The Challenge of Major Agricultural Machinery Manufacturer John Deere
John Deere deploys See & Spray, a precision application system that combines cameras, edge computing, and machine learning to identify weeds among growing crops and spray only where needed.
The Problem to Be Solved: Herbicide Costs and Environmental Impact
Broadcast application uses herbicide even where no weeds are present. See & Spray was developed to target only the places that need treatment, reducing inputs and improving application efficiency.
How AI Was Used: Real-time Weed Detection System "See & Spray"
See & Spray Ultimate uses 36 boom-mounted cameras and onboard processing to distinguish crops from weeds and activate only the required nozzles. Deere says it scans more than 2,100 square feet per second while traveling at 12 mph.
Implementation Effects and Key Takeaways
- ▸John Deere says herbicide use can be reduced by more than two-thirds, depending on field conditions.
- ▸A cited See & Spray Gen 2 comparison reports an average yield increase of 2.0 bushels per acre versus broadcast application.
- ▸On-machine processing connects image capture, identification, and nozzle control while the sprayer is moving.
What Japanese Companies Can Learn
John Deere's case demonstrates that significant value can be created by combining deep knowledge of a specific industry (agriculture) with general-purpose AI technology. The idea of using AI to "precisely" solve "common" problems (e.g., broadcast spraying) within one's area of expertise is applicable in various fields, such as defect detection in manufacturing or infrastructure maintenance and inspection. Furthermore, the importance of on-site (edge) data processing for real-time performance and stable operation is also a valuable takeaway.