Weather Station Status



This website uses WeeWX for weather conditions reporting.
Latest weather observation: 24/09/2026 23:36.

Component Status Age
h:m:s
Latest update time as of
24/09/2026 23:36
Live WeeWX observationsCurrent0:00:1924/09/2026 23:36
Met Office forecastCurrent0:31:3624/09/2026 23:05
Trearddur Bay tide dataCurrent22:35:5124/09/2026 01:00
Vestaboard weather updateCurrent1:06:3524/09/2026 22:30
Automated ntfy monitoringCurrent0:01:3624/09/2026 23:35
Web configuration backupCurrent21:21:3124/09/2026 02:15
WeeWX configuration backupCurrent21:06:3624/09/2026 02:30
Local wind forecast modelCurrent0:04:0324/09/2026 23:32
External forecast inputsCurrent0:05:4724/09/2026 23:30

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 1.5 kt 1.5 kt Collecting 2.3 kt 12° 1.6 kt 87% exact; safety score 94% (13 unsafe suitable calls) 50%: 44% of 367
80%: 77% of 367
+2 hours 367 1.8 kt 1.8 kt Collecting 3.1 kt 17° 1.7 kt 83% exact; safety score 93% (16 unsafe suitable calls) 50%: 41% of 367
80%: 71% of 367
+3 hours 366 1.7 kt 1.7 kt Collecting 2.9 kt 19° 1.8 kt 83% exact; safety score 91% (24 unsafe suitable calls) 50%: 43% of 366
80%: 75% of 366
+4 hours 366 1.6 kt 1.6 kt Collecting 2.7 kt 18° 1.8 kt 81% exact; safety score 91% (22 unsafe suitable calls) 50%: 47% of 366
80%: 77% of 366

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 20260924T163221Z-204829f1 was held back. candidate must improve composite error by at least 2%: 4.47 versus required 4.43

Forecast data quality

Healthy Latest observation age: 7 minutes · Excluded implausible rows: 11 · 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: 125; persistence: 125.

Upstream model-feature archive: 46.0 days; RAF Valley 2215 records; Met Office land 956 records. Collecting safely

Met Office revision archive: 3323 snapshots, 702 changed forecast versions and 167972 timestamped forecast rows retained.

Current upstream changes: RAF Valley steady +0.0 kt; Met Office land stations steady -1.5 kt. Upstream changes remain shadow inputs until the 60-day readiness gate is met.

Current forecast decision audit

HorizonSelected sourceWeightsExcludedReasonChange outlook
+1hcorrectedcorrected 100%local, historicalDifferential, metOffice, persistencecorrected had the lowest recency-weighted error; sources more than 8% worse were excluded.Steady; direction shift 0%
+2hcorrectedcorrected 100%local, historicalDifferential, metOffice, persistencecorrected had the lowest recency-weighted error; sources more than 8% worse were excluded.Steady; direction shift 0%
+3hcorrectedcorrected 100%local, metOffice, persistencecorrected had the lowest recency-weighted error; sources more than 8% worse were excluded.Steady; direction shift 0%
+4hcorrectedcorrected 100%local, metOffice, persistencecorrected had the lowest recency-weighted error; sources more than 8% worse were excluded.Steady; direction shift 0%
+5hcorrectedcorrected 100%local, metOffice, persistencecorrected had the lowest recency-weighted error; sources more than 8% worse were excluded.Steady; direction shift 0%
+6hcorrectedcorrected 100%local, metOffice, persistencecorrected had the lowest recency-weighted error; sources more than 8% worse were excluded.Falling; direction shift 100%

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
N1152.2 kt3.8 kt26°±3.4 kt50%: 42% of 115
80%: 70% of 115
NE290.9 kt2.0 kt38°±1.5 kt50%: 59% of 29
80%: 83% of 29
E1621.0 kt2.1 kt32°±1.7 kt50%: 65% of 162
80%: 92% of 162
SE533.0 kt4.6 kt16°±5.9 kt50%: 38% of 53
80%: 47% of 53
S14461.4 kt2.5 kt15°±2.2 kt50%: 46% of 1446
80%: 78% of 1446
SW1371.2 kt2.6 kt11°±2.0 kt50%: 42% of 137
80%: 75% of 137
W541.6 kt2.0 kt20°±2.6 kt50%: 56% of 54
80%: 93% of 54
NW2043.4 kt4.4 kt20°±4.8 kt50%: 12% of 204
80%: 44% of 204

Direction-calibration safeguards

+1h S sector: Held back — held back: held-out error 2.63 versus 2.61 without correction.
+2h S sector: Held back — held back: held-out error 3.78 versus 3.75 without correction.
+3h S sector: Held back — held back: held-out error 2.98 versus 2.99 without correction.
+4h S sector: Held back — held back: held-out error 3.22 versus 3.26 without correction.
+5h S sector: Applied — held-out error improved from 3.37 to 3.29.
+6h S sector: Applied — held-out error improved from 3.07 to 2.92.

Nearby-station lead analysis

Positive lead means the nearby station changes before Ravenspoint.

StationBest leadCorrelationSamplesRepeatable
Met Office Isle of Anglesey30 min0.86694Yes
RAF Valley0 min0.851398Yes
Met Office Gwynedd15 min0.80690Yes
Met Office Conwy0 min0.71688Yes

Recent model candidates

20260924T163221Z-204829f1 — Held back. candidate must improve composite error by at least 2%: 4.47 versus required 4.43
20260923T163221Z-98416e1e — Held back. candidate must improve composite error by at least 2%: 4.47 versus required 4.43
20260922T161721Z-f8435eae — Held back. candidate must improve composite error by at least 2%: 4.47 versus required 4.43
20260921T160231Z-68434561 — Held back. candidate must improve composite error by at least 2%: 4.46 versus required 4.43
20260920T154731Z-eb10dfb6 — Held back. candidate must improve composite error by at least 2%: 4.47 versus required 4.43
20260919T153253Z-7dc3e4de — Held back. candidate must improve composite error by at least 2%: 4.46 versus required 4.43
20260918T153211Z-ad338611 — Held back. candidate must improve composite error by at least 2%: 4.46 versus required 4.43
20260917T153211Z-947d70eb — Held back. candidate must improve composite error by at least 2%: 4.45 versus required 4.43
20260916T151741Z-ab59ad2a — Held back. candidate must improve composite error by at least 2%: 4.45 versus required 4.43
20260915T150221Z-d05d2fdb — Held back. candidate must improve composite error by at least 2%: 4.46 versus required 4.43

Met Office warning feed

Current Source: NSWWS API · Active warnings: 0 · Last checked: 1 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 correct76 (45%)
Trend direction correct50%
Average wind-strength error4.0 kt
18-knot threshold correct87%

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: 49% correct from 96 forecasts; 3.8 kt average error 39 8.8 kt 0 kt Fully correct Average error (kt)