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 7

KLAX · graphcast_ifs · lead 7

Target day = initialization date + 7 days. 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
tmax00Zbilinear30d23 2 QC4.49 [2.68, 6.24]2.30-4.39 [-6.15, -2.66]5.17 [3.00, 6.67]0% [0%, 0%]22%39%-0.36+0.232026-08-08 → 2026-08-30
tmax00Zbilinear90d23 2 QC4.49 [2.48, 6.35]2.30-4.39 [-6.25, -2.48]5.17 [2.65, 6.74]0% [0%, 0%]22%39%-0.36+0.232026-08-08 → 2026-08-30
tmax00Zbilinear365d29 2 QC4.11 [2.41, 5.90]2.52-3.93 [-5.81, -2.15]4.95 [2.83, 6.49]7% [0%, 21%]31%45%+0.01+0.332026-01-08 → 2026-08-30
tmax00Zbilinearall29 2 QC4.11 [2.49, 5.94]2.52-3.93 [-5.85, -2.20]4.95 [3.06, 6.56]7% [0%, 24%]31%45%+0.01+0.332026-01-08 → 2026-08-30
tmax00Znearest30d23 2 QC7.24 [5.23, 9.23]2.46-7.24 [-9.23, -5.23]7.78 [5.46, 9.58]0% [0%, 0%]4%4%-1.19+0.182026-08-08 → 2026-08-30
tmax00Znearest90d23 2 QC7.24 [5.02, 9.43]2.46-7.24 [-9.43, -5.02]7.78 [5.11, 9.69]0% [0%, 0%]4%4%-1.19+0.182026-08-08 → 2026-08-30
tmax00Znearest365d29 2 QC6.31 [3.82, 8.57]2.96-6.23 [-8.57, -3.65]7.18 [4.66, 9.11]7% [0%, 21%]17%17%-0.52+0.222026-01-08 → 2026-08-30
tmax00Znearestall29 2 QC6.31 [3.67, 8.67]2.96-6.23 [-8.67, -3.43]7.18 [4.72, 9.24]7% [0%, 24%]17%17%-0.52+0.222026-01-08 → 2026-08-30
tmax12Zbilinear30d23 2 QC3.88 [2.30, 5.33]1.97-3.88 [-5.33, -2.30]4.51 [2.67, 5.72]9% [0%, 15%]26%39%-0.18+0.342026-08-08 → 2026-08-30
tmax12Zbilinear90d23 2 QC3.88 [2.14, 5.39]1.97-3.88 [-5.39, -2.14]4.51 [2.32, 5.83]9% [0%, 15%]26%39%-0.18+0.342026-08-08 → 2026-08-30
tmax12Zbilinear365d28 2 QC3.52 [2.00, 4.95]2.02-3.42 [-4.95, -1.80]4.20 [2.28, 5.48]11% [0%, 20%]36%46%+0.07+0.422026-01-08 → 2026-08-30
tmax12Zbilinearall28 2 QC3.52 [1.96, 5.10]2.02-3.42 [-5.06, -1.73]4.20 [2.23, 5.54]11% [0%, 20%]36%46%+0.07+0.422026-01-08 → 2026-08-30
tmax12Znearest30d23 2 QC6.92 [5.09, 8.69]2.11-6.92 [-8.69, -5.09]7.35 [5.28, 8.88]0% [0%, 0%]0%4%-1.09+0.292026-08-08 → 2026-08-30
tmax12Znearest90d23 2 QC6.92 [4.93, 8.83]2.11-6.92 [-8.83, -4.93]7.35 [5.04, 9.01]0% [0%, 0%]0%4%-1.09+0.292026-08-08 → 2026-08-30
tmax12Znearest365d28 2 QC6.01 [3.60, 8.10]2.65-5.93 [-8.10, -3.31]6.72 [4.15, 8.47]0% [0%, 0%]14%18%-0.59+0.242026-01-08 → 2026-08-30
tmax12Znearestall28 2 QC6.01 [3.25, 8.18]2.65-5.93 [-8.17, -2.90]6.72 [3.78, 8.59]0% [0%, 0%]14%18%-0.59+0.242026-01-08 → 2026-08-30
tmin00Zbilinear30d23 2 QC1.29 [0.70, 1.89]1.19-0.70 [-1.60, 0.15]1.66 [0.88, 2.24]57% [28%, 88%]78%91%+0.42+0.372026-08-08 → 2026-08-30
tmin00Zbilinear90d23 2 QC1.29 [0.62, 1.97]1.19-0.70 [-1.67, 0.23]1.66 [0.76, 2.28]57% [26%, 96%]78%91%+0.42+0.372026-08-08 → 2026-08-30
tmin00Zbilinear365d29 2 QC3.13 [0.86, 6.91]3.65+1.56 [-1.11, 6.25]4.99 [1.08, 8.39]45% [12%, 78%]62%72%+0.16+0.072026-01-08 → 2026-08-30
tmin00Zbilinearall29 2 QC3.13 [0.90, 7.65]3.65+1.56 [-1.20, 7.08]4.99 [1.20, 8.85]45% [11%, 77%]62%72%+0.16+0.072026-01-08 → 2026-08-30
tmin00Znearest30d23 2 QC1.09 [0.78, 1.30]1.05+0.29 [-0.50, 0.94]1.40 [1.03, 1.62]52% [38%, 71%]83%96%+0.51+0.442026-08-08 → 2026-08-30
tmin00Znearest90d23 2 QC1.09 [0.68, 1.32]1.05+0.29 [-0.60, 0.99]1.40 [0.92, 1.63]52% [37%, 75%]83%96%+0.51+0.442026-08-08 → 2026-08-30
tmin00Znearest365d29 2 QC3.63 [0.93, 8.82]4.32+3.00 [-0.08, 8.59]6.33 [1.20, 10.90]41% [19%, 64%]66%76%+0.02-0.102026-01-08 → 2026-08-30
tmin00Znearestall29 2 QC3.63 [0.97, 9.67]4.32+3.00 [-0.15, 9.53]6.33 [1.26, 11.44]41% [14%, 61%]66%76%+0.02-0.102026-01-08 → 2026-08-30
tmin12Zbilinear30d23 2 QC1.12 [0.79, 1.42]1.03-0.45 [-1.23, 0.31]1.35 [0.98, 1.68]48% [33%, 67%]91%96%+0.49+0.452026-08-08 → 2026-08-30
tmin12Zbilinear90d23 2 QC1.12 [0.71, 1.45]1.03-0.45 [-1.32, 0.38]1.35 [0.90, 1.72]48% [31%, 71%]91%96%+0.49+0.452026-08-08 → 2026-08-30
tmin12Zbilinear365d28 2 QC2.63 [0.91, 6.10]3.00+1.34 [-0.91, 5.44]4.33 [1.07, 7.64]39% [18%, 62%]75%79%+0.28+0.222026-01-08 → 2026-08-30
tmin12Zbilinearall28 2 QC2.63 [0.94, 6.82]3.00+1.34 [-0.97, 6.06]4.33 [1.12, 8.14]39% [14%, 59%]75%79%+0.28+0.222026-01-08 → 2026-08-30
tmin12Znearest30d23 2 QC0.97 [0.70, 1.25]0.93+0.56 [-0.11, 1.14]1.28 [0.98, 1.53]65% [45%, 83%]87%100%+0.56+0.512026-08-08 → 2026-08-30
tmin12Znearest90d23 2 QC0.97 [0.64, 1.27]0.93+0.56 [-0.19, 1.16]1.28 [0.92, 1.55]65% [44%, 86%]87%100%+0.56+0.512026-08-08 → 2026-08-30
tmin12Znearest365d28 2 QC3.06 [0.80, 7.79]3.56+2.72 [0.17, 7.67]5.63 [1.10, 10.10]54% [25%, 78%]71%82%+0.16+0.072026-01-08 → 2026-08-30
tmin12Znearestall28 2 QC3.06 [0.80, 8.82]3.56+2.72 [0.17, 8.50]5.63 [1.10, 10.68]54% [20%, 79%]71%82%+0.16+0.072026-01-08 → 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 7, 00Z bilinear tmax+10+50-5-102026-08-08: -3.97 °F2026-08-09: -2.84 °F2026-08-10: -1.25 °F2026-08-11: -2.32 °F2026-08-12: -1.57 °F2026-08-13: -2.03 °F2026-08-14: -3.48 °F2026-08-15: -2.58 °F2026-08-16: -1.7 °F2026-08-17: -1.92 °F2026-08-18: -6.89 °F2026-08-19: -7.14 °F2026-08-20: +1.09 °F2026-08-21: -6.09 °F2026-08-22: -5.7 °F2026-08-23: -9.17 °F2026-08-24: -8.62 °F2026-08-25: -6.33 °F2026-08-26: -6.55 °F2026-08-27: -9.55 °F2026-08-28: -4.09 °F2026-08-29: -4.13 °F2026-08-30: -4.22 °F2026-08-082026-08-30°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 (23 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-4.22
2026-08-29-4.13
2026-08-28-4.09
2026-08-27-9.55
2026-08-26-6.55
2026-08-25-6.33
2026-08-24-8.62
2026-08-23-9.17
2026-08-22-5.70
2026-08-21-6.09
2026-08-20+1.09
2026-08-19-7.14
2026-08-18-6.89
2026-08-17-1.92
2026-08-16-1.70
2026-08-15-2.58
2026-08-14-3.48
2026-08-13-2.03
2026-08-12-1.57
2026-08-11-2.32
2026-08-10-1.25
2026-08-09-2.84
2026-08-08-3.97

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KLAX, lead day 7-10 to -9 °F: 2 days-9 to -8 °F: 2 days-8 to -7 °F: 1 day-7 to -6 °F: 4 days-6 to -5 °F: 1 day-5 to -4 °F: 4 days-4 to -3 °F: 2 days-3 to -2 °F: 4 days-2 to -1 °F: 5 days-1 to 0 °F: 2 days0 to 1 °F: 0 days1 to 2 °F: 2 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| 3.97 · P90 |e| 8.45 °F-100+10 °Fn = 29 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
-10.00-9.002
-9.00-8.002
-8.00-7.001
-7.00-6.004
-6.00-5.001
-5.00-4.004
-4.00-3.002
-3.00-2.004
-2.00-1.005
-1.00+0.002
+0.00+1.000
+1.00+2.002
+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
2026-08234.49 -4.39
2026-0162.66 -2.13

Availability

ModelScored period DaysCoverage
GraphCast (IFS init)2026-01-08 → 2026-08-30 29
GraphCast (IFS init)2026-01-08 → 2026-08-30 29
GraphCast (IFS init)2026-01-08 → 2026-08-30 28
GraphCast (IFS init)2026-01-08 → 2026-08-30 28

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 23 +2.46 [1.16, 3.86] yes
NCEP GFS 23 +2.51 [1.57, 3.51] yes
ECMWF IFS HRES 18 +2.12 [0.82, 3.85] yes
Persistence (baseline) 23 +1.18 [0.55, 1.82] yes

Cite this page

ShortCastCheck, KLAX graphcast_ifs lead 7, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KLAX/model/graphcast_ifs/lead/7/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KLAX (Los Angeles Intl), model graphcast_ifs, lead day 7. 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/7/

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