Skip to content

Plant perception · research model

Turn crop images into testable predictions.

Our visual classifier adapts a DINOv2 image encoder to field photographs and returns structured plant-problem predictions. Research teams can inspect the model version, scores and abstentions as they evaluate it for their own task. The current benchmark below establishes the starting point for this model product.

See the measured results

Benchmark

Where the model stands.

Our model46%
Hosted frontier model80%
Problem named correctly · 50 photos, 21 farms95% interval of the gap: 15–56 points · Measured 27 October 2026

Every human-judged photo in this comparison had been flagged by a hosted model. Confirmations inherit its problem name, which favours that model. Missed problems are not measured. The hosted comparator includes the model versions that originally read each photo.

The 95% interval resamples farms, not individual photos. The report records eight evaluations of the held-out farms, including reproductions and re-scoring. Repeated looks and the small sample limit how broadly this result can be interpreted.

Corrections remain an open problem

On a separate selection-fold diagnostic, the model returned the corrected name on 0 of 42 human-corrected photos. Those photos are not the held-out benchmark above. Expert labels and outcome training are next experiments, not a proven fix.

Download aggregate benchmark results · JSON

Sanitized aggregate results from the evaluation report generated 27 October 2026. Reviewed 4 November 2026; not a new benchmark run.

Next measurement

Evaluate an expert-labelled random sample, then test whether action and follow-up records improve results. Date not scheduled.

Preliminary result from one untuned fine-tune run. Problem naming was evaluated on 50 human-judged photos of real problems from 21 farms excluded from training.
MeasureValue
Evaluation set50 photos · 21 held-out farms
Our model23 of 50 · 46%
Hosted frontier model40 of 50 · 80%
Hosted advantage34 percentage points
95% farm-bootstrap interval of the gap15 to 56 points
Agreement with hosted labels, not accuracyAUROC 0.91 · 11 kinds · 2,704 photos
Measured27 October 2026

Research inference service

A prediction your software can use.

The private scorer returns a photo reference, model version, problem scores and an explicit abstention decision. These fields let a research pipeline compare predictions, track which model produced them and flag cases for review. The API contract is documented; customer access remains in development.

Developer reference

Portable model research

Bring inference closer to capture.

A local ONNX export provides a starting point for running the model where crop images are captured. The goal is field inference with less dependence on connectivity. Phone integration, accuracy after export and on-device latency still require validation.

Latency per photo
Not yet measured on device
Format
ONNX, 16 plant and site categories
artifact inspected 4 Nov 2026

Self-hosted inference · human review

Make uncertainty part of the record.

The product direction combines our own trained vision model with expert review. The research scorer already exposes abstention. The next step is to validate how those signals support a reviewer’s decisions, then evaluate whether verified follow-up observations improve the predictions.

Versioned model output

The scorer runs a model checkpoint through a local PyTorch or ONNX backend. Its structured response includes the model identifier and scores so results can be traced and compared.

Expert review of uncertain cases

The intended workflow presents uncertain cases to a person, preserves their corrections and links later observations. Reviewer time, missed problems and the value of additional models remain to be measured.

Research integration

Define a private model evaluation.

Tell us which growth, health or harvest-timing decision your model supports. We’ll agree on a benchmark, measure its errors and explain where evidence is missing. Your team receives a private report.

Tell Charles about your model, input format and proposed success metric. Private evaluation scope is agreed before any model or sensitive materials are exchanged.

charles@microhabitat.ca

Opens your email app. Nothing is sent from this website.

Website assistant

What would you like to know?

Ask about our crop AI, Farm Bot or field evaluations.

Enter to send · Shift + Enter for a new line

Anthropic receives your question, relevant earlier messages from this conversation and relevant source passages. Privacy