---
id: ai-for-agriculture
title: "AI for Agriculture: Precision Farming, Plant Disease Detection, and Crop Yield Prediction"
schema_type: article
category: ai
language: en
confidence: medium
last_verified: "2026-05-28"
created_date: "2026-05-24"
generation_method: ai_structured
ai_models:
  - claude-4.5-sonnet
derived_from_human_seed: true
conflict_of_interest: none_declared
is_live_document: false
data_period: static
completeness: 0.85
atomic_facts:
  - id: af-ai-for-agriculture-1
    statement: >-
      The PlantVillage paper presented an open-access repository of plant-health images intended to
      support mobile plant disease diagnostics.
    source_title: >-
      An open access repository of images on plant health to enable the development of mobile
      disease diagnostics
    source_url: https://www.frontiersin.org/articles/10.3389/fpls.2016.01182/full
    confidence: medium
  - id: af-ai-for-agriculture-2
    statement: >-
      Mohanty, Hughes, and Salathe demonstrated deep-learning classification of plant disease from
      leaf images using the PlantVillage dataset.
    source_title: Using Deep Learning for Image-Based Plant Disease Detection
    source_url: https://www.frontiersin.org/articles/10.3389/fpls.2016.01419/full
    confidence: medium
  - id: af-ai-for-agriculture-3
    statement: >-
      John Deere describes See & Spray as using cameras and machine learning to identify weeds and
      target spray application.
    source_title: See & Spray Technology
    source_url: https://www.deere.com/en/sprayers/see-spray/
    confidence: medium
primary_sources:
  - id: ps-ai-for-agriculture-1
    title: >-
      An open access repository of images on plant health to enable the development of mobile
      disease diagnostics
    type: journal_article
    year: 2016
    authors:
      - Hughes, David P.
      - Salathe, Marcel
    institution: Frontiers in Plant Science
    doi: 10.3389/fpls.2016.01182
    url: https://www.frontiersin.org/articles/10.3389/fpls.2016.01182/full
  - id: ps-ai-for-agriculture-2
    title: Using Deep Learning for Image-Based Plant Disease Detection
    type: journal_article
    year: 2016
    authors:
      - Mohanty, Sharada P.
      - Hughes, David P.
      - Salathe, Marcel
    institution: Frontiers in Plant Science
    doi: 10.3389/fpls.2016.01419
    url: https://www.frontiersin.org/articles/10.3389/fpls.2016.01419/full
  - id: ps-ai-for-agriculture-3
    title: See & Spray Technology
    type: product_documentation
    year: 2026
    institution: John Deere
    url: https://www.deere.com/en/sprayers/see-spray/
known_gaps:
  - Generalization across crop varieties, geographic regions, and lighting conditions
  - Integration of AI recommendations with farmers decision processes
disputed_statements: []
secondary_sources: []
updated: "2026-05-28"
---
## TL;DR
AI in agriculture is best supported by narrow, operational claims: plant-disease image datasets, image-based disease classification, and computer-vision spraying systems. Broad productivity or resource-savings numbers should stay out of public claims unless tied to a specific deployment study.

## Core Explanation
Reliable examples include PlantVillage-style image repositories, deep-learning models trained to classify crop diseases from leaf images, and precision-spraying equipment that uses cameras and machine learning to identify weeds. These systems assist diagnosis and field operations but still depend on crop, geography, lighting, sensor quality, and farmer workflow.

## Related Articles

- [AI for Disaster Prediction: Earthquake Forecasting, Flood Detection, and Early Warning Systems](../ai-disaster-prediction.md)
- [AI for Public Health: Disease Surveillance, Outbreak Prediction, and Population Health Analytics](../ai-public-health.md)
- [AI for Air Quality: Pollution Monitoring, Source Attribution, and Health Impact Prediction](../ai-air-quality.md)