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 · GraphCast (IFS init) · lead day 1

KLAX · graphcast_ifs · 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, GRAP_v100, starting 2026-01-01 — 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
tmax00Zbilinear30d27 2 QC3.59 [3.12, 4.20]1.16-3.59 [-4.20, -3.12]3.86 [3.27, 4.46]4% [0%, 11%]7%37%-1.20+0.292026-08-02 → 2026-08-30
tmax00Zbilinear90d27 2 QC3.59 [2.99, 4.45]1.16-3.59 [-4.45, -2.99]3.86 [3.06, 4.74]4% [0%, 11%]7%37%-1.20+0.292026-08-02 → 2026-08-30
tmax00Zbilinear365d33 2 QC3.39 [2.81, 4.14]1.12-3.39 [-4.14, -2.81]3.68 [2.96, 4.46]3% [0%, 9%]12%45%-1.33+0.242026-01-02 → 2026-08-30
tmax00Zbilinearall33 2 QC3.39 [2.87, 4.10]1.12-3.39 [-4.10, -2.87]3.68 [3.00, 4.41]3% [0%, 10%]12%45%-1.33+0.242026-01-02 → 2026-08-30
tmax00Znearest30d27 2 QC6.79 [5.97, 7.80]1.44-6.79 [-7.80, -5.97]7.00 [6.06, 7.97]0% [0%, 0%]0%0%-3.17+0.132026-08-02 → 2026-08-30
tmax00Znearest90d27 2 QC6.79 [5.84, 8.07]1.44-6.79 [-8.07, -5.84]7.00 [5.88, 8.27]0% [0%, 0%]0%0%-3.17+0.132026-08-02 → 2026-08-30
tmax00Znearest365d33 2 QC6.10 [4.52, 7.50]1.70-6.10 [-7.50, -4.52]6.47 [4.92, 7.77]0% [0%, 0%]3%6%-3.19-0.162026-01-02 → 2026-08-30
tmax00Znearestall33 2 QC6.10 [4.64, 7.52]1.70-6.10 [-7.52, -4.64]6.47 [5.05, 7.74]0% [0%, 0%]3%6%-3.19-0.162026-01-02 → 2026-08-30
tmax12Zbilinear30d27 2 QC3.52 [3.05, 4.18]1.16-3.52 [-4.18, -3.05]3.80 [3.25, 4.46]4% [0%, 11%]15%33%-1.16+0.292026-08-02 → 2026-08-30
tmax12Zbilinear90d27 2 QC3.52 [3.00, 4.36]1.16-3.52 [-4.36, -3.00]3.80 [3.12, 4.66]4% [0%, 11%]15%33%-1.16+0.292026-08-02 → 2026-08-30
tmax12Zbilinear365d32 2 QC3.42 [2.94, 4.19]1.09-3.42 [-4.19, -2.94]3.69 [3.10, 4.49]3% [0%, 9%]19%34%-1.33+0.272026-01-02 → 2026-08-30
tmax12Zbilinearall32 2 QC3.42 [2.95, 4.19]1.09-3.42 [-4.19, -2.95]3.69 [3.10, 4.47]3% [0%, 10%]19%34%-1.33+0.272026-01-02 → 2026-08-30
tmax12Znearest30d27 2 QC6.74 [5.98, 7.75]1.43-6.74 [-7.75, -5.98]6.95 [6.06, 7.94]0% [0%, 0%]0%0%-3.14+0.132026-08-02 → 2026-08-30
tmax12Znearest90d27 2 QC6.74 [5.87, 8.03]1.43-6.74 [-8.03, -5.87]6.95 [5.90, 8.23]0% [0%, 0%]0%0%-3.14+0.132026-08-02 → 2026-08-30
tmax12Znearest365d32 2 QC6.22 [4.88, 7.54]1.59-6.22 [-7.54, -4.88]6.53 [5.16, 7.80]0% [0%, 0%]0%6%-3.24-0.072026-01-02 → 2026-08-30
tmax12Znearestall32 2 QC6.22 [5.03, 7.49]1.59-6.22 [-7.49, -5.03]6.53 [5.31, 7.75]0% [0%, 0%]0%6%-3.24-0.072026-01-02 → 2026-08-30
tmin00Zbilinear30d27 2 QC0.90 [0.71, 1.10]0.69-0.70 [-1.02, -0.38]1.07 [0.84, 1.27]67% [50%, 85%]96%100%-0.10+0.182026-08-02 → 2026-08-30
tmin00Zbilinear90d27 2 QC0.90 [0.71, 1.12]0.69-0.70 [-1.06, -0.31]1.07 [0.83, 1.27]67% [50%, 86%]96%100%-0.10+0.182026-08-02 → 2026-08-30
tmin00Zbilinear365d33 2 QC1.16 [0.81, 1.73]1.12-0.15 [-0.89, 1.00]1.46 [0.95, 2.04]58% [34%, 77%]88%91%-0.13-0.052026-01-02 → 2026-08-30
tmin00Zbilinearall33 2 QC1.16 [0.78, 1.67]1.12-0.15 [-0.89, 0.99]1.46 [0.94, 2.00]58% [36%, 79%]88%91%-0.13-0.052026-01-02 → 2026-08-30
tmin00Znearest30d27 2 QC0.69 [0.48, 0.90]0.64+0.24 [-0.04, 0.56]0.85 [0.60, 1.06]78% [67%, 89%]96%100%+0.15+0.232026-08-02 → 2026-08-30
tmin00Znearest90d27 2 QC0.69 [0.48, 0.96]0.64+0.24 [-0.12, 0.68]0.85 [0.59, 1.12]78% [62%, 92%]96%100%+0.15+0.232026-08-02 → 2026-08-30
tmin00Znearest365d33 2 QC1.11 [0.60, 1.98]1.05+0.74 [0.05, 1.80]1.54 [0.74, 2.39]64% [33%, 86%]82%91%-0.07+0.012026-01-02 → 2026-08-30
tmin00Znearestall33 2 QC1.11 [0.56, 1.97]1.05+0.74 [0.03, 1.79]1.54 [0.70, 2.39]64% [31%, 86%]82%91%-0.07+0.012026-01-02 → 2026-08-30
tmin12Zbilinear30d27 2 QC0.72 [0.55, 0.87]0.61-0.49 [-0.74, -0.21]0.89 [0.70, 1.01]70% [60%, 84%]100%100%+0.12+0.272026-08-02 → 2026-08-30
tmin12Zbilinear90d27 2 QC0.72 [0.51, 0.87]0.61-0.49 [-0.73, -0.18]0.89 [0.68, 1.00]70% [60%, 86%]100%100%+0.12+0.272026-08-02 → 2026-08-30
tmin12Zbilinear365d32 2 QC0.90 [0.62, 1.37]0.89-0.12 [-0.64, 0.77]1.15 [0.80, 1.60]62% [43%, 78%]94%100%+0.10+0.132026-01-02 → 2026-08-30
tmin12Zbilinearall32 2 QC0.90 [0.60, 1.28]0.89-0.12 [-0.68, 0.77]1.15 [0.79, 1.57]62% [45%, 78%]94%100%+0.10+0.132026-01-02 → 2026-08-30
tmin12Znearest30d27 2 QC0.72 [0.53, 0.93]0.63+0.37 [0.07, 0.72]0.88 [0.65, 1.11]74% [61%, 88%]96%100%+0.12+0.242026-08-02 → 2026-08-30
tmin12Znearest90d27 2 QC0.72 [0.49, 0.92]0.63+0.37 [-0.01, 0.78]0.88 [0.62, 1.10]74% [60%, 90%]96%100%+0.12+0.242026-08-02 → 2026-08-30
tmin12Znearest365d32 2 QC0.97 [0.60, 1.58]0.82+0.68 [0.15, 1.45]1.27 [0.75, 1.86]62% [33%, 83%]84%97%+0.03+0.202026-01-02 → 2026-08-30
tmin12Znearestall32 2 QC0.97 [0.58, 1.57]0.82+0.68 [0.12, 1.41]1.27 [0.72, 1.86]62% [33%, 86%]84%97%+0.03+0.202026-01-02 → 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 GraphCast (IFS init) at KLAX, lead day 1, 00Z bilinear tmax+10+50-5-102026-08-02: -2.62 °F2026-08-03: -2.46 °F2026-08-04: -3.94 °F2026-08-05: -3.3 °F2026-08-06: -3.03 °F2026-08-07: -2.95 °F2026-08-08: -1.35 °F2026-08-09: -3.43 °F2026-08-10: -2.79 °F2026-08-11: -3.6 °F2026-08-12: -3.12 °F2026-08-13: -2.71 °F2026-08-14: -4.38 °F2026-08-15: -3.23 °F2026-08-16: -2.28 °F2026-08-17: -2.36 °F2026-08-18: -6.36 °F2026-08-19: -5.9 °F2026-08-20: -0.98 °F2026-08-21: -4.87 °F2026-08-22: -2.1 °F2026-08-23: -5.01 °F2026-08-24: -3.08 °F2026-08-25: -4.58 °F2026-08-26: -4.78 °F2026-08-29: -6.8 °F2026-08-30: -4.98 °F2026-08-022026-08-30°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 (29 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-4.98
2026-08-29-6.80
2026-08-28—
2026-08-27—
2026-08-26-4.78
2026-08-25-4.58
2026-08-24-3.08
2026-08-23-5.01
2026-08-22-2.10
2026-08-21-4.87
2026-08-20-0.98
2026-08-19-5.90
2026-08-18-6.36
2026-08-17-2.36
2026-08-16-2.28
2026-08-15-3.23
2026-08-14-4.38
2026-08-13-2.71
2026-08-12-3.12
2026-08-11-3.60
2026-08-10-2.79
2026-08-09-3.43
2026-08-08-1.35
2026-08-07-2.95
2026-08-06-3.03
2026-08-05-3.30
2026-08-04-3.94
2026-08-03-2.46
2026-08-02-2.62

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KLAX, lead day 1-10 to -9 °F: 0 days-9 to -8 °F: 0 days-8 to -7 °F: 0 days-7 to -6 °F: 2 days-6 to -5 °F: 2 days-5 to -4 °F: 6 days-4 to -3 °F: 8 days-3 to -2 °F: 11 days-2 to -1 °F: 3 days-1 to 0 °F: 1 day0 to 1 °F: 0 days1 to 2 °F: 0 days2 to 3 °F: 0 days3 to 4 °F: 0 days4 to 5 °F: 0 days5 to 6 °F: 0 days6 to 7 °F: 0 days7 to 8 °F: 0 days8 to 9 °F: 0 days9 to 10 °F: 0 daysdashed: P50 |e| 3.08 · P90 |e| 5 °F-100+10 °Fn = 33 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
-10.00-9.000
-9.00-8.000
-8.00-7.000
-7.00-6.002
-6.00-5.002
-5.00-4.006
-4.00-3.008
-3.00-2.0011
-2.00-1.003
-1.00+0.001
+0.00+1.000
+1.00+2.000
+2.00+3.000
+3.00+4.000
+4.00+5.000
+5.00+6.000
+6.00+7.000
+7.00+8.000
+8.00+9.000
+9.00+10.000

Month by month

00Z bilinear daily maximum, newest first.

Monthn MAE °FBias °F
2026-08273.59 -3.59
2026-0162.51 -2.51

Availability

ModelScored period DaysCoverage
GraphCast (IFS init)2026-01-02 → 2026-08-30 33
GraphCast (IFS init)2026-01-02 → 2026-08-30 33
GraphCast (IFS init)2026-01-02 → 2026-08-30 32
GraphCast (IFS init)2026-01-02 → 2026-08-30 32

Compared with other models

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

Other modelCommon days MAE difference °FDistinguishable
ECMWF AIFS Single 27 +2.03 [1.55, 2.77] yes
Aurora (GFS init) 1 -0.97 [-0.97, -0.97] yes
Aurora (IFS init) 2 -0.01 [-0.34, 0.31] no
FourCastNet v2 (GFS init) 1 +2.22 [2.22, 2.22] yes
FourCastNet v2 (IFS init) 2 +2.81 [2.14, 3.47] yes
NCEP GFS 27 +1.65 [1.00, 2.52] yes
GraphCast (GFS init) 1 -0.28 [-0.28, -0.28] yes
ECMWF IFS HRES 20 +1.39 [0.94, 2.06] yes
Pangu-Weather (GFS init) 1 +2.58 [2.58, 2.58] yes
Pangu-Weather (IFS init) 2 +2.61 [1.70, 3.52] yes
Persistence (baseline) 27 +1.96 [1.42, 2.68] yes

Cite this page

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

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KLAX (Los Angeles Intl), model graphcast_ifs, 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/graphcast_ifs/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