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 1

KLAX · aifs_single · lead 1

Target day = initialization date + 1 day. 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
tmax00Zbilinear30d29 2 QC1.57 [1.23, 1.90]1.38+1.02 [0.61, 1.46]1.91 [1.58, 2.21]34% [21%, 48%]62%86%+0.11+0.222026-08-02 → 2026-08-30
tmax00Zbilinear90d29 2 QC1.57 [1.21, 1.91]1.38+1.02 [0.42, 1.53]1.91 [1.55, 2.24]34% [20%, 50%]62%86%+0.11+0.222026-08-02 → 2026-08-30
tmax00Zbilinear365d29 2 QC1.57 [1.18, 1.93]1.38+1.02 [0.29, 1.56]1.91 [1.51, 2.24]34% [19%, 50%]62%86%+0.11+0.222026-08-02 → 2026-08-30
tmax00Zbilinearall29 2 QC1.57 [1.18, 1.92]1.38+1.02 [0.42, 1.61]1.91 [1.53, 2.24]34% [20%, 52%]62%86%+0.11+0.222026-08-02 → 2026-08-30
tmax00Znearest30d29 2 QC1.47 [1.14, 1.77]1.40+0.55 [0.11, 1.02]1.73 [1.40, 2.01]31% [11%, 52%]79%93%+0.16+0.212026-08-02 → 2026-08-30
tmax00Znearest90d29 2 QC1.47 [1.10, 1.83]1.40+0.55 [-0.08, 1.11]1.73 [1.35, 2.06]31% [8%, 53%]79%93%+0.16+0.212026-08-02 → 2026-08-30
tmax00Znearest365d29 2 QC1.47 [1.11, 1.85]1.40+0.55 [-0.24, 1.14]1.73 [1.35, 2.06]31% [0%, 52%]79%93%+0.16+0.212026-08-02 → 2026-08-30
tmax00Znearestall29 2 QC1.47 [1.07, 1.84]1.40+0.55 [-0.13, 1.18]1.73 [1.31, 2.07]31% [7%, 52%]79%93%+0.16+0.212026-08-02 → 2026-08-30
tmax12Zbilinear30d29 2 QC1.48 [1.11, 1.86]1.39+0.57 [-0.04, 1.14]1.84 [1.42, 2.20]41% [25%, 60%]69%90%+0.16+0.222026-08-02 → 2026-08-30
tmax12Zbilinear90d29 2 QC1.48 [1.08, 1.89]1.39+0.57 [-0.27, 1.22]1.84 [1.37, 2.24]41% [22%, 63%]69%90%+0.16+0.222026-08-02 → 2026-08-30
tmax12Zbilinear365d29 2 QC1.48 [1.08, 1.96]1.39+0.57 [-0.42, 1.27]1.84 [1.33, 2.28]41% [20%, 62%]69%90%+0.16+0.222026-08-02 → 2026-08-30
tmax12Zbilinearall29 2 QC1.48 [1.04, 1.90]1.39+0.57 [-0.31, 1.27]1.84 [1.31, 2.23]41% [20%, 62%]69%90%+0.16+0.222026-08-02 → 2026-08-30
tmax12Znearest30d29 2 QC1.42 [1.06, 1.78]1.40+0.11 [-0.56, 0.72]1.78 [1.30, 2.22]52% [34%, 69%]79%90%+0.20+0.212026-08-02 → 2026-08-30
tmax12Znearest90d29 2 QC1.42 [1.01, 1.87]1.40+0.11 [-0.79, 0.80]1.78 [1.19, 2.30]52% [33%, 69%]79%90%+0.20+0.212026-08-02 → 2026-08-30
tmax12Znearest365d29 2 QC1.42 [0.99, 1.91]1.40+0.11 [-0.97, 0.87]1.78 [1.15, 2.39]52% [32%, 69%]79%90%+0.20+0.212026-08-02 → 2026-08-30
tmax12Znearestall29 2 QC1.42 [1.01, 1.89]1.40+0.11 [-0.81, 0.86]1.78 [1.18, 2.29]52% [30%, 71%]79%90%+0.20+0.212026-08-02 → 2026-08-30
tmin00Zbilinear30d29 2 QC0.60 [0.51, 0.71]0.60-0.01 [-0.28, 0.27]0.70 [0.61, 0.82]83% [73%, 93%]100%100%+0.33+0.362026-08-02 → 2026-08-30
tmin00Zbilinear90d29 2 QC0.60 [0.50, 0.71]0.60-0.01 [-0.28, 0.33]0.70 [0.59, 0.81]83% [73%, 92%]100%100%+0.33+0.362026-08-02 → 2026-08-30
tmin00Zbilinear365d29 2 QC0.60 [0.50, 0.72]0.60-0.01 [-0.30, 0.39]0.70 [0.59, 0.82]83% [73%, 93%]100%100%+0.33+0.362026-08-02 → 2026-08-30
tmin00Zbilinearall29 2 QC0.60 [0.49, 0.72]0.60-0.01 [-0.31, 0.38]0.70 [0.58, 0.81]83% [73%, 95%]100%100%+0.33+0.362026-08-02 → 2026-08-30
tmin00Znearest30d29 2 QC0.64 [0.55, 0.75]0.64-0.04 [-0.41, 0.32]0.74 [0.64, 0.86]83% [73%, 93%]100%100%+0.29+0.312026-08-02 → 2026-08-30
tmin00Znearest90d29 2 QC0.64 [0.54, 0.74]0.64-0.04 [-0.39, 0.42]0.74 [0.63, 0.85]83% [73%, 92%]100%100%+0.29+0.312026-08-02 → 2026-08-30
tmin00Znearest365d29 2 QC0.64 [0.53, 0.76]0.64-0.04 [-0.41, 0.46]0.74 [0.63, 0.85]83% [73%, 93%]100%100%+0.29+0.312026-08-02 → 2026-08-30
tmin00Znearestall29 2 QC0.64 [0.52, 0.75]0.64-0.04 [-0.42, 0.46]0.74 [0.62, 0.85]83% [73%, 95%]100%100%+0.29+0.312026-08-02 → 2026-08-30
tmin12Zbilinear30d29 2 QC0.53 [0.41, 0.64]0.53-0.03 [-0.22, 0.21]0.65 [0.51, 0.76]90% [83%, 97%]100%100%+0.41+0.432026-08-02 → 2026-08-30
tmin12Zbilinear90d29 2 QC0.53 [0.38, 0.63]0.53-0.03 [-0.23, 0.19]0.65 [0.47, 0.75]90% [83%, 100%]100%100%+0.41+0.432026-08-02 → 2026-08-30
tmin12Zbilinear365d29 2 QC0.53 [0.39, 0.65]0.53-0.03 [-0.24, 0.20]0.65 [0.48, 0.76]90% [84%, 100%]100%100%+0.41+0.432026-08-02 → 2026-08-30
tmin12Zbilinearall29 2 QC0.53 [0.37, 0.63]0.53-0.03 [-0.25, 0.26]0.65 [0.45, 0.75]90% [84%, 100%]100%100%+0.41+0.432026-08-02 → 2026-08-30
tmin12Znearest30d29 2 QC0.57 [0.44, 0.70]0.58-0.11 [-0.37, 0.22]0.71 [0.56, 0.82]86% [76%, 97%]100%100%+0.36+0.372026-08-02 → 2026-08-30
tmin12Znearest90d29 2 QC0.57 [0.42, 0.69]0.58-0.11 [-0.38, 0.20]0.71 [0.54, 0.81]86% [75%, 100%]100%100%+0.36+0.372026-08-02 → 2026-08-30
tmin12Znearest365d29 2 QC0.57 [0.42, 0.71]0.58-0.11 [-0.39, 0.23]0.71 [0.54, 0.82]86% [75%, 100%]100%100%+0.36+0.372026-08-02 → 2026-08-30
tmin12Znearestall29 2 QC0.57 [0.41, 0.69]0.58-0.11 [-0.39, 0.29]0.71 [0.51, 0.81]86% [75%, 100%]100%100%+0.36+0.372026-08-02 → 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 1, 00Z bilinear tmax+5+2.50-2.5-52026-08-02: +2.47 °F2026-08-03: +2.03 °F2026-08-04: +0.59 °F2026-08-05: +1.44 °F2026-08-06: +1.48 °F2026-08-07: +0.08 °F2026-08-08: +3.18 °F2026-08-09: +1.29 °F2026-08-10: +0.77 °F2026-08-11: +0.25 °F2026-08-12: +0.22 °F2026-08-13: -0.32 °F2026-08-14: -1.45 °F2026-08-15: +1.3 °F2026-08-16: +3.48 °F2026-08-17: +2.35 °F2026-08-18: -1.43 °F2026-08-19: +0.28 °F2026-08-20: +3.71 °F2026-08-21: -0.11 °F2026-08-22: +3.16 °F2026-08-23: -0.43 °F2026-08-24: +2.58 °F2026-08-25: +2.49 °F2026-08-26: +1.95 °F2026-08-27: -1.07 °F2026-08-28: +2.38 °F2026-08-29: -2.55 °F2026-08-30: -0.68 °F2026-08-022026-08-30°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 (29 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-0.68
2026-08-29-2.55
2026-08-28+2.38
2026-08-27-1.07
2026-08-26+1.95
2026-08-25+2.49
2026-08-24+2.58
2026-08-23-0.43
2026-08-22+3.16
2026-08-21-0.11
2026-08-20+3.71
2026-08-19+0.28
2026-08-18-1.43
2026-08-17+2.35
2026-08-16+3.48
2026-08-15+1.30
2026-08-14-1.45
2026-08-13-0.32
2026-08-12+0.22
2026-08-11+0.25
2026-08-10+0.77
2026-08-09+1.29
2026-08-08+3.18
2026-08-07+0.08
2026-08-06+1.48
2026-08-05+1.44
2026-08-04+0.59
2026-08-03+2.03
2026-08-02+2.47

Error distribution

Distribution of the signed daily error in °F for ECMWF AIFS Single at KLAX, lead day 1-5 to -4.5 °F: 0 days-4.5 to -4 °F: 0 days-4 to -3.5 °F: 0 days-3.5 to -3 °F: 0 days-3 to -2.5 °F: 1 day-2.5 to -2 °F: 0 days-2 to -1.5 °F: 0 days-1.5 to -1 °F: 3 days-1 to -0.5 °F: 1 day-0.5 to 0 °F: 3 days0 to 0.5 °F: 4 days0.5 to 1 °F: 2 days1 to 1.5 °F: 4 days1.5 to 2 °F: 1 day2 to 2.5 °F: 5 days2.5 to 3 °F: 1 day3 to 3.5 °F: 3 days3.5 to 4 °F: 1 day4 to 4.5 °F: 0 days4.5 to 5 °F: 0 daysdashed: P50 |e| 1.44 · P90 |e| 3.16 °F-50+5 °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
-5.00-4.500
-4.50-4.000
-4.00-3.500
-3.50-3.000
-3.00-2.501
-2.50-2.000
-2.00-1.500
-1.50-1.003
-1.00-0.501
-0.50+0.003
+0.00+0.504
+0.50+1.002
+1.00+1.504
+1.50+2.001
+2.00+2.505
+2.50+3.001
+3.00+3.503
+3.50+4.001
+4.00+4.500
+4.50+5.000

Month by month

00Z bilinear daily maximum, newest first.

Monthn MAE °FBias °F
2026-08291.57 +1.02

Availability

ModelScored period DaysCoverage
ECMWF AIFS Single2026-08-02 → 2026-08-30 29
ECMWF AIFS Single2026-08-02 → 2026-08-30 29
ECMWF AIFS Single2026-08-02 → 2026-08-30 29
ECMWF AIFS Single2026-08-02 → 2026-08-30 29

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
Aurora (GFS init) 1 -5.27 [-5.27, -5.27] yes
Aurora (IFS init) 2 -4.29 [-4.64, -3.94] yes
FourCastNet v2 (GFS init) 1 -2.08 [-2.08, -2.08] yes
FourCastNet v2 (IFS init) 2 -1.47 [-2.16, -0.78] yes
NCEP GFS 29 -0.49 [-1.10, 0.07] no
GraphCast (GFS init) 1 -4.58 [-4.58, -4.58] yes
GraphCast (IFS init) 27 -2.03 [-2.77, -1.55] yes
ECMWF IFS HRES 22 -0.83 [-1.35, -0.02] yes
Pangu-Weather (GFS init) 1 -1.72 [-1.72, -1.72] yes
Pangu-Weather (IFS init) 2 -1.66 [-2.60, -0.73] yes
Persistence (baseline) 29 -0.19 [-0.80, 0.35] no

Cite this page

ShortCastCheck, KLAX aifs_single lead 1, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KLAX/model/aifs_single/lead/1/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KLAX (Los Angeles Intl), model aifs_single, lead day 1. 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/1/

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