---
title: >-
  PlantVillage, FAO, IITA, CIMMYT, and partner extension programs: PlantVillage Nuru
  offline smartphone diagnosis
slug: plantvillage-nuru-cassava-diagnosis
stable_id: 5ea0424c926cb9d5
company: PlantVillage, FAO, IITA, CIMMYT, and partner extension programs
function_code: agriculture
pattern_codes:
  - creator_to_judge
evidence_strength: verified
publication_tier: showcase
freshness: current
reviewed_at: '2026-08-23'
updated_at: '2026-08-22'
source_quality_summary: 2 peer reviewed; publication outcomes are verified.
caveat_summary: >-
  Diagnostic accuracy is not crop-yield impact. Adoption research found 45% adoption,
  65% smartphone unavailability, and 41% complexity constraints.
collections: []
bundle_version: 1.0.0
bundle_fingerprint: sha256:c23c6cc2b88153d008ea8fda928f632ce0011fc2d4c5036672a16e5d895bab93
canonical_url: https://brianletort.ai/transformations/plantvillage-nuru-cassava-diagnosis
---

# PlantVillage, FAO, IITA, CIMMYT, and partner extension programs: PlantVillage Nuru offline smartphone diagnosis

Farmers can diagnose cassava disease without waiting for scarce expert access or relying on unaided vision.

Function: Agriculture. Patterns: Creator to judge. Evidence: verified.

Freshness: current. Reviewed: 2026-08-23. Updated: 2026-08-22.


Source quality: 2 peer reviewed; publication outcomes are verified.

## Before

1. **Farmer or extension officer** — Inspect visible leaf symptoms using personal knowledge. (control: Human diagnostic skill)
2. **Expert** — Provide diagnosis when reachable. (control: Travel and availability)

## After

1. **Farmer or extension officer** — Scans multiple leaves with an Android phone in the field without internet. (control: Image-quality and six-leaf protocol)
2. **Nuru** — Classifies disease or pest symptoms and provides real-time guidance. (control: Model confidence and supported conditions)
3. **Human user** — Decides whether to act, rescan, or seek expert confirmation. (control: Human authority)

## Decision rights

Nuru returns a diagnosis and advice; the farmer or extension officer decides what action to take.

## Exception path

Users can scan six leaves, repeat under better lighting, or escalate uncertain and unsupported cases to trained experts.

## Outcomes

- **Field diagnostic accuracy** (verified): Farmers 18-31% and extension agents 40-58% → Nuru 65% in 2020; 74-88% when six leaves per plant were assessed. Diagnostic accuracy is not crop-yield impact. Adoption research found 45% adoption, 65% smartphone unavailability, and 41% complexity constraints.

## Executive lesson

The model outperformed typical users, but the workflow still depends on owning a suitable phone, capturing six useful leaves, and knowing when to escalate.

## Anti-pattern

Equating diagnostic accuracy with farmer income or ignoring access and usability barriers.

## Questions for leaders

- What physical input protocol controls accuracy?
- Who is excluded by the device requirement?

## Sources

- [Accuracy of a Smartphone-Based Object Detection Model, PlantVillage Nuru](https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2020.590889/full) — Frontiers in Plant Science
- [Perception and adoption by cassava farmers of the PlantVillage Nuru application](https://www.frontiersin.org/journals/agronomy/articles/10.3389/fagro.2024.1433204/full) — Frontiers in Agronomy