Geospatial Artificial Intelligence Algorithms for Automating Manual Observation Associated with Wheat Production

The grain sector is a key driver of Canada’s economic growth, with more than 20 million tons of wheat exports and over $20 billion in export sales annually. Many activities required for wheat production rely on laborious manual observation, such as post-harvest assessment of wheat kernels and wheat head detection. These manual, subjective tasks can be costly, unreliable, and inaccurate. Regardless, they are essential to the success of farmers, breeders, researchers, and buyers of wheat alike. This project aims to research and develop customized and novel object detection algorithms and geospatial artificial intelligence (GeoAI) algorithms to automate several manual observations required for wheat production. This project pursues a greater level of automation and precision in agriculture to drive efficiency and productivity, and to establish Canada as a global leader in agricultural automation. The project will reduce manual observational requirements, and increase productivity, profitability, sustainability, and competitiveness for Canada’s agricultural producers.

Faculty Supervisor:

Longhai Li

Student:

Partner:

Super GeoAI Technology Inc.

Discipline:

Mathematics

Sector:

Information and cultural industries; Professional, scientific and technical services

University:

University of Saskatchewan

Program: