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 2

KLAX · graphcast_ifs · lead 2

Target day = initialization date + 2 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
tmax00Zbilinear30d26 1 QC3.71 [3.10, 4.55]1.24-3.71 [-4.55, -3.10]4.05 [3.19, 5.07]0% [0%, 0%]4%38%-0.97+0.372026-08-03 → 2026-08-30
tmax00Zbilinear90d26 1 QC3.71 [2.95, 4.81]1.24-3.71 [-4.81, -2.95]4.05 [2.99, 5.31]0% [0%, 0%]4%38%-0.97+0.372026-08-03 → 2026-08-30
tmax00Zbilinear365d32 1 QC3.48 [2.79, 4.35]1.20-3.48 [-4.35, -2.79]3.83 [2.89, 4.85]0% [0%, 0%]9%47%-0.95+0.352026-01-03 → 2026-08-30
tmax00Zbilinearall32 1 QC3.48 [2.77, 4.36]1.20-3.48 [-4.36, -2.77]3.83 [2.91, 4.86]0% [0%, 0%]9%47%-0.95+0.352026-01-03 → 2026-08-30
tmax00Znearest30d26 1 QC6.88 [5.89, 8.11]1.53-6.88 [-8.11, -5.89]7.13 [5.95, 8.39]0% [0%, 0%]0%0%-2.65+0.232026-08-03 → 2026-08-30
tmax00Znearest90d26 1 QC6.88 [5.77, 8.43]1.53-6.88 [-8.43, -5.77]7.13 [5.82, 8.63]0% [0%, 0%]0%0%-2.65+0.232026-08-03 → 2026-08-30
tmax00Znearest365d32 1 QC6.13 [4.40, 7.70]1.80-6.13 [-7.70, -4.40]6.56 [4.84, 8.04]0% [0%, 0%]6%12%-2.44+0.032026-01-03 → 2026-08-30
tmax00Znearestall32 1 QC6.13 [4.33, 7.76]1.80-6.13 [-7.76, -4.33]6.56 [4.75, 8.01]0% [0%, 0%]6%12%-2.44+0.032026-01-03 → 2026-08-30
tmax12Zbilinear30d26 1 QC3.62 [3.06, 4.54]1.28-3.62 [-4.54, -3.06]4.01 [3.23, 5.04]4% [0%, 11%]12%42%-0.92+0.352026-08-03 → 2026-08-30
tmax12Zbilinear90d26 1 QC3.62 [2.98, 4.70]1.28-3.62 [-4.70, -2.98]4.01 [3.07, 5.22]4% [0%, 12%]12%42%-0.92+0.352026-08-03 → 2026-08-30
tmax12Zbilinear365d31 1 QC3.48 [2.92, 4.36]1.21-3.48 [-4.36, -2.92]3.85 [3.03, 4.90]3% [0%, 10%]13%48%-1.00+0.332026-01-03 → 2026-08-30
tmax12Zbilinearall31 1 QC3.48 [2.91, 4.37]1.21-3.48 [-4.37, -2.91]3.85 [3.03, 4.92]3% [0%, 10%]13%48%-1.00+0.332026-01-03 → 2026-08-30
tmax12Znearest30d26 1 QC6.84 [5.92, 8.19]1.52-6.84 [-8.19, -5.92]7.12 [5.97, 8.51]0% [0%, 0%]0%0%-2.63+0.232026-08-03 → 2026-08-30
tmax12Znearest90d26 1 QC6.84 [5.81, 8.46]1.52-6.84 [-8.46, -5.81]7.12 [5.86, 8.77]0% [0%, 0%]0%0%-2.63+0.232026-08-03 → 2026-08-30
tmax12Znearest365d31 1 QC6.25 [4.73, 7.82]1.77-6.25 [-7.82, -4.73]6.65 [4.98, 8.17]0% [0%, 0%]0%6%-2.59+0.032026-01-03 → 2026-08-30
tmax12Znearestall31 1 QC6.25 [4.76, 7.74]1.77-6.25 [-7.74, -4.76]6.65 [5.08, 8.17]0% [0%, 0%]0%6%-2.59+0.032026-01-03 → 2026-08-30
tmin00Zbilinear30d26 1 QC1.06 [0.88, 1.30]0.71-0.90 [-1.22, -0.62]1.23 [1.04, 1.48]50% [31%, 69%]88%100%+0.11+0.422026-08-03 → 2026-08-30
tmin00Zbilinear90d26 1 QC1.06 [0.84, 1.37]0.71-0.90 [-1.31, -0.53]1.23 [0.99, 1.53]50% [30%, 71%]88%100%+0.11+0.422026-08-03 → 2026-08-30
tmin00Zbilinear365d32 1 QC1.27 [0.93, 1.82]1.17-0.32 [-1.10, 0.89]1.54 [1.10, 2.10]44% [22%, 64%]81%94%+0.15+0.232026-01-03 → 2026-08-30
tmin00Zbilinearall32 1 QC1.27 [0.92, 1.79]1.17-0.32 [-1.11, 0.93]1.54 [1.08, 2.07]44% [23%, 64%]81%94%+0.15+0.232026-01-03 → 2026-08-30
tmin00Znearest30d26 1 QC0.66 [0.46, 0.91]0.68+0.14 [-0.14, 0.44]0.83 [0.58, 1.08]77% [52%, 93%]96%100%+0.44+0.442026-08-03 → 2026-08-30
tmin00Znearest90d26 1 QC0.66 [0.47, 0.97]0.68+0.14 [-0.18, 0.53]0.83 [0.58, 1.12]77% [45%, 92%]96%100%+0.44+0.442026-08-03 → 2026-08-30
tmin00Znearest365d32 1 QC1.12 [0.55, 2.11]1.13+0.69 [-0.05, 1.83]1.60 [0.72, 2.56]62% [22%, 87%]81%91%+0.26+0.262026-01-03 → 2026-08-30
tmin00Znearestall32 1 QC1.12 [0.57, 2.16]1.13+0.69 [-0.06, 1.91]1.60 [0.72, 2.59]62% [20%, 86%]81%91%+0.26+0.262026-01-03 → 2026-08-30
tmin12Zbilinear30d26 1 QC0.97 [0.78, 1.26]0.75-0.73 [-1.09, -0.41]1.16 [0.93, 1.48]54% [36%, 69%]92%100%+0.19+0.392026-08-03 → 2026-08-30
tmin12Zbilinear90d26 1 QC0.97 [0.75, 1.32]0.75-0.73 [-1.15, -0.40]1.16 [0.89, 1.53]54% [31%, 73%]92%100%+0.19+0.392026-08-03 → 2026-08-30
tmin12Zbilinear365d31 1 QC1.14 [0.83, 1.68]1.07-0.28 [-0.95, 0.76]1.41 [0.98, 1.96]48% [26%, 66%]87%94%+0.18+0.242026-01-03 → 2026-08-30
tmin12Zbilinearall31 1 QC1.14 [0.81, 1.63]1.07-0.28 [-0.98, 0.81]1.41 [0.97, 1.96]48% [26%, 67%]87%94%+0.18+0.242026-01-03 → 2026-08-30
tmin12Znearest30d26 1 QC0.74 [0.47, 1.06]0.71+0.28 [-0.08, 0.63]0.98 [0.65, 1.31]69% [50%, 83%]92%100%+0.38+0.422026-08-03 → 2026-08-30
tmin12Znearest90d26 1 QC0.74 [0.49, 1.11]0.71+0.28 [-0.17, 0.65]0.98 [0.65, 1.35]69% [44%, 83%]92%100%+0.38+0.422026-08-03 → 2026-08-30
tmin12Znearest365d31 1 QC1.06 [0.59, 1.91]1.01+0.67 [0.07, 1.61]1.49 [0.77, 2.31]58% [21%, 79%]81%94%+0.24+0.282026-01-03 → 2026-08-30
tmin12Znearestall31 1 QC1.06 [0.56, 1.87]1.01+0.67 [-0.02, 1.63]1.49 [0.75, 2.30]58% [24%, 80%]81%94%+0.24+0.282026-01-03 → 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 2, 00Z bilinear tmax+10+50-5-102026-08-03: -2.49 °F2026-08-04: -3.44 °F2026-08-05: -2.7 °F2026-08-06: -2.44 °F2026-08-07: -3.9 °F2026-08-08: -2.34 °F2026-08-09: -2.66 °F2026-08-10: -2.48 °F2026-08-11: -3.65 °F2026-08-12: -3 °F2026-08-13: -2.8 °F2026-08-14: -4.09 °F2026-08-15: -3.09 °F2026-08-16: -2.94 °F2026-08-17: -2.05 °F2026-08-18: -5.68 °F2026-08-19: -5.99 °F2026-08-20: -1.56 °F2026-08-21: -5.43 °F2026-08-22: -3.08 °F2026-08-23: -4.58 °F2026-08-24: -3.09 °F2026-08-25: -3.04 °F2026-08-26: -4.93 °F2026-08-27: -9.25 °F2026-08-30: -5.69 °F2026-08-032026-08-30°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 (28 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-5.69
2026-08-29—
2026-08-28—
2026-08-27-9.25
2026-08-26-4.93
2026-08-25-3.04
2026-08-24-3.09
2026-08-23-4.58
2026-08-22-3.08
2026-08-21-5.43
2026-08-20-1.56
2026-08-19-5.99
2026-08-18-5.68
2026-08-17-2.05
2026-08-16-2.94
2026-08-15-3.09
2026-08-14-4.09
2026-08-13-2.80
2026-08-12-3.00
2026-08-11-3.65
2026-08-10-2.48
2026-08-09-2.66
2026-08-08-2.34
2026-08-07-3.90
2026-08-06-2.44
2026-08-05-2.70
2026-08-04-3.44
2026-08-03-2.49

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KLAX, lead day 2-10 to -9 °F: 1 day-9 to -8 °F: 0 days-8 to -7 °F: 0 days-7 to -6 °F: 0 days-6 to -5 °F: 4 days-5 to -4 °F: 4 days-4 to -3 °F: 8 days-3 to -2 °F: 12 days-2 to -1 °F: 3 days-1 to 0 °F: 0 days0 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| 3.02 · P90 |e| 5.65 °F-100+10 °Fn = 32 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
-10.00-9.001
-9.00-8.000
-8.00-7.000
-7.00-6.000
-6.00-5.004
-5.00-4.004
-4.00-3.008
-3.00-2.0012
-2.00-1.003
-1.00+0.000
+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
2026-08263.71 -3.71
2026-0162.49 -2.49

Availability

ModelScored period DaysCoverage
GraphCast (IFS init)2026-01-03 → 2026-08-30 32
GraphCast (IFS init)2026-01-03 → 2026-08-30 32
GraphCast (IFS init)2026-01-03 → 2026-08-30 31
GraphCast (IFS init)2026-01-03 → 2026-08-30 31

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 26 +2.03 [1.41, 2.90] yes
Aurora (IFS init) 1 -0.60 [-0.60, -0.60] yes
FourCastNet v2 (IFS init) 1 +2.56 [2.56, 2.56] yes
NCEP GFS 26 +1.50 [0.78, 2.14] yes
ECMWF IFS HRES 21 +1.60 [0.88, 2.70] yes
Pangu-Weather (IFS init) 1 +1.66 [1.66, 1.66] yes
Persistence (baseline) 26 +1.82 [1.17, 2.46] yes

Cite this page

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

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

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