Weather Station Status



This website uses WeeWX for weather conditions reporting.
Latest weather observation: 30/10/2026 06:25.

Component Status Age
h:m:s
Latest update time as of
30/10/2026 06:26
Live WeeWX observationsCurrent0:00:4830/10/2026 06:25
Met Office forecastCurrent0:21:0430/10/2026 06:05
Trearddur Bay tide dataCurrent6:25:2430/10/2026 00:00
Vestaboard weather updateNOT Current7:56:04> 2:00:00
29/10/2026 22:30
Automated ntfy monitoringCurrent0:01:0530/10/2026 06:25
Web configuration backupCurrent4:11:0030/10/2026 02:15
WeeWX configuration backupCurrent3:56:0530/10/2026 02:30
Local wind forecast modelCurrent0:08:4030/10/2026 06:17
External forecast inputsCurrent0:10:2530/10/2026 06:15

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 366 1.6 kt 1.6 kt Collecting 2.6 kt 11° 2.3 kt 89% exact; safety score 96% (8 unsafe suitable calls) 50%: 51% of 366
80%: 90% of 366
+2 hours 366 2.4 kt 2.4 kt Collecting 3.0 kt 16° 2.5 kt 82% exact; safety score 94% (11 unsafe suitable calls) 50%: 43% of 366
80%: 78% of 366
+3 hours 366 2.6 kt 2.6 kt Collecting 3.0 kt 19° 2.4 kt 80% exact; safety score 94% (11 unsafe suitable calls) 50%: 37% of 366
80%: 74% of 366
+4 hours 367 2.5 kt 2.5 kt Collecting 2.9 kt 20° 2.4 kt 78% exact; safety score 93% (13 unsafe suitable calls) 50%: 35% of 367
80%: 72% 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 20261030T013224Z-584527c3 was held back. candidate must improve composite error by at least 2%: 4.53 versus required 4.39

Forecast data quality

Healthy Latest observation age: 7 minutes · Excluded implausible rows: 31 · 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: 89; persistence: 89.

Upstream model-feature archive: 81.3 days; RAF Valley 3935 records; Met Office land 1803 records. Enabled for training

Met Office revision archive: 6709 snapshots, 1549 changed forecast versions and 333886 timestamped forecast rows retained.

Current upstream changes: RAF Valley rising +2.0 kt; Met Office land stations steady -0.7 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%
+6hmetOfficemetOffice 100%local, corrected, persistencemetOffice 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
N180.7 kt0.9 kt104°±1.5 kt50%: 94% of 18
80%: 100% of 18
SE5291.9 kt2.0 kt16°±2.8 kt50%: 26% of 529
80%: 54% of 529
S7492.3 kt2.9 kt15°±3.8 kt50%: 47% of 749
80%: 80% of 749
SW8322.7 kt3.4 kt16°±4.4 kt50%: 38% of 832
80%: 87% of 832
W363.1 kt3.6 kt29°±5.3 kt50%: 39% of 36
80%: 97% of 36
NW362.0 kt2.1 kt77°±3.1 kt50%: 56% of 36
80%: 94% of 36

Direction-calibration safeguards

+1h SE sector: Held back — held back: held-out error 2.80 versus 2.60 without correction.
+2h SE sector: Applied — held-out error improved from 2.84 to 2.39.
+3h SE sector: Applied — held-out error improved from 2.61 to 1.96.
+4h SE sector: Applied — held-out error improved from 2.66 to 1.76.
+5h SE sector: Applied — held-out error improved from 2.75 to 1.85.
+6h SE sector: Applied — held-out error improved from 2.82 to 1.88.

Nearby-station lead analysis

Positive lead means the nearby station changes before Ravenspoint.

StationBest leadCorrelationSamplesRepeatable
Met Office Isle of Anglesey30 min0.92487Yes
RAF Valley0 min0.91991Yes
Met Office Gwynedd45 min0.89487Yes
Met Office Conwy0 min0.85489Yes

Recent model candidates

20261030T013224Z-584527c3 — Held back. candidate must improve composite error by at least 2%: 4.53 versus required 4.39
20261029T011725Z-9d4b7b38 — Held back. candidate must improve composite error by at least 2%: 4.53 versus required 4.39
20261028T011724Z-17e9d16b — Held back. candidate must improve composite error by at least 2%: 4.52 versus required 4.39
20261027T011724Z-8ae70733 — Held back. candidate must improve composite error by at least 2%: 4.53 versus required 4.39
20261026T010225Z-34e49c7a — Held back. candidate must improve composite error by at least 2%: 4.53 versus required 4.39
20261025T004744Z-c72f9672 — Held back. candidate must improve composite error by at least 2%: 4.52 versus required 4.39
20261024T004744Z-ed498dec — Held back. candidate must improve composite error by at least 2%: 4.53 versus required 4.39
20261023T003224Z-b4c874c6 — Held back. candidate must improve composite error by at least 2%: 4.53 versus required 4.39
20261022T003219Z-bc622192 — Held back. candidate must improve composite error by at least 2%: 4.53 versus required 4.39
20261021T003212Z-a9a04c69 — 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: 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 correct70 (42%)
Trend direction correct45%
Average wind-strength error5.6 kt
18-knot threshold correct88%

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: 39% correct from 103 forecasts; 4.7 kt average error 44 8.8 kt 0 kt Fully correct Average error (kt)