AI & Ag Informatics

AI & Ag Informatics

Our Theme:

The growth of data coupled with the rapid adoption of computing technology have become key drivers of scientific discovery and innovation in digital agriculture. Digital technologies are being deployed at various scales from the field to the cloud. The resulting data sets, when integrated with crop and physical models, represent a treasure trove of information that can be used to provide key insights into how complex crop systems evolve and interact with their environment. These data-driven insights and knowledge in turn have the potential to be translated into informed decisions in crop management and crop improvement, at scales and capacities that are well beyond the reach of conventional models. AI, data science and analytics, and scalable computing technologies have a key role to play in enabling these knowledge, discovery, and decision support pipelines.

Research under this theme is geared toward the design, development, and deployment of AI and related technologies for the advancement of our scientific knowledge and innovation at all scales of digital agriculture – from molecular scales, to farm scale, to decision support with the aid of cloud and informatics. The thrust areas are as follows:

  • AI for Breeding and Crop Management: the use of AI for plant breeding, effective variety selection, and efficient management practices.
  • AI for Computer Vision and Pattern Recognition: the use of computer vision and image processing techniques for automated crop management and field robotics.
  • Human and AI Collaboration for Agricultural Systems: the development of AI systems with human-in-the-loop capabilities for management and decision making on field.
  • From Genomes to Phenomes: the development of bioinformatics and statistical capabilities to discover genomes, to associate genes to traits, and to elucidate interactions between genotypes and environments to effect various key phenotypic traits.
  • Spatial geoinformatics: the use of satellite and geospatial data toward automated decision making.
  • Databases: the development of community databases that provide access to field data alongside genomic and phenomic data sets.

Ongoing Research Projects/Initiatives:

  • Scalable Frameworks for Computational Phenomics and Topological Data Analytics (sponsor: NSF; project website)
  • Parallel algorithms and architectures for enabling extreme-scale bioinformatics applications include graph and network analytics (sponsor: NSF; award website)
  • Search-based optimization of combinatorial structures via expensive experiments for science and engineering applications (sponsor: NSF; award website)
  • FACT: Predicting Wheat Hagberg Falling Number from Near Infrared Spectrometers (sponsor: USDA-NIFA)
  • Genomics Enabled Satellite Phenomics for Wheat Breeding in the Palouse (sponsor: USDA-NIFA, Award website, WSU News)
  • Fast and Scalable Combinatorial Algorithms for Data Analytics (Sponsor: NSF; award website)
  • National Crop Database Resources; NRSP10 (Sponsor: USDA NIFA; website)


National Science Foundation
United States Department of Agriculture

Core Faculty:

Amit Dhingra

Ananth Kalyanaraman
Electrical Engineering and Computer Science

Assefaw Gebremedhin
Electrical Engineering and Computer Science

Bala Krishnamoorthy
Mathematics and Statistics

Dingwen Tao
Electrical Engineering and Computer Science

Dorrie Main

Ganapati Bhat
Electrical Engineering and Computer Science

Jana Doppa
Electrical Engineering and Computer Science

Jia Yu
Electrical Engineering and Computer Science

Stephen Ficklin

Yan Yan
Electrical Engineering and Computer Science

Zhiwu Zhang
Crop and Soil Sciences