Normalized claim
Cost: 90% decrease
Achieved 90% reduction in physical hardware costs for monitoring.
Stewart Dairylands, a major farming enterprise in New Zealand, faced the challenge of increasing productivity and sustainability despite sparse connectivity and budget constraints. To overcome these, Stewart Dairylands partnered with Microsoft and Aware Group to deploy Microsoft Azure FarmBeats, an end-to-end AI and IoT agriculture platform. FarmBeats collected sensor and drone-based data to monitor soil moisture, temperature, and crop health, even across large, hard-to-connect tracts of land using a TV White Space network. By combining sparse sensor deployment with regular drone flights, the solution produced precision heatmaps and insights for managing crops and livestock more proactively. All data is aggregated securely in the cloud for advanced analysis using machine learning, allowing farmers to optimize irrigation, fertilization, and operational decisions. The project reduced hardware costs by 90 percent and demonstrated the viability of data-driven precision agriculture at scale. Future plans include expanding the platform with edge machine learning and farm robotics for further automation and environmental benefits.
Normalized claim
Cost: 90% decrease
Achieved 90% reduction in physical hardware costs for monitoring.
The project reduced hardware costs by 90 percent and demonstrated the viability of data-driven precision agriculture at scale
Primary read
Showing 2 of 2
Azure FarmBeats ingests data from IoT sensors and drones, transmits it over a TV White Space (TVWS) network to cover remote farmland, and aggregates it securely in the cloud. Machine learning models analyze this data to create precision heatmaps and summary insights for agricultural management. The system integrates with planned edge machine learning devices and robotics for further automation.
AI-generated summary. Verify important details with the linked sources before relying on this case.
Was this useful?
Community
No published comments yet.