Weather Station Status



This website uses WeeWX for weather conditions reporting.
Latest weather observation: 09/11/2026 15:57.

Component Status Age
h:m:s
Latest update time as of
09/11/2026 15:57
Live WeeWX observationsCurrent0:00:1809/11/2026 15:57
Met Office forecastCurrent0:52:3609/11/2026 15:05
Trearddur Bay tide dataCurrent15:57:0509/11/2026 00:00
Vestaboard weather updateCurrent0:27:3509/11/2026 15:30
Automated ntfy monitoringCurrent0:02:3609/11/2026 15:55
Web configuration backupCurrent13:42:3109/11/2026 02:15
WeeWX configuration backupCurrent13:27:3609/11/2026 02:30
Local wind forecast modelCurrent0:09:3309/11/2026 15:48
External forecast inputsCurrent0:11:4509/11/2026 15:45

Experimental Ravenspoint model

Four-hour wind forecast accuracy

Confidence Established

These are live results from forecasts published on the landing page, checked against subsequent Ravenspoint observations. The system now favours whichever input has recently performed best. Lower error figures are better.

ForecastAssessed7-day wind error30-day wind errorTrendGust errorDirection errorMet Office wind errorSailing decisionsRange coverage
+1 hour 367 1.1 kt 1.1 kt Collecting 1.8 kt 25° 1.5 kt 100% exact; safety score 100% (0 unsafe suitable calls) 50%: 52% of 367
80%: 82% of 367
+2 hours 367 1.2 kt 1.2 kt Collecting 2.7 kt 33° 1.5 kt 100% exact; safety score 100% (0 unsafe suitable calls) 50%: 52% of 367
80%: 84% of 367
+3 hours 367 1.3 kt 1.3 kt Collecting 2.5 kt 36° 1.5 kt 100% exact; safety score 100% (0 unsafe suitable calls) 50%: 56% of 367
80%: 86% of 367
+4 hours 367 1.3 kt 1.3 kt Collecting 2.6 kt 35° 1.5 kt 100% exact; safety score 100% (0 unsafe suitable calls) 50%: 50% of 367
80%: 83% of 367

2200 forecast outcomes assessed in total. Unsafe “suitable” calls carry five times the penalty of an ordinary classification error. Forecast ranges target 80% coverage.

Model safeguard: candidate 20261109T031735Z-043e5a01 was held back. candidate must improve composite error by at least 2%: 4.51 versus required 4.39

Forecast data quality

Healthy Latest observation age: 7 minutes · Excluded implausible rows: 36 · Units: metric-normalised-v2.

Weather regime: Showery / unstable.

Safety guard active Local model remains within the live safety limit. Comparisons: 2200; local unsafe suitable calls: 0; persistence: 0.

Upstream model-feature archive: 91.7 days; RAF Valley 4434 records; Met Office land 2053 records. Enabled for training

Met Office revision archive: 7707 snapshots, 1798 changed forecast versions and 382788 timestamped forecast rows retained.

Current upstream changes: RAF Valley falling -2.0 kt; Met Office land stations steady +0.4 kt. Upstream changes remain shadow inputs until the 60-day readiness gate is met.

Current forecast decision audit

HorizonSelected sourceWeightsExcludedReasonChange outlook
+1hlocallocal 85%, persistence 15%historicalDifferential, metOfficelocal had the lowest recency-weighted error; sources more than 8% worse were excluded.Steady; direction shift 0%
+2hlocallocal 85%, persistence 15%historicalDifferential, metOfficelocal had the lowest recency-weighted error; sources more than 8% worse were excluded.Steady; direction shift 0%
+3hlocallocal 85%, persistence 15%metOfficelocal had the lowest recency-weighted error; sources more than 8% worse were excluded.Steady; direction shift 0%
+4hlocallocal 85%, persistence 15%metOfficelocal had the lowest recency-weighted error; sources more than 8% worse were excluded.Steady; direction shift 0%
+5hlocallocal 85%, persistence 15%metOfficelocal had the lowest recency-weighted error; sources more than 8% worse were excluded.Steady; direction shift 0%
+6hlocallocal 85%, persistence 15%metOfficelocal had the lowest recency-weighted error; sources more than 8% worse were excluded.Steady; direction shift 0%

Direct gust and change models

+1h: gust classifiers 18 kt or more, 20 kt or more, 25 kt or more, 30 kt or more passed; wind-change classifier held back; direction-change classifier held back.
+2h: gust classifiers 18 kt or more, 20 kt or more, 25 kt or more, 30 kt or more passed; wind-change classifier held back; direction-change classifier held back.
+3h: gust classifiers 18 kt or more, 20 kt or more, 25 kt or more, 30 kt or more passed; wind-change classifier held back; direction-change classifier held back.
+4h: gust classifiers 18 kt or more, 20 kt or more, 25 kt or more, 30 kt or more passed; wind-change classifier held back; direction-change classifier held back.
+5h: gust classifiers 18 kt or more, 20 kt or more, 25 kt or more, 30 kt or more passed; wind-change classifier held back; direction-change classifier held back.
+6h: gust classifiers 18 kt or more, 20 kt or more, 25 kt or more, 30 kt or more passed; wind-change classifier held back; direction-change classifier held back.

Accuracy by observed wind direction (30 days)

DirectionAssessedWind errorGust errorDirection error80% error allowanceRange coverage
N812.2 kt4.1 kt117°±3.0 kt50%: 36% of 81
80%: 72% of 81
NE7191.0 kt2.5 kt19°±1.5 kt50%: 63% of 719
80%: 92% of 719
E7701.1 kt2.2 kt27°±1.8 kt50%: 59% of 770
80%: 87% of 770
SE2531.9 kt3.0 kt45°±3.0 kt50%: 28% of 253
80%: 69% of 253
S2821.2 kt2.6 kt38°±1.9 kt50%: 48% of 282
80%: 83% of 282
SW241.4 kt3.5 kt71°±2.4 kt50%: 42% of 24
80%: 92% of 24
W303.7 kt5.8 kt91°±5.3 kt50%: 13% of 30
80%: 40% of 30
NW412.3 kt3.4 kt117°±2.6 kt50%: 39% of 41
80%: 73% of 41

Direction-calibration safeguards

+1h NE sector: Held back — held back: held-out error 1.46 versus 1.42 without correction.
+2h NE sector: Applied — held-out error improved from 1.70 to 1.48.
+3h NE sector: Applied — held-out error improved from 1.76 to 1.59.
+4h NE sector: Held back — held back: held-out error 2.22 versus 2.12 without correction.
+5h NE sector: Held back — held back: held-out error 2.48 versus 1.96 without correction.
+6h NE sector: Held back — held back: held-out error 1.84 versus 1.63 without correction.

Nearby-station lead analysis

Positive lead means the nearby station changes before Ravenspoint.

StationBest leadCorrelationSamplesRepeatable
RAF Valley0 min0.941382Yes
Met Office Isle of Anglesey30 min0.94684Yes
Met Office Gwynedd0 min0.91687Yes
Met Office Conwy0 min0.82686Yes

Recent model candidates

20261109T031735Z-043e5a01 — Held back. candidate must improve composite error by at least 2%: 4.51 versus required 4.39
20261108T031734Z-addab19d — Held back. candidate must improve composite error by at least 2%: 4.52 versus required 4.39
20261107T030229Z-39f363e8 — Held back. candidate must improve composite error by at least 2%: 4.52 versus required 4.39
20261106T024744Z-de10484d — Held back. candidate must improve composite error by at least 2%: 4.52 versus required 4.39
20261105T023225Z-21375bc8 — Held back. candidate must improve composite error by at least 2%: 4.52 versus required 4.39
20261104T021744Z-e04be226 — Held back. candidate must improve composite error by at least 2%: 4.51 versus required 4.39
20261103T021736Z-2e3a5d78 — Held back. candidate must improve composite error by at least 2%: 4.52 versus required 4.39
20261102T020239Z-2feb28e4 — Held back. candidate must improve composite error by at least 2%: 4.52 versus required 4.39
20261101T020224Z-ee92e730 — Held back. candidate must improve composite error by at least 2%: 4.53 versus required 4.39
20261031T014724Z-dd8f2758 — Held back. candidate must improve composite error by at least 2%: 4.52 versus required 4.39

Met Office warning feed

Current Source: NSWWS API · Active warnings: 0 · Last checked: 2 minutes ago.

Three-hour trend indicator accuracy

This is a separate rolling seven-day check of the “increasing, steady or falling” message shown with live wind. It is not the six-hour forecasting model above.

Forecasts assessed168
Fully correct90 (54%)
Trend direction correct54%
Average wind-strength error3.2 kt
18-knot threshold correct99%

Weekly accuracy history

Weekly wind-trend forecast accuracy Blue columns show fully correct predictions as a percentage. The red line shows average wind-strength error in knots. 0% 25% 50% 75% 100% 2026-W32: 0% correct from 2 forecasts; 8.8 kt average error 32 2026-W33: 50% correct from 132 forecasts; 4.0 kt average error 33 2026-W34: 38% correct from 168 forecasts; 4.6 kt average error 34 2026-W35: 39% correct from 164 forecasts; 4.1 kt average error 35 2026-W36: 37% correct from 168 forecasts; 4.3 kt average error 36 2026-W37: 44% correct from 99 forecasts; 4.2 kt average error 37 2026-W38: 39% correct from 168 forecasts; 4.4 kt average error 38 2026-W39: 44% correct from 168 forecasts; 4.0 kt average error 39 2026-W40: 29% correct from 72 forecasts; 5.7 kt average error 40 2026-W41: 23% correct from 22 forecasts; 4.8 kt average error 41 2026-W42: 42% correct from 155 forecasts; 4.6 kt average error 42 2026-W43: 48% correct from 104 forecasts; 6.8 kt average error 43 2026-W44: 43% correct from 168 forecasts; 4.6 kt average error 44 2026-W45: 52% correct from 168 forecasts; 3.4 kt average error 45 2026-W46: 81% correct from 16 forecasts; 2.0 kt average error 46 8.8 kt 0 kt Fully correct Average error (kt)