← 2026-10-31  |  2026-11-03 →

Richland Creek — Daily Analysis: 2026-11-01

Classification: correct Confidence: Model continues to perform well in dry conditions, correctly filtering out QPE noise. The gap between predicted (0.24 ft) and actual (0.55 ft) peaks is small in absolute terms and consistent with baseflow variability. Confidence remains medium.

Event Summary

The model correctly identified a quiet day with minimal rainfall, predicting a near-baseline peak that aligned with the observed small rise.

Prediction vs Actual

Metric Predicted Actual Error
Peak height 0.24 ft 0.55 ft -0.31 ft
Total rise — 0.38 ft —

Band Contributions

Band Zone Precip Predicted Rise Intensity Moisture
1 ? 0.05" 0.00 ft LIGHT VERY DRY
2 ? 0.03" 0.00 ft - VERY DRY

Empirical Forecast

Headline: No rise indicated by recent rainfall Settled outcome: None (reached None) LLM said headline was correct: True Notes: The empirical model called 'No rise indicated by recent rainfall'. The gauge did see a small rise (0.38 ft) but from a very low base, staying well below the 'low_floatable' threshold of 4.0 ft. In the context of recreational usability, this is a correct 'no rise' call.

Analysis

The event on 2026-11-01 was characterized by negligible rainfall (0.0" at the gauge, ~0.05" QPE) under VERY DRY antecedent conditions. The predictor issued a peak of 0.24 ft, while the gauge recorded a maximum of 0.55 ft (a 0.38 ft rise from a very low baseflow of 0.17 ft). Although the absolute peak error is significant (-56%), the context of a dry watershed with near-zero effective rainfall means the model correctly captured the 'no meaningful flood' character of the day. The rise was slow and broad, consistent with baseflow adjustments rather than storm runoff. The prediction was within the expected noise range for dry conditions where small QPE artifacts can trigger minor, non-storm fluctuations.

Graded Prediction

Predictions issued today (archive): 12 active issuance(s) from 2026-11-01T05:20:02.175567+00:00 to 2026-11-01T16:20:02.612218+00:00; issued peaks ranged 0.17 to 0.24 ft. The prediction graded below is the HIGHEST issued peak of the day (issued 2026-11-01T16:20:02.612218+00:00), not the last card of the day.

Coefficient Adjustments

Grade-only mode: no adjustments suggested; calibration is fit offline.

Notes

Model continues to perform well in dry conditions, correctly filtering out QPE noise. The gap between predicted (0.24 ft) and actual (0.55 ft) peaks is small in absolute terms and consistent with baseflow variability. Confidence remains medium.

← 2026-10-31  |  2026-11-03 →