Raw model output on the native 0.25° grid — no MOS, no bias correction, no post-processing. Scores understate operational forecast quality. Read the fairness statement →

CastCheck methodology v0.2 · data through 2026-08-30

Los Angeles Intl · Pangu-Weather (GFS init) · lead day 1

KLAX · pangu_gfs · lead 1

Target day = initialization date + 1 day. This page is a permanent link: the numbers change as history accumulates, the address and the methodology version do not.

Scores use the latest model version segment, PANG_v100, starting 2026-08-28 — days before that ran a different version of the model and are excluded rather than silently pooled. Of the scored days, 2 carry a QC flag on the observation.

JSON for this page CSV of the daily errors Cite this page

Every number for this combination

All four windows × both initializations × both interpolations × both variables. Errors are computed in °C and shown in °F; CI is a 95 % moving-block bootstrap interval. MAE debiased and skill, debiased remove the constant offset of the window first, so a station that the model always reads a degree too warm is not scored as if it had no skill — compare the two skill columns to see how much of the error is a fixed offset. n QC next to n counts days whose observation carries a QC flag.

VariableInitMethod Windown MAE °F MAE debiased Bias °F RMSE °F ±1 °F±2 °F±3 °F Skill Skill, debiased Period
tmax00Zbilinear30d1 1 QC2.39 [2.39, 2.39]0.00-2.39 [-2.39, -2.39]2.39 [2.39, 2.39]0% [0%, 0%]0%100%+0.40—2026-08-30 → 2026-08-30
tmax00Zbilinear90d1 1 QC2.39 [2.39, 2.39]0.00-2.39 [-2.39, -2.39]2.39 [2.39, 2.39]0% [0%, 0%]0%100%+0.40—2026-08-30 → 2026-08-30
tmax00Zbilinear365d1 1 QC2.39 [2.39, 2.39]0.00-2.39 [-2.39, -2.39]2.39 [2.39, 2.39]0% [0%, 0%]0%100%+0.40—2026-08-30 → 2026-08-30
tmax00Zbilinearall1 1 QC2.39 [2.39, 2.39]0.00-2.39 [-2.39, -2.39]2.39 [2.39, 2.39]0% [0%, 0%]0%100%+0.40—2026-08-30 → 2026-08-30
tmax00Znearest30d1 1 QC2.74 [2.74, 2.74]0.00-2.74 [-2.74, -2.74]2.74 [2.74, 2.74]0% [0%, 0%]0%100%+0.32—2026-08-30 → 2026-08-30
tmax00Znearest90d1 1 QC2.74 [2.74, 2.74]0.00-2.74 [-2.74, -2.74]2.74 [2.74, 2.74]0% [0%, 0%]0%100%+0.32—2026-08-30 → 2026-08-30
tmax00Znearest365d1 1 QC2.74 [2.74, 2.74]0.00-2.74 [-2.74, -2.74]2.74 [2.74, 2.74]0% [0%, 0%]0%100%+0.32—2026-08-30 → 2026-08-30
tmax00Znearestall1 1 QC2.74 [2.74, 2.74]0.00-2.74 [-2.74, -2.74]2.74 [2.74, 2.74]0% [0%, 0%]0%100%+0.32—2026-08-30 → 2026-08-30
tmax12Zbilinear30d2 2 QC1.87 [1.85, 1.89]0.02-1.87 [-1.89, -1.85]1.87 [1.85, 1.89]0% [0%, 0%]100%100%+0.25+0.992026-08-29 → 2026-08-30
tmax12Zbilinear90d2 2 QC1.87 [1.85, 1.89]0.02-1.87 [-1.89, -1.85]1.87 [1.85, 1.89]0% [0%, 0%]100%100%+0.25+0.992026-08-29 → 2026-08-30
tmax12Zbilinear365d2 2 QC1.87 [1.85, 1.89]0.02-1.87 [-1.89, -1.85]1.87 [1.85, 1.89]0% [0%, 0%]100%100%+0.25+0.992026-08-29 → 2026-08-30
tmax12Zbilinearall2 2 QC1.87 [1.85, 1.89]0.02-1.87 [-1.89, -1.85]1.87 [1.85, 1.89]0% [0%, 0%]100%100%+0.25+0.992026-08-29 → 2026-08-30
tmax12Znearest30d2 2 QC2.01 [1.91, 2.12]0.11-2.01 [-2.12, -1.91]2.02 [1.91, 2.12]0% [0%, 0%]50%100%+0.19+0.962026-08-29 → 2026-08-30
tmax12Znearest90d2 2 QC2.01 [1.91, 2.12]0.11-2.01 [-2.12, -1.91]2.02 [1.91, 2.12]0% [0%, 0%]50%100%+0.19+0.962026-08-29 → 2026-08-30
tmax12Znearest365d2 2 QC2.01 [1.91, 2.12]0.11-2.01 [-2.12, -1.91]2.02 [1.91, 2.12]0% [0%, 0%]50%100%+0.19+0.962026-08-29 → 2026-08-30
tmax12Znearestall2 2 QC2.01 [1.91, 2.12]0.11-2.01 [-2.12, -1.91]2.02 [1.91, 2.12]0% [0%, 0%]50%100%+0.19+0.962026-08-29 → 2026-08-30
tmin00Zbilinear30d1 1 QC2.07 [2.07, 2.07]0.00-2.07 [-2.07, -2.07]2.07 [2.07, 2.07]0% [0%, 0%]0%100%-0.04—2026-08-30 → 2026-08-30
tmin00Zbilinear90d1 1 QC2.07 [2.07, 2.07]0.00-2.07 [-2.07, -2.07]2.07 [2.07, 2.07]0% [0%, 0%]0%100%-0.04—2026-08-30 → 2026-08-30
tmin00Zbilinear365d1 1 QC2.07 [2.07, 2.07]0.00-2.07 [-2.07, -2.07]2.07 [2.07, 2.07]0% [0%, 0%]0%100%-0.04—2026-08-30 → 2026-08-30
tmin00Zbilinearall1 1 QC2.07 [2.07, 2.07]0.00-2.07 [-2.07, -2.07]2.07 [2.07, 2.07]0% [0%, 0%]0%100%-0.04—2026-08-30 → 2026-08-30
tmin00Znearest30d1 1 QC2.87 [2.87, 2.87]0.00-2.87 [-2.87, -2.87]2.87 [2.87, 2.87]0% [0%, 0%]0%100%-0.43—2026-08-30 → 2026-08-30
tmin00Znearest90d1 1 QC2.87 [2.87, 2.87]0.00-2.87 [-2.87, -2.87]2.87 [2.87, 2.87]0% [0%, 0%]0%100%-0.43—2026-08-30 → 2026-08-30
tmin00Znearest365d1 1 QC2.87 [2.87, 2.87]0.00-2.87 [-2.87, -2.87]2.87 [2.87, 2.87]0% [0%, 0%]0%100%-0.43—2026-08-30 → 2026-08-30
tmin00Znearestall1 1 QC2.87 [2.87, 2.87]0.00-2.87 [-2.87, -2.87]2.87 [2.87, 2.87]0% [0%, 0%]0%100%-0.43—2026-08-30 → 2026-08-30
tmin12Zbilinear30d2 2 QC1.18 [1.14, 1.21]1.18-0.04 [-1.21, 1.14]1.18 [1.14, 1.21]0% [0%, 0%]100%100%+0.21-1.362026-08-29 → 2026-08-30
tmin12Zbilinear90d2 2 QC1.18 [1.14, 1.21]1.18-0.04 [-1.21, 1.14]1.18 [1.14, 1.21]0% [0%, 0%]100%100%+0.21-1.362026-08-29 → 2026-08-30
tmin12Zbilinear365d2 2 QC1.18 [1.14, 1.21]1.18-0.04 [-1.21, 1.14]1.18 [1.14, 1.21]0% [0%, 0%]100%100%+0.21-1.362026-08-29 → 2026-08-30
tmin12Zbilinearall2 2 QC1.18 [1.14, 1.21]1.18-0.04 [-1.21, 1.14]1.18 [1.14, 1.21]0% [0%, 0%]100%100%+0.21-1.362026-08-29 → 2026-08-30
tmin12Znearest30d2 2 QC1.32 [0.55, 2.08]1.32-0.76 [-2.08, 0.55]1.52 [0.55, 2.08]50% [0%, 100%]50%100%+0.12-1.632026-08-29 → 2026-08-30
tmin12Znearest90d2 2 QC1.32 [0.55, 2.08]1.32-0.76 [-2.08, 0.55]1.52 [0.55, 2.08]50% [0%, 100%]50%100%+0.12-1.632026-08-29 → 2026-08-30
tmin12Znearest365d2 2 QC1.32 [0.55, 2.08]1.32-0.76 [-2.08, 0.55]1.52 [0.55, 2.08]50% [0%, 100%]50%100%+0.12-1.632026-08-29 → 2026-08-30
tmin12Znearestall2 2 QC1.32 [0.55, 2.08]1.32-0.76 [-2.08, 0.55]1.52 [0.55, 2.08]50% [0%, 100%]50%100%+0.12-1.632026-08-29 → 2026-08-30

+ model too warm · − model too cold · bias interval includes zero · ★ lowest MAE · = not distinguishable from the leader · ▼ significantly worse · n < 30 greyed and unranked · CI is a 95 % moving-block bootstrap interval.

Daily error, last 90 days

Daily forecast minus observed error in °F for Pangu-Weather (GFS init) at KLAX, lead day 1, 00Z bilinear tmax+2.5+1.20-1.2-2.52026-08-30: -2.39 °F2026-08-30°F, forecast − observed
Forecast − observed, °F, 00Z bilinear daily maximum. The dashed line is zero; the thick line is a centred 7-day mean, drawn only where the whole window is present. Gaps are days with no score, never interpolation. Hover a point for its date and value.
The same series as a table (1 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-2.39

Error distribution

Distribution of the signed daily error in °F for Pangu-Weather (GFS init) at KLAX, lead day 1-2.5 to -2.25 °F: 1 day-2.25 to -2 °F: 0 days-2 to -1.75 °F: 0 days-1.75 to -1.5 °F: 0 days-1.5 to -1.25 °F: 0 days-1.25 to -1 °F: 0 days-1 to -0.75 °F: 0 days-0.75 to -0.5 °F: 0 days-0.5 to -0.25 °F: 0 days-0.25 to 0 °F: 0 days0 to 0.25 °F: 0 days0.25 to 0.5 °F: 0 days0.5 to 0.75 °F: 0 days0.75 to 1 °F: 0 days1 to 1.25 °F: 0 days1.25 to 1.5 °F: 0 days1.5 to 1.75 °F: 0 days1.75 to 2 °F: 0 days2 to 2.25 °F: 0 days2.25 to 2.5 °F: 0 daysdashed: P50 |e| 2.39 · P90 |e| 2.39 °F-2.50+2.5 °Fn = 1 days
All scored days for 00Z bilinear daily maximum, 20 equal bins. The dashed marks are the 50th and 90th percentiles of the absolute error, mirrored on both sides. Hover a bar for its bin and count.
Bin counts as a table
From °FTo °FDays
-2.50-2.251
-2.25-2.000
-2.00-1.750
-1.75-1.500
-1.50-1.250
-1.25-1.000
-1.00-0.750
-0.75-0.500
-0.50-0.250
-0.25+0.000
+0.00+0.250
+0.25+0.500
+0.50+0.750
+0.75+1.000
+1.00+1.250
+1.25+1.500
+1.50+1.750
+1.75+2.000
+2.00+2.250
+2.25+2.500

Month by month

00Z bilinear daily maximum, newest first.

Monthn MAE °FBias °F
2026-0812.39 -2.39

Availability

ModelScored period DaysCoverage
Pangu-Weather (GFS init)2026-08-30 → 2026-08-30 1
Pangu-Weather (GFS init)2026-08-30 → 2026-08-30 1
Pangu-Weather (GFS init)2026-08-29 → 2026-08-30 2
Pangu-Weather (GFS init)2026-08-29 → 2026-08-30 2

Compared with other models

Paired bootstrap on the days both models cover (90d, 00Z, bilinear, daily maximum). Negative means Pangu-Weather (GFS init) has the lower MAE. "Distinguishable" means the 95 % interval excludes zero.

Other modelCommon days MAE difference °FDistinguishable
ECMWF AIFS Single 1 +1.72 [1.72, 1.72] yes
Aurora (GFS init) 1 -3.55 [-3.55, -3.55] yes
Aurora (IFS init) 1 -2.92 [-2.92, -2.92] yes
FourCastNet v2 (GFS init) 1 -0.36 [-0.36, -0.36] yes
FourCastNet v2 (IFS init) 1 -0.44 [-0.44, -0.44] yes
NCEP GFS 1 -0.32 [-0.32, -0.32] yes
GraphCast (GFS init) 1 -2.86 [-2.86, -2.86] yes
GraphCast (IFS init) 1 -2.58 [-2.58, -2.58] yes
ECMWF IFS HRES 1 -0.17 [-0.17, -0.17] yes
Pangu-Weather (IFS init) 1 -0.88 [-0.88, -0.88] yes
Persistence (baseline) 1 -1.61 [-1.61, -1.61] yes

Cite this page

ShortCastCheck, KLAX pangu_gfs lead 1, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KLAX/model/pangu_gfs/lead/1/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KLAX (Los Angeles Intl), model pangu_gfs, lead day 1. Methodology version 0.2, schema version 0.1, data through 2026-08-30. Accessed 2026-08-31. https://castcheck.zifanzhang.com/station/KLAX/model/pangu_gfs/lead/1/

Accessed2026-08-31 (data through 2026-08-30; page built 2026-08-31T03:52:06+00:00)

JSON CSV all scores methodology v0.2 licence