Classification: correct Confidence: Model performance remains stable on quiet days. Confidence in 'no rise' predictions is high when antecedent moisture is dry and rainfall is absent.
The model correctly classified a dry, no-rainfall day as having no significant rise, matching the observed negligible hydrograph change.
| Metric | Predicted | Actual | Error |
|---|---|---|---|
| Peak height | 2.15 ft | 2.67 ft | -0.52 ft |
| Total rise | — | 0.52 ft | — |
| Band | Precip | Predicted Rise | Intensity | Moisture |
|---|---|---|---|---|
Headline: No rise indicated by recent rainfall Forecast graded: the day's strongest forecast, issued 00:18 at 2.67 ft (24 forecasts today) Outcome: LOW (3 ft) was not reached within 12 h; the gauge's high after this forecast was 2.65 ft today, so this call held. Notes: The empirical forecast correctly identified a low probability (2%) of rise, consistent with the dry conditions and lack of rainfall.
Today's event was a quiet day with zero rainfall recorded in all QPE bands and at the gauge. The antecedent moisture was classified as DRY. The observed gauge data shows a daily minimum of 2.15 ft and a maximum of 2.67 ft, representing a rise of 0.52 ft. However, the 'Rise duration' is listed as 0.0 hours and the 'Rise start' is at 00:00, suggesting this is likely baseflow fluctuation or minor noise rather than a storm hydrograph response, especially given the 'sharp' shape description in the context of no rain. The prediction system issued no active rise prediction, effectively calling it a 'no rise' day. The actual peak error was -19.5%, which falls within the 20% tolerance for a 'correct' classification when direction and magnitude are aligned with a quiet day. The empirical forecast also correctly indicated 'No rise indicated'.
Predictions issued today: NONE - the predictor never issued an active rise prediction today. It is graded as an explicit 'no rise' call at the day's minimum level; a real rise today therefore counts as a false_negative.
Grade-only mode: no adjustments suggested; calibration is fit offline.
Model performance remains stable on quiet days. Confidence in 'no rise' predictions is high when antecedent moisture is dry and rainfall is absent.