Field service · Production

super.AI computer vision reduces Triputra's fertilizer usage by 20% across 27 million trees

The problem

Triputra's Agriculture division needed to apply fertilizer efficiently across 27 million trees but had no way to process the millions of drone and satellite images they had collected — manual counting was impractical at this scale and the company had no prior ML experience.

Workflow diagram · grounded in source
1
Drone footage ingested
trigger
“customised computer vision model for them that took their drone video footage as an input”
2
Computer vision tree identification
ai_action
“customised computer vision model for them that took their drone video footage as an input and provided data input for tree and feature identification”
3
Fruit yield counting
ai_action
“an API that can automatically count the fruit yield of their farm”
4
Automated tree database created
integration
“created an automatic database of their trees from drone and satellite images powered by AI modelling”
5
Per-tree fertilization map output
output
“provided Triputra a map outlining the various fertilisation needs for each tree”
Reported outcome

Using a computer vision model across 27 million crop images, Triputra reduced fertilizer usage by 20% with no impact on crop yield and achieved 98% process automation (up from 0%).

Reported metrics
Fertilizer usage reduction20%
Process automation rate98%
Crop images processed27 million
Deployment timeline10 weeks
Show all 5 reported metrics
fertilizer usage reduction20%
process automation rate98%
crop images processed27 million
deployment timeline10 weeks
cost savingsignificant cost saving
Reported stack
computer vision modelAPI
Source
https://super.ai/case-studies/triputra
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Using a computer vision model across 27 million crop images, Triputra reduced fertilizer usage by 20% with no impact on crop yield and achieved 98% process automation (up from 0%).

What tools did this team use?

computer vision model, API.

What results were reported?

Fertilizer usage reduction: 20%; Process automation rate: 98%; Crop images processed: 27 million; Deployment timeline: 10 weeks (source-reported, not independently verified).

How is this field service AI workflow structured?

Drone footage ingested → Computer vision tree identification → Fruit yield counting → Automated tree database created → Per-tree fertilization map output.

Related field service cases