Unlocking the promises of Big Data requires a clear vision, a talented and agile cross-disciplinary team, and an agile but long-term commitment to developing the tools and systems required to tackle the real world challenges of turning data into actionable information. This is the challenge G.E.M.S™ — an international agroinformatics initiative jointly led by the College of Food, Agricultural and Natural Resources Sciences (CFANS) and the Minnesota Supercomputing Institute (MSI) at the University of Minnesota — is tackling head on.
G.E.M.S™ is the first and the only system designed from the very start to support and functionally integrate spatially and temporally distributed genomic, environmental, management, and socioeconomic data in a single integrated platform.
Making diverse data interoperable is only the start. With a focus on effective data security, flexible data sharing, and environments suitable for advanced and ever-improving data analytics, G.E.M.S™ is addressing the hard problems that until now have kept most from unlocking the power and potential of the Big Data revolution.
With core, long-term MNDrive funding from the Minnesota State Government, augmented with additional project and partner resources, G.E.M.S™ is under continuous development and re-invention by university programmers and data scientists. The G.E.M.S™ team works day-to-day with leading-edge domain specialists in food, agriculture, remote and high-throughput sensing, and machine learning within a growing network of public and private partners worldwide. Close cross-disciplinary and cross-institutional collaboration ensures that G.E.M.S™ data sharing and data analytic features evolve in a modular but interoperable, demand-driven fashion.
Stakeholders provide rapid feedback on core G.E.M.S™ feature developments, and continuously challenge us to imagine and invent new ways to enable and accelerate innovation in agriculture.
The University of Minnesota is among the largest and highest ranked public research universities in the United States. Founded in 1851, it presently has more than 60,000 enrolled students and an annual budget of more than $3.6 billion. The university is ranked number 8 in research among all U.S. public universities, and conducts more than $900 million in research annually.
College of Food, Agricultural and Natural Resource Sciences (CFANS) is a world-renowned center of learning and research in food, agricultural and natural resource sciences. In 2017, CFANS had 256 faculty training 2,058 undergraduate and 745 graduate students and conducted $111 million in R&D. The college has had, and continues to have, a large local and global impact. Its faculty and alum include Nobel Laureate Norman Borlaug, who’s high-yielding, semi-dwarf wheat varieties helped spark the Green Revolution worldwide; TT Chang who co-developed semi-dwarf rice, the other cornerstone crop innovation of the Green Revolution; George Harrar who as President of the Rockefeller Foundation contributed to the conception, creation and funding of the CGIAR (international agricultural research centers); and Vernon Ruttan, who as President of the Agricultural Development Council helped build the economic case for massive public investments in food and agricultural R&D throughout Asia in the 1970s and 1980s.
CFANS continues to impact local and global agriculture with its path-breaking, public-private innovation partnerships, and its strategic alliance with the Minnesota Supercomputing Institute that, via their new G.E.M.S™ agroinformatics platform, are creating the cutting edge in the application of big data analytics to food and agriculture the world over.
Minnesota Supercomputer Institute (MSI), established in 1983, is the UMN’s principle center for computational research. MSI provides services to over 560 active groups that sponsor more than 3,300 unique users from 19 different university colleges, maintaining an array of systems dedicated to the computational needs of investigators in the state of Minnesota’s higher education institutions and their collaborators. It is also an active co-developer along with CFANS of the G.E.M.S™ agroinformatics platform. MSI currently has two main flagship supercomputers, Itasca and Mesabi. Taken together, these systems are comprised of 26,560 compute cores with 92 TB of RAM and can support over 800 TFLOPS of peak performance. All MSI researchers have access to a high-performance parallel storage platform. This system provides 2.4 PB (PetaBytes) of storage with sustained read and write speeds of up to 25 GB/sec. The integrity of the data is protected by daily snapshots and tape backups. High value data sets are backed up to an off-site facility as a part of the institute’s disaster recovery plan. MSI has a second-tier storage solution designed to address the growing need for resources that support data-intensive research. MSI also supports a cloud computing platform built on OpenStack to allow quick deployment of web, database and other development projects. Further, members of MSI may utilize an immersive visualization laboratory with active 3D stereographic motion tracking systems.
A distinguishing feature of MSI is its rich staff support structure. MSI has 16 dedicated consulting staff, all of whom have advanced degrees (12 in life sciences) and a wealth of experience working on a wide variety of research and development projects. MSI consultants are often written into grants and many consultants are included in proposals as key personnel. MSI consultants cover a broad range of expertise including: Big Data analysis, informatics, custom analysis pipeline development, genomics, data mining, bioinformatics image processing, visualization and computational biology.
The College of Science and Engineering (CSE) at the University of Minnesota has over 5,500 undergraduate students and nearly 3,000 graduate students. Among the 430 CSE faculty, GEMS has been particularly engaged with several highly-cited collaborators in the Department of Computer Science and Engineering with research specialties in the areas of spatial data mining, robotics and high-throughput sensing, machine learning, remote-sensed analytics, bioinformatics and computational biology, databases and Geographical Information Systems.
Education and Training
Bioinformatics and Computational Biology (BiCB) Training Program
G.E.M.S has joined forces with the BiCB Graduate Training Program to train the next generation of Informaticists and Data Scientists. Computation is the vanguard of today’s life sciences (biomedical, food and agricultural) research. The BiCB program is at the forefront of life sciences computation. It combines the strengths and skills of eight internationally renowned partners — University of Rochester, University of Minnesota Twin Cities, Mayo Clinic, IBM, The Hormel Institute, Cray, Inc., National Marrow Donor Program (NMDP), and the Brain Sciences Center — to create a one-of-a-kind opportunity for research and graduate education at the intersection of quantitative sciences, biology, medicine, food and agriculture.