Regrow Ag: Accelerating sustainable food and fiber production with Google Cloud
Regrow Ag, formed from the merger of precision agriculture and soil science companies, develops data-driven regenerative agriculture solutions to accelerate greenhouse gas emissions reduction and build climate resilience globally. They scaled their platform using Google Cloud, Google Earth Engine, Vertex AI, and BigQuery to enable monitoring of 1.2 billion acres worldwide and reduced data product development time from 6 months to under 1 month. The solution uses satellite imagery and geospatial data via Google Earth Engine, ML model training and deployment with Vertex AI, data warehousing and analytics through BigQuery, and serves data through APIs. Customers include General Mills, Kellogg Company, and Cargill, leveraging the platform to monitor agricultural practices, reduce emissions, and promote regenerative agriculture. Google Cloud platform allows Regrow Ag to operate efficiently with one DevOps engineer supporting 60 team members, providing scalability and faster innovative product delivery.
- Organization
- Regrow Ag
- Industry
- Agriculture
- Location
- United States
Reported outcomes
Strategic outcomes
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Regrow Ag, Kellogg Company, General Mills, Cargill, Bill and Melinda Gates Foundation
- Provider
- GCP
- Maturity
- Scaled Production
- Linked source
- Google Cloud Customer Story
Enabled global agricultural data collection at scale to monitor 1
Primary read
Use case focus
Showing 3 of 3
- 1Sustainability
- 2Environmental Monitoring
- 3AI Model Training & Deployment
- Regrow Ag faced infrastructure limitations in scaling their data products globally to meet growing customer needs for monitoring and reducing emissions in agriculture supply chains.
- They needed to accelerate product development and data processing from 6 months per product to less than one month across diverse international geographies.
- Adopted Google Cloud and Google Earth Engine to access vast satellite and geospatial datasets continuously refreshed in near real-time.
- Utilized Vertex AI for building, tuning, training, and deploying ML models for regenerating agriculture monitoring.
- Stored and analyzed data in BigQuery and SQL-based data stores, providing data through APIs for customers and partners.
- Leveraged Google Cloud’s scalability and ML tools to enable rapid product iteration and efficient platform operation with minimal operational overhead.
- Enabled global agricultural data collection at scale to monitor 1.2 billion acres of land.
- Helped reduce emissions, such as 1,600 tons reduced by rice growers in the Mississippi river basin, equating to removing 345 gasoline cars from the road for a year.
- Accelerated product development cycles from six months to less than one month, dramatically increasing agility.
- Reduced infrastructure complexity and staffing needs, operating with one DevOps engineer for 60 data scientists and team members.
- Provided expert advice to customers and supply chain partners, fostering adoption of regenerative agriculture globally.
Architecture
The solution architecture integrates Google Earth Engine for satellite imagery and geospatial data, Vertex AI for ML model lifecycle management, BigQuery for warehousing and analytics. Data products are served through APIs, enabling scalable monitoring of agricultural emissions and regenerative practices globally.
Sources & evidence1
- Customer explicitly identified
- Deployment status explicitly supported
- Primary source available
- Technical implementation details available
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Was this useful?
Community
Comments
Loading comments...