Past Projects

Past projects and agtech demonstrations

Innovation Farms is unique in Canada in that it operates on a commercial seed farm to test and validate new technologies to bring them from pre-commercial to market, showcase technology demonstrations, and share insights to increase understanding of and access to digital agriculture tools.

Since launching Innovation Farms, EMILI has partnered on a number of digital agriculture activities that aim to increase productivity, sustainability, and profitability across the agriculture and agri-food sector.

Past projects

The following activities, which are listed alphabetically, represent some of the ways EMILI demonstrates the productivity and sustainability of commercialized technologies to empower growers and others along the value chain to adopt and fully deploy digital tools.

Return to featured projects

 

ATP’s Nutriscan

EMILI, Nutriscan (2023)

Soil samples collected from a 2023  canola nitrogen ramp trial were analyzed with ATP’s NutriScan diagnostic tool.

Fusarium head blight risk mapping tool comparison

EMILI, University of Manitoba, Metos Canada (2023)

EMILI compared two FHB risk mapping models to validate the relationship between current weather patterns and disease risk.

Metos iScout

Grosse Isle (2023-2024)

EMILI uses an iSCOUT® mobile app to monitor insect traps and identify specific insect species on the farm.

Metos Yield Prediction Model

Site: Grosse Isle (2024)

Live and predictive information from seven METOS® weather stations provides insight into disease forecasting, yield predictions, and local weather events.

Sensor network

Site: Grosse Isle (2024)

We have set up Internet of Things sensors to provide vital insights to inform sustainable and profitable crop production decisions.

Ukko Agro Weather Stations

EMILI, Ukko Agro (2023-2024)

Live and predictive information from Ukko Agro's weather station provides insight into weather, crop growth stages, and crop disease.

UW and NRC Machine Learning Algorithm

Site: Grosse Isle (2023-2025)

Image collections of pea plants and their root systems are being developed to apply machine learning to prairie crops.

UW and UM Weed Identification Algorithm

EMILI, UWinnipeg, UManitoba (2019-2024)

We are developing a public database of plant and weed images to train machine learning models for Prairie-centric crop management.