用允许对流模型中的深度学习诊断风暴模式
DOI:
10.1175/mwr-d-22-0342.1
发表时间:
2023
期刊:
Monthly Weather Review
影响因子:
3.2
作者:
[Sobash, Ryan A., Gagne, David John, Becker, Charlie L., Ahijevych, David, Gantos, Gabrielle N., Schwartz, Craig S.]
通讯作者:
Schwartz, Craig S.
共 17 条
Collaborative Research: Conference: NSF Workshop Sustainable Computing for Sustainability
-
批准号:2334855
-
项目类别:Standard Grant
-
资助金额:$0.14万
-
财政年份:2023
-
负责人:Amy McGovern
-
依托单位:
EAGER: Improving our Understanding of Supercell Storms through Data Science
-
批准号:1802627
-
项目类别:Standard Grant
-
资助金额:$16.85万
-
财政年份:2018
-
负责人:Amy McGovern
-
依托单位:
CAREER: Developing Dynamic Relational Models to Anticipate Tornado Formation
-
批准号:0746816
-
项目类别:Continuing Grant
-
资助金额:$50.0万
-
财政年份:2008
-
负责人:Amy McGovern
-
依托单位:
海外基金