Location: Office of Associate Administrator
Project Number: 0500-00110-001-007-S
Project Type: Non-Assistance Cooperative Agreement
Start Date: Sep 30, 2023
End Date: Sep 29, 2025
Objective:
Modern agricultural research is a highly multidisciplinary enterprise that increasingly requires sophisticated computational and statistical methods to analyze datasets that are rapidly expanding in size, scope, and complexity. As such, agricultural science benefits from a team approach that brings together deep domain expertise and strong data science and analytics skills. The overall goal of this partnership is to advance ARS’s research efforts and enhance the Cooperator’s student training programs by providing graduate research experiences that allow students with advanced data analytics skills to collaborate with ARS research teams working on data-intensive research problems.
Our specific objectives are four-fold. First, we will advance ARS’s research efforts by allowing Cooperator-affiliated graduate students with strong, applied skills in data science and related fields (e.g., computer science, artificial intelligence, machine learning, statistics) to contribute these skills to ARS’s scientific research. Second, we will enhance participating students’ educational experiences by providing paid, hands-on, real-world research opportunities, scientific domain expertise, and mentoring from ARS scientists. Third, we will boost the Cooperator’s affiliated departments and programs by increasing the breadth of training they are able to offer to their students. Finally, we will support future ARS workforce development efforts by increasing student awareness of ARS and agricultural research as a rewarding career path for data scientists.
Approach:
ARS has deep scientific expertise across a wide spectrum of agricultural research domains, spanning biological disciplines from landscape ecology to molecular biology, engineering, chemistry, and more. ARS also has extensive scientific computing infrastructure, called SCINet, that includes multiple high-performance computing (HPC) clusters, high-performance and archival storage systems, and a high-speed networking backbone. The Cooperator has strong academic programs in Engineering, Computer Science, and Mathematics at both undergraduate and graduate levels. Faculty research areas relevant to the collaboration include data analytics/science, data mining, machine learning, AI, cybersecurity, and autonomous systems.
We will develop a process to match graduate students who have strong skills in data science and related fields with ARS research units and ARS researchers who will serve as mentors for the students during paid, 10-week research experiences. Students will work with their ARS mentor (or mentors) to contribute their expertise to active ARS research efforts while also learning new research skills and domain knowledge. Students will also be co-mentored by faculty at their home institution during their fellowships. Student participants will have full access to scientific computing infrastructure and training resources provided by SCINet and the ARS AI Center of Excellence (AI-COE). We anticipate that most fellowships will follow a hybrid work model in which students receive 2 weeks of travel support to visit their assigned ARS unit and mentor(s) and spend the remainder of the research experience working remotely from their home or home institution.
