- Published model
eq_operational_S2_gear1_v2-ecb87f020f99- Window
- 30 days
- Second look at 2023–2025
- ranking accuracy 96.9%; information gain 2.61 nats per M6+ cell-window (a cell’s 30 days that held an M6+) over a uniform map
- Live record of this version
- 50 (1 non-overlapping) closed 30-day forecasts (they overlap), 24 distinct M6+ earthquakes; no score yet: 1 non-overlapping 30-day window so far (a score is quoted from 2)
- Forecasts recorded
- 923 (798 closed and scored, 1 waiting)
- Ledger
- 934 chained rows, 0 breaks
Track record
How the forecasts have scored
Two kinds of evidence, kept apart. Test results: how each published model scored on years held back from its development, in tests written down before the data was scored. Live record: how the forecasts we actually published scored once their windows closed. If a live model is not scored yet, this page says so directly. It also shows any scoring backlogs.
In numbers
3,640
forecasts recorded
Every published forecast, frozen with its inputs.
3,490
closed and scored
Windows that have ended and been scored against what happened.
9
waiting to be scored
Windows that have ended but are not scored yet.
0
breaks in the ledgers
Each entry carries the previous entry’s hash, so an edit to history would show here.
Needs attention
- 9 matured forecast windows are waiting for scoring.
By hazard
- Published numbers
- NOAA DTOPS (SHIPS-RII as fallback) for the Atlantic, East and Central Pacific; HazardPulse v8.3 elsewhere, tested on 2025–2026 cycles in the basins where it publishes, none used to fit it, with best-track inputs
- Window
- 24 hours
- Test, 2025 season (scored once)
- DTOPS ranking accuracy 92.8%, Brier skill 0.31; 601 cycles, 44 rapid intensifications
- Live record of the published models
- NOAA DTOPS (SHIPS-RII as fallback), Atlantic, East and Central Pacific: 181 storm-cycles, 22 rapid intensifications; Brier score 0.062, ranking accuracy 94.4%; HazardPulse v8.3, elsewhere: 174 storm-cycles, 21 rapid intensifications; Brier score 0.082, ranking accuracy 81.2%
- Forecasts recorded
- 256 (247 closed and scored, 5 waiting)
- Ledger
- 197 chained rows, 0 breaks
- Published model
tornado_v3-05a06c843c87- Window
- 60 minutes
- Test, 2025 (scored once)
- ranking accuracy 97.0%, Brier skill 0.11; 1,469,977 storm observations, 1,579 tornadic
- Live record of this version
- 35,125 storm forecasts, 43 tornadic; ranking accuracy 95.7%
- Forecasts recorded
- 2,461 (2,445 closed and scored, 3 waiting)
- Ledger
- 2,527 chained rows, 0 breaks
- Row hashes
- 2,357 rows match their own hash; 170 earlier rows match it with
forecast_idremoved (they were hashed before that field was added); 0 mismatches
Live record, by model version
Every model version that has published a number, including retired ones. A score is shown only once 10 or more events have been observed for that version: with fewer, a model that always says “no” would look as good as a skilful one. Earthquake forecasts are issued several times a day for 30 days ahead, so their windows overlap: each earthquake is counted once, and a score also needs two windows that do not overlap.
| Hazard | Model version | Status | Forecasts closed | Events observed | Score |
|---|---|---|---|---|---|
| Earthquake | eq_coherence_v1_0 | retired | 717 (7 non-overlapping) | 87 | ranking 65.8%; information gain per M6+ earthquake per window vs a uniform map −15.47 (averaged over overlapping windows) |
| Earthquake | eq_operational_C0_v1-d28c62a2e35b | retired | 3 (1 non-overlapping) | 23 | no score yet: 1 non-overlapping 30-day window so far (a score is quoted from 2) |
| Earthquake | eq_operational_S1_gear1_v1-d409c534bb4c | retired | 28 (1 non-overlapping) | 26 | no score yet: 1 non-overlapping 30-day window so far (a score is quoted from 2) |
| Earthquake | eq_operational_S2_gear1_v2-ecb87f020f99 | published | 50 (1 non-overlapping) | 24 | no score yet: 1 non-overlapping 30-day window so far (a score is quoted from 2) |
| Tornado | tornado_storm_v1_0 | retired | 233,600 | 634 | ranking 74.2%; Brier skill vs climatology −8.45 |
| Tornado | tornado_v3-05a06c843c87 | published | 35,125 | 43 | ranking 95.7%; Brier skill vs climatology 0.08 |
| Tornado | tornado_v3-9005905f08b7 | retired | 1,807 | 0 | too few events to score yet (need 10) |
| Hurricane | hurricane_ri_stack_v1-35938d6c09b7 | published | 181 | 22 | ranking 94.4%; Brier score 0.06 |
| Hurricane | hurricane_ri_v8_2 | retired | 33 | 6 | too few events to score yet (need 10) |
| Hurricane | hurricane_ri_v8_3 | published | 174 | 21 | ranking 81.2%; Brier score 0.08 |
| Hurricane | jtwc_warning_ingest | retired | 5 | 0 | too few events to score yet (need 10) |
Does a 10% forecast come true 1 time in 10?
Calibration compares what was forecast with what happened. The published tornado model’s 2025 test, split by how high the forecast was. Live calibration is measured once enough forecasts with events have closed.
| Forecast range | Storm observations | Average forecast | Tornado followed | 95% interval |
|---|---|---|---|---|
| 0%–0.1% | 1,340,592 | <0.01% | 0.01% | <0.01%–0.01% |
| 0.1%–0.2% | 44,834 | 0.14% | 0.13% | 0.10%–0.17% |
| 0.2%–0.5% | 39,904 | 0.32% | 0.29% | 0.24%–0.35% |
| 0.5%–1.0% | 18,840 | 0.70% | 0.58% | 0.48%–0.70% |
| 1.0%–2.0% | 11,724 | 1.40% | 1.17% | 0.99%–1.38% |
| 2.0%–5.0% | 8,184 | 3.09% | 2.30% | 1.99%–2.64% |
| 5.0%–10.0% | 3,231 | 7.03% | 6.96% | 6.12%–7.88% |
| 10.0%–20.0% | 1,595 | 13.76% | 16.99% | 15.21%–18.89% |
| 20.0%–30.0% | 430 | 24.49% | 21.86% | 18.15%–25.95% |
| 30.0%–50.0% | 641 | 37.65% | 34.63% | 31.03%–38.38% |
| 50.0%–100% | 2 | 51.27% | 50.00% | 6.08%–93.92% |
In a well-calibrated row the two middle numbers agree. Every breakdown of the tornado test