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 4

KLAX · graphcast_ifs · lead 4

Target day = initialization date + 4 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, 1 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
tmax00Zbilinear30d25 1 QC3.73 [2.80, 4.89]1.50-3.73 [-4.89, -2.80]4.17 [2.99, 5.29]4% [0%, 12%]16%40%-0.53+0.342026-08-05 → 2026-08-29
tmax00Zbilinear90d25 1 QC3.73 [2.67, 5.23]1.50-3.73 [-5.23, -2.67]4.17 [2.76, 5.51]4% [0%, 12%]16%40%-0.53+0.342026-08-05 → 2026-08-29
tmax00Zbilinear365d31 1 QC3.56 [2.68, 4.82]1.52-3.53 [-4.81, -2.62]4.04 [2.91, 5.23]10% [0%, 24%]19%39%-0.58+0.292026-01-05 → 2026-08-29
tmax00Zbilinearall31 1 QC3.56 [2.67, 4.73]1.52-3.53 [-4.72, -2.59]4.04 [2.90, 5.18]10% [0%, 25%]19%39%-0.58+0.292026-01-05 → 2026-08-29
tmax00Znearest30d25 1 QC7.00 [5.74, 8.46]1.78-7.00 [-8.46, -5.74]7.31 [5.86, 8.70]0% [0%, 0%]0%0%-1.87+0.212026-08-05 → 2026-08-29
tmax00Znearest90d25 1 QC7.00 [5.62, 8.78]1.78-7.00 [-8.78, -5.62]7.31 [5.69, 8.97]0% [0%, 0%]0%0%-1.87+0.212026-08-05 → 2026-08-29
tmax00Znearest365d31 1 QC6.25 [4.44, 8.24]2.06-6.21 [-8.24, -4.33]6.76 [4.95, 8.54]6% [0%, 21%]6%6%-1.77+0.042026-01-05 → 2026-08-29
tmax00Znearestall31 1 QC6.25 [4.31, 8.08]2.06-6.21 [-8.08, -4.15]6.76 [4.79, 8.38]6% [0%, 24%]6%6%-1.77+0.042026-01-05 → 2026-08-29
tmax12Zbilinear30d25 1 QC3.72 [2.90, 4.86]1.40-3.72 [-4.86, -2.90]4.13 [3.10, 5.24]4% [0%, 12%]12%36%-0.52+0.382026-08-05 → 2026-08-29
tmax12Zbilinear90d25 1 QC3.72 [2.76, 5.07]1.40-3.72 [-5.07, -2.76]4.13 [2.85, 5.38]4% [0%, 12%]12%36%-0.52+0.382026-08-05 → 2026-08-29
tmax12Zbilinear365d30 1 QC3.40 [2.36, 4.72]1.45-3.36 [-4.72, -2.25]3.88 [2.70, 5.08]10% [0%, 26%]20%40%-0.57+0.302026-01-05 → 2026-08-29
tmax12Zbilinearall30 1 QC3.40 [2.26, 4.62]1.45-3.36 [-4.62, -2.16]3.88 [2.65, 5.07]10% [0%, 29%]20%40%-0.57+0.302026-01-05 → 2026-08-29
tmax12Znearest30d25 1 QC6.94 [5.74, 8.37]1.70-6.94 [-8.37, -5.74]7.24 [5.85, 8.62]0% [0%, 0%]0%0%-1.85+0.252026-08-05 → 2026-08-29
tmax12Znearest90d25 1 QC6.94 [5.62, 8.82]1.70-6.94 [-8.82, -5.62]7.24 [5.69, 8.95]0% [0%, 0%]0%0%-1.85+0.252026-08-05 → 2026-08-29
tmax12Znearest365d30 1 QC6.15 [4.13, 8.12]2.11-6.10 [-8.12, -3.97]6.69 [4.75, 8.41]7% [0%, 24%]7%10%-1.84-0.022026-01-05 → 2026-08-29
tmax12Znearestall30 1 QC6.15 [3.98, 8.05]2.11-6.10 [-8.05, -3.77]6.69 [4.63, 8.40]7% [0%, 26%]7%10%-1.84-0.022026-01-05 → 2026-08-29
tmin00Zbilinear30d25 1 QC0.87 [0.66, 1.11]0.54-0.77 [-1.04, -0.55]1.04 [0.78, 1.27]64% [43%, 82%]96%100%+0.44+0.602026-08-05 → 2026-08-29
tmin00Zbilinear90d25 1 QC0.87 [0.63, 1.12]0.54-0.77 [-1.06, -0.53]1.04 [0.73, 1.29]64% [42%, 84%]96%100%+0.44+0.602026-08-05 → 2026-08-29
tmin00Zbilinear365d31 1 QC1.54 [0.74, 3.10]1.64+0.20 [-0.94, 2.30]2.59 [0.88, 4.48]55% [31%, 77%]84%90%+0.39+0.402026-01-05 → 2026-08-29
tmin00Zbilinearall31 1 QC1.54 [0.73, 3.24]1.64+0.20 [-0.91, 2.64]2.59 [0.89, 4.63]55% [30%, 76%]84%90%+0.39+0.402026-01-05 → 2026-08-29
tmin00Znearest30d25 1 QC0.51 [0.34, 0.67]0.50+0.22 [0.03, 0.41]0.70 [0.46, 0.89]84% [74%, 95%]100%100%+0.67+0.632026-08-05 → 2026-08-29
tmin00Znearest90d25 1 QC0.51 [0.31, 0.68]0.50+0.22 [0.02, 0.41]0.70 [0.41, 0.90]84% [73%, 100%]100%100%+0.67+0.632026-08-05 → 2026-08-29
tmin00Znearest365d31 1 QC1.58 [0.40, 3.93]1.88+1.35 [0.12, 3.80]3.20 [0.54, 5.74]68% [33%, 90%]84%87%+0.38+0.322026-01-05 → 2026-08-29
tmin00Znearestall31 1 QC1.58 [0.43, 4.23]1.88+1.35 [0.13, 4.15]3.20 [0.57, 5.93]68% [31%, 89%]84%87%+0.38+0.322026-01-05 → 2026-08-29
tmin12Zbilinear30d25 1 QC0.87 [0.66, 1.12]0.56-0.72 [-1.00, -0.47]1.05 [0.80, 1.28]72% [50%, 89%]96%100%+0.44+0.592026-08-05 → 2026-08-29
tmin12Zbilinear90d25 1 QC0.87 [0.64, 1.14]0.56-0.72 [-1.04, -0.45]1.05 [0.75, 1.30]72% [50%, 90%]96%100%+0.44+0.592026-08-05 → 2026-08-29
tmin12Zbilinear365d30 1 QC1.40 [0.73, 2.70]1.44+0.08 [-0.91, 1.93]2.31 [0.90, 4.02]63% [36%, 85%]87%90%+0.38+0.382026-01-05 → 2026-08-29
tmin12Zbilinearall30 1 QC1.40 [0.73, 2.93]1.44+0.08 [-0.91, 2.28]2.31 [0.88, 4.20]63% [36%, 86%]87%90%+0.38+0.382026-01-05 → 2026-08-29
tmin12Znearest30d25 1 QC0.57 [0.41, 0.75]0.52+0.28 [0.01, 0.52]0.77 [0.57, 0.94]84% [74%, 95%]100%100%+0.64+0.622026-08-05 → 2026-08-29
tmin12Znearest90d25 1 QC0.57 [0.40, 0.78]0.52+0.28 [-0.03, 0.52]0.77 [0.54, 0.95]84% [73%, 100%]100%100%+0.64+0.622026-08-05 → 2026-08-29
tmin12Znearest365d30 1 QC1.42 [0.46, 3.45]1.59+1.18 [0.13, 3.34]2.80 [0.65, 5.08]70% [38%, 90%]87%90%+0.37+0.322026-01-05 → 2026-08-29
tmin12Znearestall30 1 QC1.42 [0.46, 3.76]1.59+1.18 [0.13, 3.61]2.80 [0.65, 5.29]70% [35%, 90%]87%90%+0.37+0.322026-01-05 → 2026-08-29

+ 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 4, 00Z bilinear tmax+10+50-5-102026-08-05: -2.43 °F2026-08-06: -2.25 °F2026-08-07: -3.93 °F2026-08-08: -2.27 °F2026-08-09: -2.78 °F2026-08-10: -1.7 °F2026-08-11: -3.31 °F2026-08-12: -2.67 °F2026-08-13: -2 °F2026-08-14: -3.77 °F2026-08-15: -3.06 °F2026-08-16: -1.61 °F2026-08-17: -1.78 °F2026-08-18: -5.83 °F2026-08-19: -4.99 °F2026-08-20: -0.73 °F2026-08-21: -6.28 °F2026-08-22: -4.18 °F2026-08-23: -5.2 °F2026-08-24: -3.43 °F2026-08-25: -4.06 °F2026-08-26: -5.88 °F2026-08-27: -8.35 °F2026-08-28: -3.49 °F2026-08-29: -7.26 °F2026-08-052026-08-29°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 (25 days, newest first) · download CSV
Climatological dayError °F
2026-08-29-7.26
2026-08-28-3.49
2026-08-27-8.35
2026-08-26-5.88
2026-08-25-4.06
2026-08-24-3.43
2026-08-23-5.20
2026-08-22-4.18
2026-08-21-6.28
2026-08-20-0.73
2026-08-19-4.99
2026-08-18-5.83
2026-08-17-1.78
2026-08-16-1.61
2026-08-15-3.06
2026-08-14-3.77
2026-08-13-2.00
2026-08-12-2.67
2026-08-11-3.31
2026-08-10-1.70
2026-08-09-2.78
2026-08-08-2.27
2026-08-07-3.93
2026-08-06-2.25
2026-08-05-2.43

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KLAX, lead day 4-10 to -9 °F: 0 days-9 to -8 °F: 1 day-8 to -7 °F: 1 day-7 to -6 °F: 1 day-6 to -5 °F: 3 days-5 to -4 °F: 5 days-4 to -3 °F: 8 days-3 to -2 °F: 6 days-2 to -1 °F: 3 days-1 to 0 °F: 1 day0 to 1 °F: 2 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| 3.49 · P90 |e| 5.88 °F-100+10 °Fn = 31 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
-9.00-8.001
-8.00-7.001
-7.00-6.001
-6.00-5.003
-5.00-4.005
-4.00-3.008
-3.00-2.006
-2.00-1.003
-1.00+0.001
+0.00+1.002
+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
2026-08253.73 -3.73
2026-0162.87 -2.68

Availability

ModelScored period DaysCoverage
GraphCast (IFS init)2026-01-05 → 2026-08-29 31
GraphCast (IFS init)2026-01-05 → 2026-08-29 31
GraphCast (IFS init)2026-01-05 → 2026-08-29 30
GraphCast (IFS init)2026-01-05 → 2026-08-29 30

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 25 +2.13 [1.04, 3.72] yes
NCEP GFS 25 +1.60 [1.00, 2.26] yes
ECMWF IFS HRES 19 +2.16 [1.17, 3.67] yes
Persistence (baseline) 25 +1.29 [0.82, 1.99] yes

Cite this page

ShortCastCheck, KLAX graphcast_ifs lead 4, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KLAX/model/graphcast_ifs/lead/4/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KLAX (Los Angeles Intl), model graphcast_ifs, lead day 4. 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/4/

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