Developing a smartphone-based grain quality assurance tool
Accelerated Innovation
Consortium Contribution
$679,898
Cluster Contribution
$557,247
Grain Discovery
Inarix
Sevita International
Goal
To develop a smartphone-based grain quality assurance tool for grain farmers
Project Summary
By leveraging AI, specifically computer vision and machine learning algorithms, the project partners will provide options to complement grain testing methods with a software-as-a-service (SaaS) platform.
Once developed, the platform will allow users to take a photo of a soybean sample using a standard smartphone and receive an AI-generated quality assessment in under 20 seconds. By delivering consistent, scalable and real-time results, the tool will help improve information flow throughout the grain value chain—from field to export—and support more marketing opportunities for Canadian farmers.
The AI app will analyze high-resolution images to provide consistent, high-quality assessments of soybeans. Key features of the platform include:
- Real-time, standardized assessments of soybean variety;
- Enhanced traceability and transparency for grain buyers and processors; and
- Increased accessibility with tools designed for smartphone use across rural regions.
Grain Discovery will lead the commercialization and market deployment of a solution that will include the AI technological brick developed and provided by Inarix, while Sevita International will contribute critical historical data and serve as the primary pilot site for real-world testing and validation.
Results and Impact
- Increased Operational Efficiency: The solution replaces slow, manual, and subjective grain testing with automated AI workflows, significantly accelerating grading processes and reducing delays.
- Improved Consistency and Objectivity: By shifting from subjective human evaluation to automated AI analysis, the platform ensures consistent and reliable grading results, which is essential for managing high-value, identity-preserved crops.
- Enhanced Traceability: The integration of digital workflows enables robust traceability from "field to load to ticket," addressing weaknesses in the value chain and improving transparency for buyers, processors, and traceability programs.
- Data-Driven Predictive Insights: Beyond immediate grading, the platform supports "Traceability 2.0" modeling, which combines farmer and buyer data with satellite and agronomic inputs. This allows for forward-looking capabilities, such as quality and carbon intensity forecasting, rather than relying solely on reactive testing.
