Normalized claim
Accuracy: 90%
Impurity detection accuracy exceeded 90%.
SMBSC modernizes beet sugar intake quality screening with AI on AWS
Use case typeManufacturing quality monitoringUpdated Jun 13, 2026
Southern Minnesota Beet Sugar Cooperative (SMBSC) modernized intake quality inspection for beet loads during peak harvest by deploying an AI-powered computer vision system with Tactical Edge AI. The solution replaced manual visual grading and binary inspection with continuous 0–100 impurity scoring to improve consistency, visibility into quality trends, and throughput across receiving operations.
- Organization
- Southern Minnesota Beet Sugar Cooperative
- Industry
- Agriculture
- Location
- United States
- Published
- May 2026
Reported outcomes
3 seconds
timeTime & speed
90%accuracy
Strategic outcomes
New product / capabilityReplaced manual grading with continuous scoringBetter decisions & insightImproved visibility into quality trendsSpeed & agilityEnabled near real-time quality processingRisk & complianceAutomatically alerted on impurity exceptions
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
Time: 3 seconds decrease
Grading time dropped to under 3 seconds per load.
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Southern Minnesota Beet Sugar Cooperative
- Provider
- AWS
- Maturity
- Production
- Linked source
- AWS Solutions Case Study
Tactical Edge AI built, trained, and deployed a computer vision model on Amazon SageMaker AI
Customer identity supportedSource describes one deploymentMaturity supported
Primary read
Use case focus
Showing 3 of 3
- 1Computer Vision
- 2Quality Inspection
- 3Process Automation
- Manual grading of beet impurities was inconsistent during peak harvest.
- Inspection created labor bottlenecks and delayed quality visibility.
- Off-specification loads and payment adjustments created financial risk.
- Tactical Edge AI built, trained, and deployed a computer vision model on Amazon SageMaker AI.
- Amazon S3 ingested intake images through event-driven notifications into processing workflows.
- AWS Lambda handled orchestration and dashboard pipeline updates for near real-time processing.
- The system applied threshold-based exception handling and automatically alerted operations leaders when impurity levels exceeded set levels.
Technologies
- Impurity detection accuracy exceeded 90%.
- Grading time dropped to under 3 seconds per load.
- Automated reporting removed weekly compilation work.
- SMBSC projected about USD 5 million in annual savings.
- Alert-to-action time dropped from days to minutes.
Architecture
Tactical Edge AI deployed an AI-powered computer vision workflow on AWS. Intake images are stored in Amazon S3 and routed via event-driven notifications into processing workflows. Amazon SageMaker AI is used to build, train, and deploy the impurity detection model, while AWS Lambda orchestrates backend processing and dashboard pipeline updates. The system produces continuous 0–100 impurity scores and sends automated alerts when quality thresholds are exceeded.
Sources & evidence1
Evidence: Medium65/100Evidence strength
- Customer explicitly identified
- Deployment status explicitly supported
- Primary source available
- Quantified outcome available
- Technical implementation details available
Type: Customer StoryPublished: May 27, 2026Publisher: AWSEvidence: PrimaryConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
AI patterns
Was this useful?
Community
Comments
No published comments yet.