Harvora™ model-card brief
Wind-damage watch for orchards model card
This model card documents the method, evidence target and limitations for wind-damage watch for orchards. The watch is fitted on forecast-only daily weather from the prior season at a fixed sensitivity operating point — forecast-versus-ERA5 wind-weather evidence, not observed orchard-damage validation. A source-derived 97% companion figure exists as a separate evidence tier and is never blended into this number.
Direct answer
What this supports
Wind surfaces report a day-level protection and labour signal with peak-gust context; local exposure and shelter modify the on-block reading.
Intended for New Zealand growers, technical partners, lenders and insurers.
Evidence and method
How the signal is formed
Forecast gusts are screened against a sensitivity-prioritised damaging-wind threshold and sampled as a distribution of damaging-gust hours.
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 watch is fitted on forecast-only daily weather from the prior season at a fixed sensitivity operating point — forecast-versus-ERA5 wind-weather evidence, not observed orchard-damage validation. A source-derived 97% companion figure exists as a separate evidence tier and is never blended into this number.
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