AI decision support tools for optimizing alfalfa yield and nutritive value

Alfalfa forage is the queen of forages in Canada, both for its nutritional value and for its global distribution across Canada. However, alfalfa yield and nutritive value are affected by multiple environmental and agronomic factors. The interaction among all of those factors makes it difficult for producers and field advisors to determine which of these leads to poor yields and how better management practices can improve yield. Producers and field advisors do not have adequate tools to take all of those factors into consideration. During this project we will develop a decision support tool targeting specific actions for improving yield and forage nutritive value from the Alfalfa field by integrating agrarian factors with artificial intelligence. This project will develop a Diagnostic and decision support tool using machine learning integrating proximal and remote data collected in the field to 1) Identify potential environmental and soil-related factors affecting alfalfa yield and nutritive value derived from the nutritional value of forage samples; 2) Predict potential yield and nutritive value loss derived from soil nutrient analysis related to actual conditions in the field.

Faculty Supervisor:

Bruno Agard

Student:

Partner:

Canadian Forage and Grassland Association

Discipline:

Mathematics

Sector:

Agriculture

University:

Polytechnique Montréal

Program: