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 0

KLAX · aifs_single · lead 0

Target day = initialization date + 0 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
tmax00Zbilinear30d30 2 QC1.48 [1.24, 1.74]1.31+0.73 [0.21, 1.28]1.77 [1.50, 2.01]33% [23%, 43%]70%93%——2026-08-01 → 2026-08-30
tmax00Zbilinear90d30 2 QC1.48 [1.24, 1.76]1.31+0.73 [-0.09, 1.47]1.77 [1.52, 2.03]33% [21%, 45%]70%93%——2026-08-01 → 2026-08-30
tmax00Zbilinear365d30 2 QC1.48 [1.21, 1.77]1.31+0.73 [-0.22, 1.50]1.77 [1.47, 2.02]33% [21%, 46%]70%93%——2026-08-01 → 2026-08-30
tmax00Zbilinearall30 2 QC1.48 [1.21, 1.78]1.31+0.73 [-0.12, 1.50]1.77 [1.49, 2.04]33% [21%, 45%]70%93%——2026-08-01 → 2026-08-30
tmax00Znearest30d30 2 QC1.37 [1.14, 1.67]1.33+0.27 [-0.31, 0.87]1.69 [1.38, 2.02]37% [27%, 47%]80%93%——2026-08-01 → 2026-08-30
tmax00Znearest90d30 2 QC1.37 [1.15, 1.70]1.33+0.27 [-0.58, 1.06]1.69 [1.39, 2.09]37% [24%, 46%]80%93%——2026-08-01 → 2026-08-30
tmax00Znearest365d30 2 QC1.37 [1.16, 1.74]1.33+0.27 [-0.77, 1.10]1.69 [1.38, 2.16]37% [24%, 47%]80%93%——2026-08-01 → 2026-08-30
tmax00Znearestall30 2 QC1.37 [1.12, 1.73]1.33+0.27 [-0.64, 1.03]1.69 [1.35, 2.08]37% [22%, 48%]80%93%——2026-08-01 → 2026-08-30
tmin00Zbilinear30d30 2 QC0.50 [0.38, 0.64]0.50-0.01 [-0.22, 0.19]0.62 [0.48, 0.77]93% [87%, 100%]100%100%——2026-08-01 → 2026-08-30
tmin00Zbilinear90d30 2 QC0.50 [0.35, 0.62]0.50-0.01 [-0.22, 0.19]0.62 [0.44, 0.75]93% [87%, 100%]100%100%——2026-08-01 → 2026-08-30
tmin00Zbilinear365d30 2 QC0.50 [0.34, 0.64]0.50-0.01 [-0.24, 0.20]0.62 [0.45, 0.78]93% [86%, 100%]100%100%——2026-08-01 → 2026-08-30
tmin00Zbilinearall30 2 QC0.50 [0.34, 0.63]0.50-0.01 [-0.24, 0.23]0.62 [0.42, 0.75]93% [86%, 100%]100%100%——2026-08-01 → 2026-08-30
tmin00Znearest30d30 2 QC0.56 [0.45, 0.69]0.54-0.17 [-0.41, 0.07]0.68 [0.55, 0.83]87% [70%, 100%]100%100%——2026-08-01 → 2026-08-30
tmin00Znearest90d30 2 QC0.56 [0.42, 0.68]0.54-0.17 [-0.41, 0.08]0.68 [0.51, 0.82]87% [73%, 100%]100%100%——2026-08-01 → 2026-08-30
tmin00Znearest365d30 2 QC0.56 [0.41, 0.69]0.54-0.17 [-0.43, 0.09]0.68 [0.51, 0.83]87% [71%, 100%]100%100%——2026-08-01 → 2026-08-30
tmin00Znearestall30 2 QC0.56 [0.41, 0.68]0.54-0.17 [-0.43, 0.12]0.68 [0.50, 0.82]87% [72%, 100%]100%100%——2026-08-01 → 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 0, 00Z bilinear tmax+5+2.50-2.5-52026-08-01: +2.7 °F2026-08-02: +2.34 °F2026-08-03: +1.91 °F2026-08-04: +0.29 °F2026-08-05: +1.55 °F2026-08-06: +1.69 °F2026-08-07: +0.15 °F2026-08-08: +2.81 °F2026-08-09: +0.46 °F2026-08-10: +1.79 °F2026-08-11: +0.19 °F2026-08-12: -0.23 °F2026-08-13: -1.24 °F2026-08-14: -1.6 °F2026-08-15: +1.02 °F2026-08-16: +2.04 °F2026-08-17: +2.14 °F2026-08-18: -1.23 °F2026-08-19: +0.35 °F2026-08-20: +3.49 °F2026-08-21: +0.41 °F2026-08-22: +1.97 °F2026-08-23: -0.18 °F2026-08-24: +2.24 °F2026-08-25: +1.88 °F2026-08-26: +0.74 °F2026-08-27: -3.64 °F2026-08-28: +1.01 °F2026-08-29: -2.24 °F2026-08-30: -0.96 °F2026-08-012026-08-30°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 (30 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-0.96
2026-08-29-2.24
2026-08-28+1.01
2026-08-27-3.64
2026-08-26+0.74
2026-08-25+1.88
2026-08-24+2.24
2026-08-23-0.18
2026-08-22+1.97
2026-08-21+0.41
2026-08-20+3.49
2026-08-19+0.35
2026-08-18-1.23
2026-08-17+2.14
2026-08-16+2.04
2026-08-15+1.02
2026-08-14-1.60
2026-08-13-1.24
2026-08-12-0.23
2026-08-11+0.19
2026-08-10+1.79
2026-08-09+0.46
2026-08-08+2.81
2026-08-07+0.15
2026-08-06+1.69
2026-08-05+1.55
2026-08-04+0.29
2026-08-03+1.91
2026-08-02+2.34
2026-08-01+2.70

Error distribution

Distribution of the signed daily error in °F for ECMWF AIFS Single at KLAX, lead day 0-5 to -4.5 °F: 0 days-4.5 to -4 °F: 0 days-4 to -3.5 °F: 1 day-3.5 to -3 °F: 0 days-3 to -2.5 °F: 0 days-2.5 to -2 °F: 1 day-2 to -1.5 °F: 1 day-1.5 to -1 °F: 2 days-1 to -0.5 °F: 1 day-0.5 to 0 °F: 2 days0 to 0.5 °F: 6 days0.5 to 1 °F: 1 day1 to 1.5 °F: 2 days1.5 to 2 °F: 6 days2 to 2.5 °F: 4 days2.5 to 3 °F: 2 days3 to 3.5 °F: 1 day3.5 to 4 °F: 0 days4 to 4.5 °F: 0 days4.5 to 5 °F: 0 daysdashed: P50 |e| 1.58 · P90 |e| 2.71 °F-50+5 °Fn = 30 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
-4.00-3.501
-3.50-3.000
-3.00-2.500
-2.50-2.001
-2.00-1.501
-1.50-1.002
-1.00-0.501
-0.50+0.002
+0.00+0.506
+0.50+1.001
+1.00+1.502
+1.50+2.006
+2.00+2.504
+2.50+3.002
+3.00+3.501
+3.50+4.000
+4.00+4.500
+4.50+5.000

Month by month

00Z bilinear daily maximum, newest first.

Monthn MAE °FBias °F
2026-08301.48 +0.73

Availability

ModelScored period DaysCoverage
ECMWF AIFS Single2026-08-01 → 2026-08-30 30
ECMWF AIFS Single2026-08-01 → 2026-08-30 30

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) 2 -4.30 [-4.97, -3.63] yes
Aurora (IFS init) 3 -3.22 [-4.21, -2.04] yes
FourCastNet v2 (GFS init) 2 -1.72 [-2.93, -0.51] yes
FourCastNet v2 (IFS init) 3 -1.32 [-2.91, -0.23] yes
NCEP GFS 30 -0.60 [-1.21, -0.04] yes
GraphCast (GFS init) 2 -3.97 [-4.24, -3.70] yes
GraphCast (IFS init) 28 -1.88 [-2.48, -1.34] yes
ECMWF IFS HRES 25 -0.82 [-1.42, 0.42] no
Pangu-Weather (GFS init) 2 -0.87 [-1.83, 0.09] no
Pangu-Weather (IFS init) 3 -0.73 [-2.09, 0.41] no

Cite this page

ShortCastCheck, KLAX aifs_single lead 0, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KLAX/model/aifs_single/lead/0/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KLAX (Los Angeles Intl), model aifs_single, lead day 0. 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/0/

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