Harvora™ model-card brief
Pollination weather planning model card
This model card documents the method, evidence target and limitations for pollination weather planning. The benchmark is independent forecast-versus-ERA5 weather reproduction: it validates the weather-suitability call, not fruit set or hive outcomes — those remain a separate outcome track.
Direct answer
What this supports
The pollination surface counts bee-flyable hours across the flowering window so bee placement and bloom weather can be planned together.
Intended for New Zealand growers, technical partners, lenders and insurers.
Evidence and method
How the signal is formed
Hourly temperature, wind, rainfall and daylight are combined into bee-flyable criteria and sampled across the bloom window as a Monte Carlo distribution.
Evidence grade: ESTIMATE
Weather-benchmark measured today; every grower outcome logged in the product feeds the field benchmark it is measured against next.
Boundary
How to read this evidence
The benchmark is independent forecast-versus-ERA5 weather reproduction: it validates the weather-suitability call, not fruit set or hive outcomes — those remain a separate outcome track.
Sources and related evidence
- Open-Meteo historical forecast API · SOURCED
- Harvora public technical brief · SOURCED
- Harvora source register · SOURCED
Published 25 August 2026 · Last reviewed 25 August 2026 · Harvora technical review
Apply it to your operation