Skip to main content
ARS Home » Research » Research Project #439086

Research Project: Advancing Agricultural Research through High Performance Computing

Location: National Programs

Project Number: 0500-00096-001-02-S
Project Type: Non-Assistance Cooperative Agreement

Start Date: Sep 1, 2020
End Date: Aug 31, 2023

Agricultural research continues to move towards inter-disciplinary research that requires the use of Big Data and at times the integration of a wide range of scientific research methods and technologies [e.g., unmanned aircraft systems (UAS), climate and environmental data, surveillance and analysis of plant and animal pests, disease ecology, and other items related to productivity]. As such, agricultural research requires more complex levels of analysis with the ability to add additional variables when looking to improve agriculture productivity. This results in the need for a Big Data paradigm that includes the development of new analysis techniques [e.g. spatial epidemiology and disease ecology, molecular epidemiology, landscape analysis, agroecology, data science, artificial intelligence (AI), machine learning (ML), and access to high performance computing clusters (HPC) for complex data analysis, modeling, and machine learning. Computational tools need to run optimally in an HPC environment, which requires specialized development. All of this needs to be developed and put into place with training for proper analysis. Clear examples are development and use of new statistical and image analysis tools for georeferenced agricultural data related to agricultural operations, utilization of blockchain technology for agricultural data integrity and management, integrated analysis of agricultural systems at multiple levels of organization spanning cells, organisms, communities and interactions with environment, and across temporal and spatial scales. Translation of the advances made in data analysis domain utilizing high performance computing to gains in agricultural productivity requires the development of a well-trained diverse workforce. The overall objective of the partnership between the cooperator and the Agricultural Research Service (ARS) is to develop a hub for collaborative, multi-disciplinary research in Geospatial Agriculture to take advantage of the personnel, data, and HPC resources available from both partners. This hub will be uniquely poised to address challenging questions in Disease Ecology, Epidemiology, and Landscape Agroecology that require the partners work together to develop and apply analytical, numerical, and computing technologies within a Big Data Paradigm; these questions include, but are not limited to, what are the biotic and environmental drivers of the spread of infectious diseases in plants and animals across complex landscapes? How can emerging technologies (e.g., sensors, drone imagery, machine learning) be applied to predict dynamics of disease across spatial scales from sub-organismal to landscape, regional and global?

ARS has extensive experience researching agriculture productivity, environmental ecology involving animals, animal waste and field studies, unmanned aerial vehicles, and complex agricultural systems. ARS also has a wide-ranging network for research on controlling diseases/ pests, especially foreign diseases and non-native Invasive pests. Cooperator has expertise in agriculture research and computational aspects related to that research, especially in the area of infectious diseases, epidemiology, geospatial analysis, and bioinformatics. Cooperator has unique experience with unmanned aerial systems and subsequent analysis like geospatial statistics. In collaboration with ARS, Cooperator faculty and staff will provide intellectual input in research and training. Cooperator also has extensive experience with the establishment and operations of high-performance computing (HPC) and developing/altering computational software to run in an HPC environment. In this project, ARS and Cooperator will work together to create a collaborative, multi-disciplinary program to utilize the HPC environment and to analyze large volumes and types of data needed to improve agricultural productivity and sustainability. Types of analysis include epidemiology, geospatial statistics, bioinformatics, modeling, and AI/ML. These types of analysis will require HPC configurations of large memory nodes, normal nodes, graphical processing unit (GPU) nodes and data storage.