Skip to main content
Connecting world-renowned researchers across academic boundaries with multidisciplinary practitioners to solve agri-food systems challenges.

Working Groups

Rapid Phenotyping

This group explores the limits of digital agriculture (new sensors, models and computational techniques) to reliably bridge the genome-phenome gap on a wide variety of dimensions (environment, management and microbe).

Led by Mike Gore, College of Agriculture and Life Sciences, Associate Professor of Molecular Breeding and Genetics for Nutritional Quality, Liberty Hyde Bailey Professor, International Professor of Plant Breeding and Genetics

Weather, Climate and Agriculture

In the lab and in the field, this group seeks to discover new paradigms for sustainable agricultural management enabled by the integration of newly available and anticipated data streams (via novel in situ and remote sensors and methodologies) with emerging multi-scale hybrid models of crop and climate.

Led by Abe Stroock, College of Engineering, Gordon L. Dibble Professor of Chemical and Biomolecular Engineering, William C. Hooey Director of the School of Chemical and Biomolecular Engineering.

Socioeconomic Analysis for Digital Agriculture

By drawing on a range of social science disciplines, we address social and economic questions that structure the potential of digital agriculture technologies. Through engagement with farmers, farm workers, off-farm service providers, agribusinesses, environmental NGOs and government agencies, we seek to understand the application and continuing development of digital tools for agricultural production and environmental protection. Based on engagement with relevant histories, we aim to advance analysis and dialogue around questions of whose vision and problem definitions inform technological designs, how benefits are distributed and which people and places are disrupted by digital technologies in agriculture.

Led by Steven Wolf, College of Agriculture and Life Sciences, Associate Professor, Department of Natural Resources

Systems Analytics for Circular Economy and Smart Agriculture

Systems analytics is a “union” of systems approach and data analytics, and it has emerged as an important component of digital agriculture. This working group focuses on advancing digital agriculture through systems-level modeling, integration, control and optimization, agricultural big data analytics and machine learning, and multi-scale, hybrid data-driven and mechanistic modeling.

One possible theme of this working group is “circular economy” in agriculture, which centers on the production of agricultural and food commodities using the minimum amount of external inputs, while “closing the loops” of nutrients (e.g. P and N) and reducing negative discharges to the environment through organic waste treatment. This concept connects animal science areas (e.g. animal feeding, dairy manure, poultry litter) with crop science (organic fertilizer production through nutrient recycling), as well as energy, environmental, and climate issues (watershed protection, food waste processing, energy system development) and social sciences aspects (resource/environmental economics, policy, etc.)

The other theme is towards “smart” (and possible “unmanned”) food and agricultural production through smart cyber-physical systems and advanced data analytics, coupled with systems modeling, analysis, integration, optimization and design.

This working group focuses on systems modeling and data analytics, and provides the intellectual framework for artifacts, including software modules that can be called via APIs by the “AI, Analytics and Decision Support” layer of the Software-defined Farm (see below). This working group also works closely with Rapid Phenotyping, Socioeconomic Analysis for Digital Agriculture and Weather, Climate and Agriculture.

Led by Fengqi You, College of Engineering, Roxanne E. and Michael J. Zak Professor

The Software-defined Farm™

The Software-defined Farm™ (SDF) is being designed to work for large and small-scale farms; for farms with significant, limited, or even absent internet connectivity; and for farms with varying types of digitally controlled infrastructure, such as sensors, autonomous vehicles, or robots. SDF supports a systems engineering framework to enable data-driven machine learning and artificial intelligence (AI). The SDF actively manages a hybridization of cloud, edge and local compute resources.

The SDF is a multilayer software solution enabled by a common application programming interface (API), to provide for ease of application development, while also enabling applications to be tailored to different farm environments. It presents a user interface (UI) of dashboards to serve a diverse user base (suppliers, producers, distributors, policy makers, insurers, etc.)

The UI is underpinned by a decision support layer with a systems engineering framework that integrates and prioritizes diverse data streams from the local environment and external sources to feed a variety of mechanistic and data-driven artificial intelligence tools and models – including farm operational models, animal and crop models, market models, insurance models, etc. The SDF stack incorporates components of Microsoft’s FarmBeats platform, an advanced end-to-end IoT platform for agriculture that enables seamless data collection from various sensors, cameras and drones.

Led by Hakim Weatherspoon, Computing and Information Science, Associate Professor of Computer Science

Skip to toolbar