AI System for Preparing Harvest Readiness Observations

The problem

In day-to-day operations, harvest observations may be scattered across notes from different teams. When crop images, variety, planting date, field measurements, weather and plot notes are distributed across sensors, documents, field records or team systems, issues do not become visible in time.

This fragmented data delays preparation of the harvest observation list and forces teams to search for supporting evidence again by hand. Before making a decision, the agronomist or agricultural engineer must complete missing records and verify each conflict individually.

A common exception is that variety, shading and microclimate can alter appearance. Without this context check, incomplete or incorrect automation could direct a crop towards an early or late harvest, so no physical or operational action can be applied directly.

What we set out to improve

• Proportion of candidate plots for which the specialist requests additional measurements
• Proportion of outputs corrected or rejected by the agronomist or agricultural engineer
• Time between the source event and the inspection output

How the system works

1. 01 Define the review scope and the authorised agronomist or agricultural engineer role
2. 02 Retrieve inputs: crop images, variety, planting date, field measurements, weather and plot notes
3. 03 Check source identity, date, calibration or version, and data recency
4. 04 Combine images and measurements by plot
5. 05 Flag missing measurements and unusual development
6. 06 Check for an exception: variety, shading and microclimate can alter appearance
7. 07 Route low-confidence or conflicting records to a separate specialist queue
8. 08 Write the source identity, rule, output and timestamp to the audit trail
9. 09 Have the agronomist or agricultural engineer approve, correct, defer or reject the output

Methods we used

• Visual preclassification and integration of calendar and field data
• Source, format, timing and required-field checks for crop images, variety, planting date, field measurements, weather and plot notes
• A missing-data warning instead of an estimate when inputs are incomplete or conflicting
• Separate evaluation of exceptions and the main rule
• Combined retention of the source, rule result, harvest observation list and human decision

Where people stay involved

Data and security

Access to crop images, variety, planting date, field measurements, weather and plot notes is limited to the minimum permissions required for the task. Commercial, location and employee information is masked where possible, and only the necessary subset of the raw dataset is passed to the model. Access, outputs and the agronomist's or agricultural engineer's decisions are logged; the system is not released to production until the organisation approves the retention period and data location.

Who this suits

Frequently asked questions