PLAYBOOK ATLASPlaybook Atlas

Agriculture

AI in agriculture: explore 28 applications.

Connect field observations to crop-specific planning and supervised farm actions.

Explore crop-image review, yield forecasting, irrigation and prescription workflows for growers, agronomists and farm operations teams.

Plan your first AI move See the 28 applications

Where the 28 applications sit

Explore the domains
  1. 17Crop Production Management
  2. 10Data and Information Management
  3. 3Environmental and Risk Management
  4. 3Resource and Input Management

01Why AI now

Why agriculture is moving on AI, in three figures.

Each figure links to its source.

  1. AgTech AI market: $4.7B by 2028

    Precision agriculture and yield prediction lead investment

    Source: MarketsandMarkets

  2. Models explained nearly 90% of yield variance

    Deep-learning models using satellite imagery explained nearly 90% of the variance in field-scale soybean yield.

    Source: ISPRS Journal of Photogrammetry and Remote Sensing / Elsevier

  3. Plant pests destroy up to 40% of crops

    FAO reports that plant pests destroy up to 40% of agricultural crops annually, causing approximately $220 billion in global trade losses.

    Source: Food and Agriculture Organization of the United Nations

How to evaluate a first project

Define the crop, region, season and decision before selecting a model. Check imagery, weather and field records against local observations, including look-alike symptoms and missing measurements. Evaluate the resulting prescription or forecast in a supervised trial and record its actual handoff to field equipment.

02Capability map

Where agriculture puts AI to work, domain by domain.

Pick a domain to see its applications. Each one opens a full report.

Inside Crop Production Management

Applications in Crop Production Management

What the use cases ask AI to do

Share of the agriculture use cases, by the kind of work the AI does.

  1. Reasoning

    Analyzes, predicts and decides: scoring, forecasting, classifying.

    36%

  2. Perception

    Sees, hears and reads: documents, images, audio and video.

    35%

  3. Generation

    Creates: text, images, code and other content.

    29%

Under 1% each: optimization and agentic.

03What gets built

The approaches agriculture uses most, and when to skip them.

Knowing when not to use one matters as much as knowing when to.

  1. 01 · 23 applications

    Domain Intelligence

    Domain/workflow taxonomy for solution labels that are not implementation techniques.

    Domain Intelligence, in depth

  2. 02 · 2 applications

    Classical-Supervised

    Train models on labeled tabular data to predict well-defined outcomes.

    Use it when

    • When you have a clearly defined target variable (label) and a well-scoped prediction problem (classification or regression).
    • When your data is primarily structured/tabular (numeric and categorical features) rather than raw text, images, or audio.
    • When you have sufficient labeled historical data that is representative of future production data.

    Skip it when

    • When you lack labeled data or labels are extremely sparse/expensive, making supervised training impractical.
    • When the core data is unstructured (e.g., raw text, images, audio) and you are not converting it into meaningful features first.
    • When the task is exploratory or descriptive (e.g., clustering, anomaly discovery without labels), where unsupervised or self-supervised methods are more appropriate.
    Classical-Supervised, in depth

  3. 03 · 1 application

    Computer-Vision

    AI pattern for interpreting and acting on images and video data.

    Use it when

    • When you need to automate or augment tasks that currently rely on human visual inspection (e.g., quality control, surveillance).
    • When visual information (images, video, documents) is the primary or richest source of signal for the problem.
    • When real-time or near-real-time decisions based on camera feeds are required (e.g., robotics, autonomous systems, safety monitoring).

    Skip it when

    • When the problem can be solved more simply and robustly with non-visual sensors or structured data (e.g., barcodes, RFID, logs).
    • When you lack access to sufficient, representative visual data and cannot feasibly collect or label it.
    • When privacy, legal, or ethical constraints prohibit capturing or processing the necessary images or video.
    Computer-Vision, in depth

04The applications

28 agriculture applications, each with a full report.

The widest first, by the number of use cases each covers. Every report shows what changed, how it works, who has done it and what can go wrong.

  1. Imagery-Based Nitrogen Prescription ReviewReview crop imagery, prepare a locally approved variable nitrogen map, verify its equipment handoff and reconcile the recorded application.Domain & Workflow Intelligence43 use cases
  2. Crop Disease Image Model QualificationBuild an expert-reviewed crop image reference, compare local classifiers, measure visible symptom extent where justified, and qualify a reviewed model release for its target device.Domain & Workflow Intelligence29 use cases
  3. On-Farm Yield Response EvaluationCompare an approved management change with current practice using qualified harvest records, replicated field trials and design-aware analysis, then review whether to adopt or retest it.Domain & Workflow Intelligence26 use cases
  4. Winter-Wheat Model Evaluation and ExplanationsEvaluate county-level winter-wheat estimates against transparent baselines, inspect growth-stage model attributions and release only evidence whose scope and data cutoff are clear.Classical Supervised ML23 use cases
  5. County Crop Yield Experiments with Weather and ImageryTest whether weather history and satellite imagery improve county-level crop-yield estimates over simple historical baselines. Use CropNet as a research starting point, verify data rights and release timing, and evaluate on untouched seasons and regions before offering a prospective planning forecast.Domain & Workflow Intelligence12 use cases
  6. Crop Quality Grading WorkflowsQualify crop-specific sample inspection and grading methods, compare their errors against reference observations, and carry reviewed evidence into accountable lot decisions.Computer Vision12 use cases
All 28 applications, A to Z

Work with us

The catalog shows what is possible. A sprint decides what you should fund.

Reading every report still leaves the hardest question open: which move is worth funding first, here, given your constraints. That is the sprint: two weeks, fixed scope, and a candid answer either way.

Book a 30-minute callHow the sprint works

Two weeks Fixed scope A candid fit-or-no-fit answer

  1. 01

    Three ranked opportunities

    A decision-ready shortlist scored against value, feasibility, evidence, risk, and time to proof.

  2. 02

    One pilot-ready workflow

    A bounded operating design with actors, handoffs, data needs, controls, and success measures.

  3. 03

    A defensible 90-day plan

    Build-versus-buy guidance, ROI assumptions, risk treatment, sequencing, and executive decisions.

05Rules & standards

Rules and standards to check, with their scope and sources.

Selected US and EU references for these workflows. Applicability depends on jurisdiction, organization, data and intended use. The planning notes are Atlas editorial guidance; they are not official implementation-time estimates or an exhaustive list of obligations.

  1. Pesticide label requirements

    Law or regulation

    United States · registered pesticide use

    Pesticide labels define legally enforceable directions for use. An AI-generated application prescription must stay within the applicable label and other relevant federal and state requirements.

    EPA: Introduction to Pesticide Labels

    Source checked

    Project planning note

    Check the crop, product, rate, method and restrictions against the current label before sending a prescription to equipment.

  2. Agricultural dispensing by drone · Part 137

    Law or regulation

    United States · agricultural UAS dispensing operations

    Agricultural drone dispensing has FAA certification and operating requirements. Applicable exemptions, certificates and operating permissions depend on the aircraft and operation; ordinary aerial imaging is a different use case.

    FAA: Dispensing Chemicals and Agricultural Products with UAS

    Source checked

    Project planning note

    Separate imaging from dispensing; confirm the operator’s permissions for the planned aircraft and flight.

Your next step

Find your first move in agriculture.

Ask the workspace which move fits your company. Add your size, systems and constraints, and it works from these 28 applications to a plan your team can act on.

Plan your first AI move

Rather talk it through? Book a 30-minute call