TalentCloud revolutionizes sustainable farming in China
TalentCloud, a Chinese agricultural technology firm, overcame limitations of traditional farming methods in China by developing the Agro-Brain solution, powered by Microsoft Azure Machine Learning and Azure IoT. Agro-Brain gathers real-time field and environmental data with millions of sensors and cameras, feeds this data to Azure IoT Hub, and uses Azure Machine Learning for rapid training of complex agricultural models. The solution provides farmers with actionable recommendations for irrigation, fertilization, and crop management, reducing reliance on chemicals and improving food safety. The closed-loop system incorporates plant science and real-world field data, returning operational recommendations to field devices for precision agriculture. The move to Azure IoT increased the system’s scalability, enabling support for millions of sensors (up from just 100,000), with improved stability and security. Azure’s automated ML capabilities streamlined data scientist workflows by reducing model development time and debugging (by 65%). Visual Studio Code and ONNX standardize and accelerate model development and edge deployment. The implementation enabled TalentCloud to export their technology globally, contributing to more sustainable and safer food production. With less reliance on manual coding, TalentCloud focused on innovation and expanding their solution to reach more farmers.
- Organization
- TalentCloud
- Industry
- Agriculture
- Location
- China
- Published
- May 2020
Reported outcomes
−65%
timeTime & speed
Strategic outcomes
Catalog median for time & speed deployments: −60% across 727 reported metrics. Compare benchmarks →
Primary read
Use case focus
Showing 3 of 3
- 1Data-Driven Precision Agriculture with IoT and AI
- 2Real-time Crop Management Optimization
- 3Sustainable Farming Decision Support System
- Traditional Chinese farms limited by lack of scientific/farming knowledge
- Frequent food safety issues and environmental pollution
- Old farming methods with heavy use of chemicals/pesticides
- Insufficient number of agricultural technicians
- Manual coding and lack of system scalability, previously supporting only 100,000 sensors
- Developed Agro-Brain platform using Azure Machine Learning and Azure IoT
- Deployed millions of edge sensors and cameras for real-time data collection
- Automated data ingestion and model training using Azure IoT Hub and Azure ML
- Actionable crop and field recommendations delivered to farmers
- Visual Studio Code and ONNX used for accelerated, standardized model development and deployment
- Supported millions of IoT sensors (up from 100,000)
- Reduced model debugging time by 65%
- Enhanced model accuracy for precision farming
- Improved food safety and crop quality
- Reduced pollution and less chemical use
- Enabled global export and adoption of the solution
Architecture
IoT sensors and cameras in the field collect real-time data (soil, weather, images) that is sent to Azure IoT Hub. Azure Machine Learning automates model training using this data to provide precision agriculture recommendations. These are fed back to edge devices (via ONNX and Visual Studio Code) and control irrigation/fertilization equipment automatically, creating a closed feedback loop that integrates domain knowledge with real-world sensor data.
Sources & evidence1
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Was this useful?