NRT: Improving strategies for hunger relief and food security using computational data science

当个人为积极健康的生活获得安全和有营养的食物的机会有限时，就会发生粮食不安全。这是一个全球性问题，在国内影响着相当数量的个人。为了解决这一问题，参与饥饿救济的人道主义组织与政府和私营部门合作。人道主义组织依靠不确定的供应来源，对不均衡和多变的需求作出反应，并就如何使用稀缺资源作出谨慎的决定。这些组织生成关于食物供应、食物分配和食物需求的大规模数据，这有助于它们履行其职能。挑战不仅来自供需的不确定性，而且来自不同组织收集的信息的差异。这项授予北卡罗来纳农业和技术州立大学的国家科学基金会研究培训(NRT)奖将开发一种创新的、跨学科的数据科学培训模式，旨在增加劳动力，帮助这些组织分析他们的努力，并改善地方、州和联邦层面的粮食援助提供。这一培训旨在通过结合工业和系统工程、计算机科学、数学、农业经济学、社会学和公共政策等学科，为总共50名硕士和博士生提供独特和全面的培训体验，其中包括45(45)名资助学员。目前，由于(A)该领域的传统STEM学生培训不包括公共政策视角，以及(B)使用大数据仅限于STEM人群的一部分，目前还没有正式的培训机制，学生可以通过这种机制获得从食品援助供应链产生的异类大数据中获得洞察力所需的跨学科知识。为了满足这一需求，该项目的研究和教育工作将使用国内人道主义饥饿救济供应链的现有数据作为基础，以创新的、基于证据的、可扩展的方法来培训其未来的劳动力。我们的项目将为培养受雇于人道主义部门的下一代数据科学家提供一个模式。总体目标有两个：(I)创建一种可持续的培训模式，改善STEM领域的学生从事数据科学职业的准备；(Ii)提供培训经验，指导学生使用大数据提供信息，并有可能改变具有社会影响的服务的提供。我们建议利用大数据来减少供应链中的不确定性，并通过解决信息不平等、可视化和信息驱动的决策建模来推动更有效的食品配送模式。该计划将包括一个暑期培训学院、产业界/学术界研究集群、专业发展研讨会以及对培训模式的持续评估。完成所有要求的学生将获得有关大数据收集、解释及其在决策中使用的新知识和技能；获得有关使用大数据解决饥饿救济和粮食安全方面的多学科问题的新知识；并获得通过行业级认证考试所需的培训。在北卡罗来纳农业和技术州立大学，该奖项将有助于建立一个新的基于证书的跨学科数据科学研究生培训计划。在更大的人道主义领域，这项工作产生的研究将通过减少信息不平等来改善获得食物的机会，通过提供实时可适应的信息可视化来增强业务决策，并创建能够对粮食援助政策和行动产生积极影响的新的信息驱动的决策模型。NSF研究培训(NRT)计划旨在鼓励为STEM研究生教育培训开发和实施大胆的、具有潜在变革意义的新模式。Traineesship Track致力于通过创新的、基于证据的、与不断变化的劳动力和研究需求保持一致的综合培训模式，在高度优先的跨学科研究领域对STEM研究生进行有效培训。该项目由研究生教育联盟和教授项目(AGEP)共同资助。AGEP资助科学、技术、工程和数学(STEM)和/或STEM教育研究方面的研究和开发、实施和模式调查，以改变博士教育的博士论文阶段、博士后培训和/或教师晋升。

Food insecurity occurs when individuals have limited access to safe and nutritious food for an active, healthy life. It is a global issue that affects a significant number of individuals domestically. To address it, humanitarian organizations involved in hunger relief work collaboratively with the government and private sector. Humanitarian organizations rely on uncertain sources of supply, respond to uneven and variable needs, and make careful decisions regarding how to use scarce resources. These organizations generate data on a massive scale about food supply, food distribution, and food need, which helps them to perform their function. Challenges arise from not only the uncertainty of supply and demand but also from variations in information collected by different organizations. This National Science Foundation Research Traineeship (NRT) award to North Carolina Agricultural and Technical State University will develop an innovative, interdisciplinary training model in data science designed to grow the workforce that will help these organizations analyze their efforts and improve the provision of food aid at the local, state, and federal level. This traineeship seeks to provide a unique and comprehensive training experience for a total of 50 masters and doctoral students, including forty-five (45) funded trainees, by combining disciplines in industrial and systems engineering, computer science, mathematics, agricultural economics, sociology, and public policy.At present, no formal training mechanism exists by which students can acquire the interdisciplinary knowledge needed to derive insight from heterogeneous big data generated by the food aid supply chain because (a) traditional STEM student training in this area does not include the public policy perspective and (b) working with big data is limited to a subset of the STEM population. To answer this need, this project's research and education efforts will use existing data from the domestic humanitarian hunger relief supply chain as the basis for an innovative, evidence-based, scalable approach to training its future workforce. Our program will provide a model for preparing the next generation of data scientists employed in the humanitarian sector. The overarching goal is two-fold: (i) to create a sustainable training model that improves the preparation of students in STEM fields to pursue careers in data science and (ii) to provide training experiences that will orient students on the use of big data to inform and potentially transform the delivery of services that have societal impact. We propose to leverage big data to reduce uncertainty in this supply chain and drive more effective modes of food distribution by addressing information inequality, visualization, and information-driven decision modeling. The program will feature a summer training institute, industry/academia research clusters, professional development seminars, and ongoing evaluation of the training model. Students who complete all requirements will obtain new knowledge and skills with respect to big data collection, interpretation, and its use in decision-making; obtain new knowledge about using big data to address multidisciplinary problems in hunger relief and food security; and obtain the training necessary to pass an industry-level certification exam. At North Carolina Agricultural and Technical State University, the award will help to establish a new certificate-based interdisciplinary graduate training program in data science. In the larger humanitarian sector, the research generated by this work will improve access to food by reducing information inequality, enhance operational decision-making by providing real-time adaptable visualization of information, and create new information-driven decision models that can positively impact food aid policy and operations.The NSF Research Traineeship (NRT) Program is designed to encourage the development and implementation of bold, new potentially transformative models for STEM graduate education training. The Traineeship Track is dedicated to effective training of STEM graduate students in high priority interdisciplinary research areas, through comprehensive traineeship models that are innovative, evidence-based, and aligned with changing workforce and research needs.This project is co-funded by the Alliances for Graduate Education and the Professoriate (AGEP) program. AGEP funds research and the development, implementation, and investigation of models to transform the dissertation phase of doctoral education, postdoctoral training and/or faculty advancement of historically underrepresented minorities (URMs) in Science, Technology, Engineering and Mathematics (STEM) and/or STEM education research.