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 5

KLAX · graphcast_ifs · lead 5

Target day = initialization date + 5 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
tmax00Zbilinear30d25 2 QC3.77 [2.68, 5.02]1.61-3.77 [-5.02, -2.68]4.21 [2.81, 5.36]4% [0%, 12%]8%48%-0.33+0.362026-08-06 → 2026-08-30
tmax00Zbilinear90d25 2 QC3.77 [2.54, 5.33]1.61-3.77 [-5.33, -2.54]4.21 [2.60, 5.57]4% [0%, 12%]8%48%-0.33+0.362026-08-06 → 2026-08-30
tmax00Zbilinear365d31 2 QC3.69 [2.68, 4.96]1.66-3.57 [-4.93, -2.53]4.13 [2.84, 5.30]3% [0%, 10%]13%48%-0.29+0.382026-01-06 → 2026-08-30
tmax00Zbilinearall31 2 QC3.69 [2.73, 4.93]1.66-3.57 [-4.86, -2.55]4.13 [2.89, 5.27]3% [0%, 10%]13%48%-0.29+0.382026-01-06 → 2026-08-30
tmax00Znearest30d25 2 QC7.01 [5.65, 8.40]1.75-7.01 [-8.40, -5.65]7.30 [5.74, 8.63]0% [0%, 0%]0%0%-1.47+0.312026-08-06 → 2026-08-30
tmax00Znearest90d25 2 QC7.01 [5.55, 8.80]1.75-7.01 [-8.80, -5.55]7.30 [5.62, 8.92]0% [0%, 0%]0%0%-1.47+0.312026-08-06 → 2026-08-30
tmax00Znearest365d31 2 QC6.36 [4.68, 8.12]2.09-6.25 [-8.12, -4.41]6.79 [5.03, 8.38]0% [0%, 0%]3%6%-1.21+0.222026-01-06 → 2026-08-30
tmax00Znearestall31 2 QC6.36 [4.61, 8.07]2.09-6.25 [-8.05, -4.32]6.79 [4.95, 8.38]0% [0%, 0%]3%6%-1.21+0.222026-01-06 → 2026-08-30
tmax12Zbilinear30d25 2 QC3.68 [2.71, 4.91]1.51-3.67 [-4.90, -2.71]4.11 [2.92, 5.22]4% [0%, 12%]12%40%-0.30+0.412026-08-06 → 2026-08-30
tmax12Zbilinear90d25 2 QC3.68 [2.58, 5.10]1.51-3.67 [-5.09, -2.58]4.11 [2.69, 5.39]4% [0%, 12%]12%40%-0.30+0.412026-08-06 → 2026-08-30
tmax12Zbilinear365d30 2 QC3.47 [2.51, 4.73]1.62-3.33 [-4.67, -2.19]3.92 [2.71, 5.11]7% [0%, 17%]20%43%-0.32+0.342026-01-06 → 2026-08-30
tmax12Zbilinearall30 2 QC3.47 [2.44, 4.71]1.62-3.33 [-4.65, -2.12]3.92 [2.67, 5.07]7% [0%, 17%]20%43%-0.32+0.342026-01-06 → 2026-08-30
tmax12Znearest30d25 2 QC6.88 [5.60, 8.26]1.72-6.88 [-8.26, -5.60]7.19 [5.75, 8.49]0% [0%, 0%]0%0%-1.42+0.322026-08-06 → 2026-08-30
tmax12Znearest90d25 2 QC6.88 [5.50, 8.63]1.72-6.88 [-8.63, -5.50]7.19 [5.62, 8.79]0% [0%, 0%]0%0%-1.42+0.322026-08-06 → 2026-08-30
tmax12Znearest365d30 2 QC6.15 [4.21, 8.15]2.16-6.07 [-8.15, -3.96]6.68 [4.76, 8.36]3% [0%, 12%]7%10%-1.34+0.132026-01-06 → 2026-08-30
tmax12Znearestall30 2 QC6.15 [4.03, 7.95]2.16-6.07 [-7.95, -3.76]6.68 [4.66, 8.24]3% [0%, 13%]7%10%-1.34+0.132026-01-06 → 2026-08-30
tmin00Zbilinear30d25 2 QC0.97 [0.77, 1.16]0.65-0.70 [-0.99, -0.38]1.09 [0.86, 1.26]64% [47%, 83%]96%100%+0.46+0.602026-08-06 → 2026-08-30
tmin00Zbilinear90d25 2 QC0.97 [0.71, 1.17]0.65-0.70 [-1.01, -0.34]1.09 [0.79, 1.27]64% [47%, 85%]96%100%+0.46+0.602026-08-06 → 2026-08-30
tmin00Zbilinear365d31 2 QC1.95 [0.84, 4.06]2.14+0.60 [-0.90, 3.42]3.37 [0.95, 5.80]55% [30%, 78%]81%87%+0.35+0.332026-01-06 → 2026-08-30
tmin00Zbilinearall31 2 QC1.95 [0.84, 4.56]2.14+0.60 [-0.86, 3.85]3.37 [0.94, 6.21]55% [27%, 76%]81%87%+0.35+0.332026-01-06 → 2026-08-30
tmin00Znearest30d25 2 QC0.64 [0.46, 0.76]0.67+0.24 [-0.09, 0.49]0.85 [0.64, 1.00]76% [65%, 89%]96%100%+0.65+0.592026-08-06 → 2026-08-30
tmin00Znearest90d25 2 QC0.64 [0.43, 0.77]0.67+0.24 [-0.15, 0.50]0.85 [0.51, 0.99]76% [65%, 94%]96%100%+0.65+0.592026-08-06 → 2026-08-30
tmin00Znearest365d31 2 QC2.12 [0.56, 5.29]2.53+1.80 [0.06, 5.17]4.29 [0.75, 7.56]61% [32%, 83%]81%84%+0.29+0.202026-01-06 → 2026-08-30
tmin00Znearestall31 2 QC2.12 [0.56, 5.93]2.53+1.80 [0.10, 5.73]4.29 [0.77, 8.08]61% [28%, 81%]81%84%+0.29+0.202026-01-06 → 2026-08-30
tmin12Zbilinear30d25 2 QC0.95 [0.78, 1.14]0.72-0.68 [-1.02, -0.40]1.09 [0.88, 1.28]52% [33%, 67%]100%100%+0.47+0.562026-08-06 → 2026-08-30
tmin12Zbilinear90d25 2 QC0.95 [0.76, 1.17]0.72-0.68 [-1.07, -0.37]1.09 [0.84, 1.31]52% [30%, 67%]100%100%+0.47+0.562026-08-06 → 2026-08-30
tmin12Zbilinear365d30 2 QC1.75 [0.84, 3.58]1.88+0.39 [-0.93, 2.85]2.93 [0.95, 5.12]43% [15%, 62%]87%90%+0.38+0.362026-01-06 → 2026-08-30
tmin12Zbilinearall30 2 QC1.75 [0.85, 4.09]1.88+0.39 [-0.89, 3.34]2.93 [0.94, 5.58]43% [9%, 62%]87%90%+0.38+0.362026-01-06 → 2026-08-30
tmin12Znearest30d25 2 QC0.67 [0.47, 0.82]0.68+0.30 [-0.14, 0.61]0.91 [0.66, 1.08]76% [65%, 89%]92%100%+0.63+0.582026-08-06 → 2026-08-30
tmin12Znearest90d25 2 QC0.67 [0.41, 0.82]0.68+0.30 [-0.23, 0.62]0.91 [0.57, 1.07]76% [65%, 94%]92%100%+0.63+0.582026-08-06 → 2026-08-30
tmin12Znearest365d30 2 QC1.85 [0.56, 4.61]2.14+1.54 [0.06, 4.37]3.70 [0.77, 6.59]63% [35%, 83%]77%87%+0.35+0.272026-01-06 → 2026-08-30
tmin12Znearestall30 2 QC1.85 [0.58, 5.17]2.14+1.54 [0.06, 4.98]3.70 [0.81, 7.18]63% [31%, 83%]77%87%+0.35+0.272026-01-06 → 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 5, 00Z bilinear tmax+10+50-5-102026-08-06: -2.37 °F2026-08-07: -3.51 °F2026-08-08: -2.23 °F2026-08-09: -2.82 °F2026-08-10: -1.73 °F2026-08-11: -2.59 °F2026-08-12: -2.27 °F2026-08-13: -2.14 °F2026-08-14: -2.84 °F2026-08-15: -2.78 °F2026-08-16: -2.58 °F2026-08-17: -2.09 °F2026-08-18: -4.94 °F2026-08-19: -4.99 °F2026-08-20: -0.01 °F2026-08-21: -5.82 °F2026-08-22: -4.87 °F2026-08-23: -7.14 °F2026-08-24: -3.34 °F2026-08-25: -3.03 °F2026-08-26: -6.05 °F2026-08-27: -7.61 °F2026-08-28: -4.02 °F2026-08-29: -6.66 °F2026-08-30: -5.7 °F2026-08-062026-08-30°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 (25 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-5.70
2026-08-29-6.66
2026-08-28-4.02
2026-08-27-7.61
2026-08-26-6.05
2026-08-25-3.03
2026-08-24-3.34
2026-08-23-7.14
2026-08-22-4.87
2026-08-21-5.82
2026-08-20-0.01
2026-08-19-4.99
2026-08-18-4.94
2026-08-17-2.09
2026-08-16-2.58
2026-08-15-2.78
2026-08-14-2.84
2026-08-13-2.14
2026-08-12-2.27
2026-08-11-2.59
2026-08-10-1.73
2026-08-09-2.82
2026-08-08-2.23
2026-08-07-3.51
2026-08-06-2.37

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KLAX, lead day 5-10 to -9 °F: 0 days-9 to -8 °F: 0 days-8 to -7 °F: 2 days-7 to -6 °F: 3 days-6 to -5 °F: 2 days-5 to -4 °F: 4 days-4 to -3 °F: 5 days-3 to -2 °F: 11 days-2 to -1 °F: 2 days-1 to 0 °F: 1 day0 to 1 °F: 0 days1 to 2 °F: 1 day2 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| 3.03 · P90 |e| 6.66 °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
-9.00-8.000
-8.00-7.002
-7.00-6.003
-6.00-5.002
-5.00-4.004
-4.00-3.005
-3.00-2.0011
-2.00-1.002
-1.00+0.001
+0.00+1.000
+1.00+2.001
+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
2026-08253.77 -3.77
2026-0163.40 -2.74

Availability

ModelScored period DaysCoverage
GraphCast (IFS init)2026-01-06 → 2026-08-30 31
GraphCast (IFS init)2026-01-06 → 2026-08-30 31
GraphCast (IFS init)2026-01-06 → 2026-08-30 30
GraphCast (IFS init)2026-01-06 → 2026-08-30 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 +1.72 [0.63, 3.15] yes
NCEP GFS 25 +2.21 [1.35, 3.14] yes
ECMWF IFS HRES 18 +1.65 [0.40, 3.14] yes
Persistence (baseline) 25 +0.93 [0.48, 1.91] yes

Cite this page

ShortCastCheck, KLAX graphcast_ifs lead 5, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KLAX/model/graphcast_ifs/lead/5/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KLAX (Los Angeles Intl), model graphcast_ifs, lead day 5. 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/5/

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