← Back to Buffalo River Dashboard
A small neural network watches the last 48 hours of 1 km radar rainfall over every square of the watershed above these gauges — plus the gauges' own recent behavior — and projects the level forward hour by hour. It was trained on 12 years of storms and validated against every year it never saw.
Based only on rain that has already fallen. If more rain falls, these numbers become the floor, not the forecast — the model re-issues every hour as new radar arrives. Experimental: trust the main dashboard and your own judgment first.
| Time | Predicted (cfs) | Likely range |
|---|---|---|
| +1 hr (7:00 PM) | 55 | 54 – 56 |
| +2 hr (8:00 PM) | 54 | 54 – 56 |
| +3 hr (9:00 PM) | 54 | 52 – 56 |
| +4 hr (10:00 PM) | 53 | 51 – 55 |
| +5 hr (11:00 PM) | 52 | 50 – 54 |
| +6 hr (12:00 AM) | 51 | 49 – 53 |
| Time | Predicted (cfs) | Likely range |
|---|---|---|
| +1 hr (7:00 PM) | 21 | 21 – 22 |
| +2 hr (8:00 PM) | 21 | 20 – 22 |
| +3 hr (9:00 PM) | 20 | 20 – 21 |
| +4 hr (10:00 PM) | 20 | 20 – 21 |
Predicted value is the model's median; the likely range spans its 25th–75th percentile. Boxley gets a shorter window because its smaller upstream basin gives the radar less lead time. Model: pixel-v5, running on-site — no cloud services. Want the full story — the architecture, the training, the failed experiments? Understand the math →