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 · ECMWF AIFS Single · lead day 5

KLAX · aifs_single · 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, aifs-single-gpid5, starting 2026-08-01 — 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 QC2.05 [1.40, 2.77]1.98+0.55 [-1.08, 1.89]2.59 [1.67, 3.37]28% [12%, 46%]60%84%+0.28+0.222026-08-06 → 2026-08-30
tmax00Zbilinear90d25 2 QC2.05 [1.31, 2.76]1.98+0.55 [-1.41, 1.98]2.59 [1.52, 3.35]28% [11%, 50%]60%84%+0.28+0.222026-08-06 → 2026-08-30
tmax00Zbilinear365d25 2 QC2.05 [1.27, 2.85]1.98+0.55 [-1.67, 2.12]2.59 [1.52, 3.46]28% [11%, 50%]60%84%+0.28+0.222026-08-06 → 2026-08-30
tmax00Zbilinearall25 2 QC2.05 [1.31, 2.75]1.98+0.55 [-1.61, 1.95]2.59 [1.53, 3.36]28% [12%, 50%]60%84%+0.28+0.222026-08-06 → 2026-08-30
tmax00Znearest30d25 2 QC1.95 [1.23, 2.62]1.95+0.07 [-1.51, 1.38]2.49 [1.54, 3.17]28% [11%, 46%]60%80%+0.31+0.232026-08-06 → 2026-08-30
tmax00Znearest90d25 2 QC1.95 [1.09, 2.67]1.95+0.07 [-1.93, 1.41]2.49 [1.29, 3.18]28% [10%, 50%]60%80%+0.31+0.232026-08-06 → 2026-08-30
tmax00Znearest365d25 2 QC1.95 [1.06, 2.70]1.95+0.07 [-2.12, 1.60]2.49 [1.30, 3.24]28% [8%, 50%]60%80%+0.31+0.232026-08-06 → 2026-08-30
tmax00Znearestall25 2 QC1.95 [1.04, 2.66]1.95+0.07 [-2.08, 1.42]2.49 [1.31, 3.19]28% [8%, 50%]60%80%+0.31+0.232026-08-06 → 2026-08-30
tmax12Zbilinear30d24 2 QC1.49 [0.76, 2.20]1.49+0.49 [-0.45, 1.47]2.05 [1.13, 2.74]38% [13%, 68%]79%83%+0.48+0.432026-08-06 → 2026-08-30
tmax12Zbilinear90d24 2 QC1.49 [0.48, 2.24]1.49+0.49 [-0.66, 1.55]2.05 [0.65, 2.78]38% [10%, 80%]79%83%+0.48+0.432026-08-06 → 2026-08-30
tmax12Zbilinear365d24 2 QC1.49 [0.46, 2.29]1.49+0.49 [-0.72, 1.62]2.05 [0.65, 2.81]38% [10%, 78%]79%83%+0.48+0.432026-08-06 → 2026-08-30
tmax12Zbilinearall24 2 QC1.49 [0.48, 2.20]1.49+0.49 [-0.69, 1.49]2.05 [0.68, 2.74]38% [12%, 78%]79%83%+0.48+0.432026-08-06 → 2026-08-30
tmax12Znearest30d24 2 QC1.45 [0.83, 2.04]1.45-0.01 [-0.96, 0.93]1.96 [1.20, 2.51]58% [36%, 83%]71%83%+0.49+0.452026-08-06 → 2026-08-30
tmax12Znearest90d24 2 QC1.45 [0.57, 2.09]1.45-0.01 [-1.16, 1.02]1.96 [0.65, 2.56]58% [32%, 92%]71%83%+0.49+0.452026-08-06 → 2026-08-30
tmax12Znearest365d24 2 QC1.45 [0.55, 2.14]1.45-0.01 [-1.23, 1.11]1.96 [0.63, 2.57]58% [29%, 94%]71%83%+0.49+0.452026-08-06 → 2026-08-30
tmax12Znearestall24 2 QC1.45 [0.58, 2.10]1.45-0.01 [-1.23, 0.97]1.96 [0.66, 2.56]58% [32%, 91%]71%83%+0.49+0.452026-08-06 → 2026-08-30
tmin00Zbilinear30d25 2 QC0.58 [0.40, 0.83]0.58+0.04 [-0.19, 0.21]0.75 [0.46, 1.01]84% [61%, 100%]100%100%+0.68+0.652026-08-06 → 2026-08-30
tmin00Zbilinear90d25 2 QC0.58 [0.38, 0.84]0.58+0.04 [-0.22, 0.21]0.75 [0.45, 1.04]84% [59%, 100%]100%100%+0.68+0.652026-08-06 → 2026-08-30
tmin00Zbilinear365d25 2 QC0.58 [0.37, 0.89]0.58+0.04 [-0.24, 0.21]0.75 [0.43, 1.07]84% [57%, 100%]100%100%+0.68+0.652026-08-06 → 2026-08-30
tmin00Zbilinearall25 2 QC0.58 [0.38, 0.87]0.58+0.04 [-0.26, 0.20]0.75 [0.43, 1.05]84% [57%, 100%]100%100%+0.68+0.652026-08-06 → 2026-08-30
tmin00Znearest30d25 2 QC0.63 [0.42, 0.88]0.61+0.07 [-0.18, 0.26]0.80 [0.50, 1.07]80% [59%, 97%]96%100%+0.65+0.622026-08-06 → 2026-08-30
tmin00Znearest90d25 2 QC0.63 [0.42, 0.91]0.61+0.07 [-0.20, 0.26]0.80 [0.48, 1.09]80% [57%, 100%]96%100%+0.65+0.622026-08-06 → 2026-08-30
tmin00Znearest365d25 2 QC0.63 [0.39, 0.97]0.61+0.07 [-0.20, 0.27]0.80 [0.46, 1.12]80% [54%, 100%]96%100%+0.65+0.622026-08-06 → 2026-08-30
tmin00Znearestall25 2 QC0.63 [0.40, 0.94]0.61+0.07 [-0.23, 0.25]0.80 [0.46, 1.11]80% [53%, 100%]96%100%+0.65+0.622026-08-06 → 2026-08-30
tmin12Zbilinear30d24 2 QC0.69 [0.56, 0.87]0.62-0.33 [-0.67, -0.06]0.89 [0.74, 1.08]71% [59%, 84%]100%100%+0.60+0.622026-08-06 → 2026-08-30
tmin12Zbilinear90d24 2 QC0.69 [0.55, 0.91]0.62-0.33 [-0.75, -0.05]0.89 [0.72, 1.13]71% [57%, 86%]100%100%+0.60+0.622026-08-06 → 2026-08-30
tmin12Zbilinear365d24 2 QC0.69 [0.54, 0.90]0.62-0.33 [-0.77, -0.03]0.89 [0.71, 1.12]71% [57%, 89%]100%100%+0.60+0.622026-08-06 → 2026-08-30
tmin12Zbilinearall24 2 QC0.69 [0.55, 0.95]0.62-0.33 [-0.79, -0.04]0.89 [0.71, 1.13]71% [57%, 87%]100%100%+0.60+0.622026-08-06 → 2026-08-30
tmin12Znearest30d24 2 QC0.73 [0.59, 0.93]0.67-0.30 [-0.73, 0.07]0.97 [0.80, 1.17]71% [56%, 83%]96%100%+0.58+0.582026-08-06 → 2026-08-30
tmin12Znearest90d24 2 QC0.73 [0.58, 0.97]0.67-0.30 [-0.87, 0.11]0.97 [0.79, 1.22]71% [50%, 84%]96%100%+0.58+0.582026-08-06 → 2026-08-30
tmin12Znearest365d24 2 QC0.73 [0.58, 0.96]0.67-0.30 [-0.86, 0.13]0.97 [0.77, 1.21]71% [52%, 86%]96%100%+0.58+0.582026-08-06 → 2026-08-30
tmin12Znearestall24 2 QC0.73 [0.58, 0.98]0.67-0.30 [-0.87, 0.11]0.97 [0.76, 1.22]71% [51%, 85%]96%100%+0.58+0.582026-08-06 → 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 ECMWF AIFS Single at KLAX, lead day 5, 00Z bilinear tmax+10+50-5-102026-08-06: +2 °F2026-08-07: +0.32 °F2026-08-08: +2.17 °F2026-08-09: +1.84 °F2026-08-10: +1.44 °F2026-08-11: +0.46 °F2026-08-12: +0.74 °F2026-08-13: -0.18 °F2026-08-14: -0.32 °F2026-08-15: +2.44 °F2026-08-16: +4.24 °F2026-08-17: +4.73 °F2026-08-18: +1.7 °F2026-08-19: +1.42 °F2026-08-20: +6.94 °F2026-08-21: -1.78 °F2026-08-22: -0.82 °F2026-08-23: -2.65 °F2026-08-24: +1.64 °F2026-08-25: -2.43 °F2026-08-26: -4.57 °F2026-08-27: -2.18 °F2026-08-28: +0.4 °F2026-08-29: -1.9 °F2026-08-30: -1.95 °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
2026-08-30-1.95
2026-08-29-1.90
2026-08-28+0.40
2026-08-27-2.18
2026-08-26-4.57
2026-08-25-2.43
2026-08-24+1.64
2026-08-23-2.65
2026-08-22-0.82
2026-08-21-1.78
2026-08-20+6.94
2026-08-19+1.42
2026-08-18+1.70
2026-08-17+4.73
2026-08-16+4.24
2026-08-15+2.44
2026-08-14-0.32
2026-08-13-0.18
2026-08-12+0.74
2026-08-11+0.46
2026-08-10+1.44
2026-08-09+1.84
2026-08-08+2.17
2026-08-07+0.32
2026-08-06+2.00

Error distribution

Distribution of the signed daily error in °F for ECMWF AIFS Single at KLAX, lead day 5-10 to -9 °F: 0 days-9 to -8 °F: 0 days-8 to -7 °F: 0 days-7 to -6 °F: 0 days-6 to -5 °F: 0 days-5 to -4 °F: 1 day-4 to -3 °F: 0 days-3 to -2 °F: 3 days-2 to -1 °F: 3 days-1 to 0 °F: 3 days0 to 1 °F: 4 days1 to 2 °F: 5 days2 to 3 °F: 3 days3 to 4 °F: 0 days4 to 5 °F: 2 days5 to 6 °F: 0 days6 to 7 °F: 1 day7 to 8 °F: 0 days8 to 9 °F: 0 days9 to 10 °F: 0 daysdashed: P50 |e| 1.84 · P90 |e| 4.44 °F-100+10 °Fn = 25 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
-7.00-6.000
-6.00-5.000
-5.00-4.001
-4.00-3.000
-3.00-2.003
-2.00-1.003
-1.00+0.003
+0.00+1.004
+1.00+2.005
+2.00+3.003
+3.00+4.000
+4.00+5.002
+5.00+6.000
+6.00+7.001
+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
2026-08252.05 +0.55

Availability

ModelScored period DaysCoverage
ECMWF AIFS Single2026-08-06 → 2026-08-30 25
ECMWF AIFS Single2026-08-06 → 2026-08-30 25
ECMWF AIFS Single2026-08-06 → 2026-08-30 24
ECMWF AIFS Single2026-08-06 → 2026-08-30 24

Compared with other models

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

Other modelCommon days MAE difference °FDistinguishable
NCEP GFS 25 +0.49 [-0.36, 1.24] no
GraphCast (IFS init) 25 -1.72 [-3.15, -0.63] yes
ECMWF IFS HRES 18 -0.16 [-0.76, 0.89] no
Persistence (baseline) 25 -0.79 [-1.76, 0.07] no

Cite this page

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

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