CAREER: Behavioral Analytics and Field Experiments in Sustainable Innovation Policies

职业：可持续创新政策中的行为分析和现场实验

• 批准号: 1945332
• 负责人: Omar Asensio
• 金额: $ 60万
• 依托单位: Georgia Tech Research Corporation
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-06-01 至 2025-05-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1945332&HistoricalAwards=false
• 关键词: CAREER; Behavioral; Analytics; Field; Experiments

The analysis of big data in digital platforms accelerates entrepreneurial activity and supports the development of innovation related skills in the economy. However, these data often exhibit a paradox in that there is distance between those who own, curate, and control intelligence gleamed from massive data (e.g., companies owning mobile application databases) and those who broadcast it (e.g., users or communities). For open data in the public domain, this distance can be narrowed by directly involving communities, and training local cohorts of students and professionals to be able to interpret and translate data to answer questions of significance to the community. Using social innovations in energy systems and transportation, this CAREER project deploys big data analytics and experimental science to advance the design of incentives for resource conservation policies in both urban and non-urban areas. Buildings and transportation are important sectors of the economy; therefore, this research calls on human and machine intelligence to advance research on how large-scale civic data in combination with behavioral strategies can be used to increase resource conservation, while providing aggregate intelligence about infrastructure and localized impacts in near real time. This research creates the necessary data infrastructure for a suite of information-based policy interventions. This includes linkages in the application of artificial intelligence and machine learning prediction with methods of causal inference. Unstructured data that would take months of human processing will be interpreted and classified rapidly, while structured data that lives in disparate information systems can be linked and activated to enable policy analysis. Furthermore, this CAREER program integrates behavioral research, teaching, and the dissemination of computational tools as a means to broaden participation in analytic policy processes among historically under-represented communities. The research, will lies at the intersection of data science and policy, will deploy novel approaches to evaluate, engage, and disseminate open data to problems of resource efficiency and behavior changes for critical civic infrastructure and natural resource protection. It engages not only with civic partners, but also with K-12 students as well as undergraduate and graduate students.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.

数字平台中的大数据分析加速了创业活动，并支持经济中与创新相关的技能的发展。然而，这些数据往往表现出一种悖论，即那些拥有、策划和控制从海量数据中闪烁出来的情报的人之间存在距离（例如，拥有移动的应用数据库的公司）和广播它的公司（例如，用户或社区）。对于公共领域的开放数据，可以通过直接让社区参与，培训当地的学生和专业人员，使他们能够解释和翻译数据，回答对社区有意义的问题，来缩小这一距离。利用能源系统和交通领域的社会创新，该CAREER项目部署了大数据分析和实验科学，以推进城市和非城市地区资源保护政策的激励设计。建筑物和交通是经济的重要部门;因此，这项研究呼吁人类和机器智能推进关于如何将大规模公民数据与行为策略相结合来提高资源保护的研究，同时提供有关基础设施和本地化影响的汇总情报在接近真实的时间。这项研究为一套基于信息的政策干预措施建立了必要的数据基础设施。这包括人工智能和机器学习预测应用与因果推理方法的联系。需要人工处理数月的非结构化数据将被快速解释和分类，而存在于不同信息系统中的结构化数据可以被链接和激活，以进行政策分析。此外，该职业计划整合了行为研究，教学和计算工具的传播，作为扩大历史上代表性不足的社区参与分析政策过程的一种手段。该研究将处于数据科学和政策的交叉点，将部署新的方法来评估，参与和传播开放数据，以解决关键公民基础设施和自然资源保护的资源效率和行为变化问题。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

The climate is changing. Engineering education needs to change as well

气候正在发生变化。

• DOI: 10.1002/jee.20485
• 发表时间: 2022
• 期刊: Journal of Engineering Education
• 影响因子: 3.4
• 作者: Martin, Michael James;Diem, Stephanie J.;Karwat, Darshan M.;Krieger, Elena M.;Rittschof, Clare C.;Bayon, Baindu;Aghazadeh, Mahdieh;Asensio, Omar;Zeilkova, Tamara Jane;Garcia‐Cazarin, Mary
• 通讯作者: Garcia‐Cazarin, Mary

Reliability of electric vehicle charging infrastructure: A cross-lingual deep learning approach

• DOI: 10.1016/j.commtr.2023.100095
• 发表时间: 2023
• 期刊: Communications in Transportation Research
• 作者: Yifan Liu;Azell Francis;Catharina Hollauer;M. Lawson;Omar Shaikh;Ashley Cotsman;Khushi Bhardwaj;Aline Banboukian;Mimi Li;Anne Webb;O. Asensio

Impacts of micromobility on car displacement with evidence from a natural experiment and geofencing policy

微移动对汽车位移的影响，来自自然实验和地理围栏政策的证据

• DOI: 10.1038/s41560-022-01135-1
• 发表时间: 2022
• 期刊: Nature Energy
• 影响因子: 56.7
• 作者: Asensio, Omar Isaac;Apablaza, Camila Z.;Lawson, M. Cade;Chen, Edward W.;Horner, Savannah J.
• 通讯作者: Horner, Savannah J.

EnergyVis: Interactively Tracking and Exploring Energy Consumption for ML Models

• DOI: 10.1145/3411763.3451780
• 发表时间: 2021-03
• 期刊: Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems
• 作者: Omar Shaikh;Jon Saad-Falcon;Austin P. Wright;Nilaksh Das;Scott Freitas;O. Asensio;Duen Horng Chau

Generative AI and Discovery of Preferences for Single-Use Plastics Regulations

生成人工智能和发现一次性塑料法规的偏好

• 发表时间: 2023
• 期刊: Proceedings of the AAAI 2023 Fall Symposium on Artificial Intelligence and Climate: The Role of AI in a Climate-Smart Sustainable Future
• 作者: Hollauer, Catharina;Garcelán, Jorge;Ragam, Nikhita;Vaish, Tia;Asensio, Omar Isaac
• 通讯作者: Asensio, Omar Isaac