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 2

KLAX · aifs_single · 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, 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
tmax00Zbilinear30d28 2 QC1.72 [1.21, 2.25]1.46+1.18 [0.59, 1.76]2.14 [1.56, 2.65]36% [17%, 57%]61%89%+0.09+0.262026-08-03 → 2026-08-30
tmax00Zbilinear90d28 2 QC1.72 [1.17, 2.30]1.46+1.18 [0.32, 1.77]2.14 [1.50, 2.66]36% [14%, 57%]61%89%+0.09+0.262026-08-03 → 2026-08-30
tmax00Zbilinear365d28 2 QC1.72 [1.13, 2.36]1.46+1.18 [0.26, 1.78]2.14 [1.44, 2.69]36% [13%, 57%]61%89%+0.09+0.262026-08-03 → 2026-08-30
tmax00Zbilinearall28 2 QC1.72 [1.17, 2.37]1.46+1.18 [0.38, 1.83]2.14 [1.50, 2.75]36% [13%, 57%]61%89%+0.09+0.262026-08-03 → 2026-08-30
tmax00Znearest30d28 2 QC1.57 [1.11, 2.05]1.48+0.70 [0.09, 1.29]1.95 [1.37, 2.41]32% [15%, 48%]68%86%+0.17+0.252026-08-03 → 2026-08-30
tmax00Znearest90d28 2 QC1.57 [1.08, 2.10]1.48+0.70 [-0.23, 1.30]1.95 [1.32, 2.46]32% [12%, 50%]68%86%+0.17+0.252026-08-03 → 2026-08-30
tmax00Znearest365d28 2 QC1.57 [1.04, 2.17]1.48+0.70 [-0.27, 1.31]1.95 [1.27, 2.48]32% [7%, 50%]68%86%+0.17+0.252026-08-03 → 2026-08-30
tmax00Znearestall28 2 QC1.57 [1.04, 2.20]1.48+0.70 [-0.15, 1.37]1.95 [1.27, 2.54]32% [10%, 50%]68%86%+0.17+0.252026-08-03 → 2026-08-30
tmax12Zbilinear30d28 2 QC1.43 [1.05, 1.82]1.38+0.53 [-0.08, 1.08]1.72 [1.25, 2.09]39% [23%, 58%]71%89%+0.24+0.302026-08-03 → 2026-08-30
tmax12Zbilinear90d28 2 QC1.43 [0.97, 1.85]1.38+0.53 [-0.38, 1.11]1.72 [1.10, 2.12]39% [21%, 59%]71%89%+0.24+0.302026-08-03 → 2026-08-30
tmax12Zbilinear365d28 2 QC1.43 [0.95, 1.90]1.38+0.53 [-0.37, 1.15]1.72 [1.09, 2.15]39% [19%, 60%]71%89%+0.24+0.302026-08-03 → 2026-08-30
tmax12Zbilinearall28 2 QC1.43 [0.95, 1.90]1.38+0.53 [-0.32, 1.11]1.72 [1.09, 2.17]39% [19%, 59%]71%89%+0.24+0.302026-08-03 → 2026-08-30
tmax12Znearest30d28 2 QC1.40 [1.02, 1.77]1.40+0.06 [-0.58, 0.63]1.67 [1.20, 2.05]39% [22%, 61%]79%93%+0.26+0.292026-08-03 → 2026-08-30
tmax12Znearest90d28 2 QC1.40 [0.89, 1.89]1.40+0.06 [-0.85, 0.69]1.67 [1.00, 2.18]39% [19%, 65%]79%93%+0.26+0.292026-08-03 → 2026-08-30
tmax12Znearest365d28 2 QC1.40 [0.88, 1.93]1.40+0.06 [-0.89, 0.72]1.67 [0.98, 2.18]39% [18%, 65%]79%93%+0.26+0.292026-08-03 → 2026-08-30
tmax12Znearestall28 2 QC1.40 [0.90, 1.90]1.40+0.06 [-0.84, 0.67]1.67 [1.00, 2.19]39% [18%, 65%]79%93%+0.26+0.292026-08-03 → 2026-08-30
tmin00Zbilinear30d28 2 QC0.62 [0.53, 0.70]0.62+0.01 [-0.31, 0.39]0.69 [0.61, 0.77]82% [71%, 93%]100%100%+0.51+0.522026-08-03 → 2026-08-30
tmin00Zbilinear90d28 2 QC0.62 [0.52, 0.70]0.62+0.01 [-0.32, 0.44]0.69 [0.59, 0.77]82% [71%, 95%]100%100%+0.51+0.522026-08-03 → 2026-08-30
tmin00Zbilinear365d28 2 QC0.62 [0.52, 0.70]0.62+0.01 [-0.33, 0.52]0.69 [0.59, 0.78]82% [71%, 94%]100%100%+0.51+0.522026-08-03 → 2026-08-30
tmin00Zbilinearall28 2 QC0.62 [0.51, 0.70]0.62+0.01 [-0.33, 0.50]0.69 [0.58, 0.77]82% [71%, 100%]100%100%+0.51+0.522026-08-03 → 2026-08-30
tmin00Znearest30d28 2 QC0.66 [0.56, 0.79]0.66+0.02 [-0.40, 0.50]0.77 [0.65, 0.90]79% [57%, 96%]100%100%+0.47+0.482026-08-03 → 2026-08-30
tmin00Znearest90d28 2 QC0.66 [0.55, 0.80]0.66+0.02 [-0.40, 0.58]0.77 [0.63, 0.90]79% [57%, 100%]100%100%+0.47+0.482026-08-03 → 2026-08-30
tmin00Znearest365d28 2 QC0.66 [0.54, 0.83]0.66+0.02 [-0.41, 0.65]0.77 [0.63, 0.92]79% [56%, 100%]100%100%+0.47+0.482026-08-03 → 2026-08-30
tmin00Znearestall28 2 QC0.66 [0.53, 0.82]0.66+0.02 [-0.41, 0.64]0.77 [0.61, 0.91]79% [56%, 100%]100%100%+0.47+0.482026-08-03 → 2026-08-30
tmin12Zbilinear30d28 2 QC0.56 [0.47, 0.65]0.49-0.23 [-0.48, 0.04]0.66 [0.56, 0.75]82% [73%, 90%]100%100%+0.55+0.612026-08-03 → 2026-08-30
tmin12Zbilinear90d28 2 QC0.56 [0.46, 0.65]0.49-0.23 [-0.50, 0.03]0.66 [0.55, 0.76]82% [73%, 91%]100%100%+0.55+0.612026-08-03 → 2026-08-30
tmin12Zbilinear365d28 2 QC0.56 [0.44, 0.66]0.49-0.23 [-0.49, 0.06]0.66 [0.53, 0.76]82% [71%, 93%]100%100%+0.55+0.612026-08-03 → 2026-08-30
tmin12Zbilinearall28 2 QC0.56 [0.45, 0.66]0.49-0.23 [-0.53, 0.08]0.66 [0.54, 0.75]82% [71%, 93%]100%100%+0.55+0.612026-08-03 → 2026-08-30
tmin12Znearest30d28 2 QC0.60 [0.50, 0.71]0.55-0.26 [-0.60, 0.12]0.73 [0.62, 0.82]75% [62%, 88%]100%100%+0.52+0.572026-08-03 → 2026-08-30
tmin12Znearest90d28 2 QC0.60 [0.49, 0.71]0.55-0.26 [-0.63, 0.14]0.73 [0.61, 0.82]75% [62%, 90%]100%100%+0.52+0.572026-08-03 → 2026-08-30
tmin12Znearest365d28 2 QC0.60 [0.46, 0.71]0.55-0.26 [-0.63, 0.17]0.73 [0.58, 0.83]75% [62%, 92%]100%100%+0.52+0.572026-08-03 → 2026-08-30
tmin12Znearestall28 2 QC0.60 [0.48, 0.72]0.55-0.26 [-0.64, 0.20]0.73 [0.60, 0.82]75% [63%, 91%]100%100%+0.52+0.572026-08-03 → 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 ECMWF AIFS Single at KLAX, lead day 2, 00Z bilinear tmax+10+50-5-102026-08-03: +2.55 °F2026-08-04: +0.48 °F2026-08-05: +1.59 °F2026-08-06: +2.21 °F2026-08-07: +0.27 °F2026-08-08: +2.43 °F2026-08-09: +1.25 °F2026-08-10: +1 °F2026-08-11: -0.26 °F2026-08-12: +0.42 °F2026-08-13: -0.05 °F2026-08-14: -0.6 °F2026-08-15: +1.55 °F2026-08-16: +2.79 °F2026-08-17: +3.68 °F2026-08-18: -0.38 °F2026-08-19: +0.33 °F2026-08-20: +4.22 °F2026-08-21: -1.16 °F2026-08-22: +2.37 °F2026-08-23: +1.14 °F2026-08-24: +2.68 °F2026-08-25: +5.02 °F2026-08-26: +2.92 °F2026-08-27: -0.68 °F2026-08-28: +1.74 °F2026-08-29: -2.68 °F2026-08-30: -1.74 °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
2026-08-30-1.74
2026-08-29-2.68
2026-08-28+1.74
2026-08-27-0.68
2026-08-26+2.92
2026-08-25+5.02
2026-08-24+2.68
2026-08-23+1.14
2026-08-22+2.37
2026-08-21-1.16
2026-08-20+4.22
2026-08-19+0.33
2026-08-18-0.38
2026-08-17+3.68
2026-08-16+2.79
2026-08-15+1.55
2026-08-14-0.60
2026-08-13-0.05
2026-08-12+0.42
2026-08-11-0.26
2026-08-10+1.00
2026-08-09+1.25
2026-08-08+2.43
2026-08-07+0.27
2026-08-06+2.21
2026-08-05+1.59
2026-08-04+0.48
2026-08-03+2.55

Error distribution

Distribution of the signed daily error in °F for ECMWF AIFS Single at KLAX, lead day 2-10 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: 0 days-4 to -3 °F: 0 days-3 to -2 °F: 1 day-2 to -1 °F: 2 days-1 to 0 °F: 5 days0 to 1 °F: 5 days1 to 2 °F: 5 days2 to 3 °F: 7 days3 to 4 °F: 1 day4 to 5 °F: 1 day5 to 6 °F: 1 day6 to 7 °F: 0 days7 to 8 °F: 0 days8 to 9 °F: 0 days9 to 10 °F: 0 daysdashed: P50 |e| 1.57 · P90 |e| 3.15 °F-100+10 °Fn = 28 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
-5.00-4.000
-4.00-3.000
-3.00-2.001
-2.00-1.002
-1.00+0.005
+0.00+1.005
+1.00+2.005
+2.00+3.007
+3.00+4.001
+4.00+5.001
+5.00+6.001
+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
2026-08281.72 +1.18

Availability

ModelScored period DaysCoverage
ECMWF AIFS Single2026-08-03 → 2026-08-30 28
ECMWF AIFS Single2026-08-03 → 2026-08-30 28
ECMWF AIFS Single2026-08-03 → 2026-08-30 28
ECMWF AIFS Single2026-08-03 → 2026-08-30 28

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 (IFS init) 1 -4.56 [-4.56, -4.56] yes
FourCastNet v2 (IFS init) 1 -1.39 [-1.39, -1.39] yes
NCEP GFS 28 -0.53 [-1.39, 0.24] no
GraphCast (IFS init) 26 -2.03 [-2.90, -1.41] yes
ECMWF IFS HRES 23 -0.44 [-1.27, 0.84] no
Pangu-Weather (IFS init) 1 -2.30 [-2.30, -2.30] yes
Persistence (baseline) 28 -0.17 [-0.85, 0.35] no

Cite this page

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

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