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

Chicago O'Hare · ECMWF AIFS Single · lead day 2

KORD · 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, 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
tmax00Zbilinear30d28 1 QC3.58 [2.50, 4.62]1.45-3.56 [-4.62, -2.47]4.03 [2.92, 4.98]7% [0%, 19%]18%36%-0.11+0.562026-08-03 → 2026-08-30
tmax00Zbilinear90d28 1 QC3.58 [2.44, 4.85]1.45-3.56 [-4.85, -2.42]4.03 [2.81, 5.15]7% [0%, 18%]18%36%-0.11+0.562026-08-03 → 2026-08-30
tmax00Zbilinear365d28 1 QC3.58 [2.37, 4.78]1.45-3.56 [-4.78, -2.34]4.03 [2.68, 5.10]7% [0%, 20%]18%36%-0.11+0.562026-08-03 → 2026-08-30
tmax00Zbilinearall28 1 QC3.58 [2.41, 4.81]1.45-3.56 [-4.81, -2.39]4.03 [2.68, 5.16]7% [0%, 19%]18%36%-0.11+0.562026-08-03 → 2026-08-30
tmax00Znearest30d28 1 QC3.12 [2.07, 4.20]1.46-3.10 [-4.20, -2.03]3.64 [2.45, 4.65]14% [0%, 35%]29%61%+0.03+0.552026-08-03 → 2026-08-30
tmax00Znearest90d28 1 QC3.12 [1.97, 4.42]1.46-3.10 [-4.42, -1.93]3.64 [2.33, 4.78]14% [0%, 36%]29%61%+0.03+0.552026-08-03 → 2026-08-30
tmax00Znearest365d28 1 QC3.12 [1.91, 4.35]1.46-3.10 [-4.32, -1.88]3.64 [2.28, 4.75]14% [0%, 38%]29%61%+0.03+0.552026-08-03 → 2026-08-30
tmax00Znearestall28 1 QC3.12 [1.91, 4.37]1.46-3.10 [-4.34, -1.88]3.64 [2.25, 4.77]14% [0%, 36%]29%61%+0.03+0.552026-08-03 → 2026-08-30
tmax12Zbilinear30d28 1 QC3.42 [2.52, 4.29]1.30-3.38 [-4.27, -2.46]3.79 [2.80, 4.66]7% [0%, 18%]18%39%-0.06+0.602026-08-03 → 2026-08-30
tmax12Zbilinear90d28 1 QC3.42 [2.49, 4.39]1.30-3.38 [-4.39, -2.44]3.79 [2.71, 4.71]7% [0%, 18%]18%39%-0.06+0.602026-08-03 → 2026-08-30
tmax12Zbilinear365d28 1 QC3.42 [2.47, 4.41]1.30-3.38 [-4.37, -2.39]3.79 [2.69, 4.73]7% [0%, 19%]18%39%-0.06+0.602026-08-03 → 2026-08-30
tmax12Zbilinearall28 1 QC3.42 [2.47, 4.43]1.30-3.38 [-4.43, -2.40]3.79 [2.68, 4.74]7% [0%, 18%]18%39%-0.06+0.602026-08-03 → 2026-08-30
tmax12Znearest30d28 1 QC2.98 [2.04, 3.93]1.37-2.93 [-3.90, -1.96]3.43 [2.31, 4.35]11% [0%, 25%]32%57%+0.07+0.582026-08-03 → 2026-08-30
tmax12Znearest90d28 1 QC2.98 [1.99, 4.00]1.37-2.93 [-3.97, -1.94]3.43 [2.24, 4.40]11% [0%, 26%]32%57%+0.07+0.582026-08-03 → 2026-08-30
tmax12Znearest365d28 1 QC2.98 [1.99, 4.01]1.37-2.93 [-3.96, -1.93]3.43 [2.25, 4.44]11% [0%, 27%]32%57%+0.07+0.582026-08-03 → 2026-08-30
tmax12Znearestall28 1 QC2.98 [1.99, 4.04]1.37-2.93 [-4.01, -1.94]3.43 [2.21, 4.44]11% [0%, 26%]32%57%+0.07+0.582026-08-03 → 2026-08-30
tmin00Zbilinear30d28 1 QC1.59 [1.29, 1.89]1.57+0.10 [-0.81, 0.85]1.96 [1.63, 2.25]43% [29%, 56%]71%86%+0.50+0.512026-08-03 → 2026-08-30
tmin00Zbilinear90d28 1 QC1.59 [1.24, 1.97]1.57+0.10 [-0.88, 0.95]1.96 [1.59, 2.29]43% [26%, 60%]71%86%+0.50+0.512026-08-03 → 2026-08-30
tmin00Zbilinear365d28 1 QC1.59 [1.21, 1.92]1.57+0.10 [-1.00, 1.04]1.96 [1.52, 2.26]43% [26%, 61%]71%86%+0.50+0.512026-08-03 → 2026-08-30
tmin00Zbilinearall28 1 QC1.59 [1.23, 2.00]1.57+0.10 [-0.88, 1.02]1.96 [1.58, 2.34]43% [25%, 62%]71%86%+0.50+0.512026-08-03 → 2026-08-30
tmin00Znearest30d28 1 QC1.75 [1.42, 2.11]1.68-0.55 [-1.60, 0.30]2.14 [1.76, 2.53]32% [23%, 41%]61%86%+0.44+0.472026-08-03 → 2026-08-30
tmin00Znearest90d28 1 QC1.75 [1.39, 2.15]1.68-0.55 [-1.68, 0.42]2.14 [1.73, 2.54]32% [21%, 43%]61%86%+0.44+0.472026-08-03 → 2026-08-30
tmin00Znearest365d28 1 QC1.75 [1.37, 2.16]1.68-0.55 [-1.82, 0.46]2.14 [1.70, 2.57]32% [23%, 43%]61%86%+0.44+0.472026-08-03 → 2026-08-30
tmin00Znearestall28 1 QC1.75 [1.37, 2.18]1.68-0.55 [-1.72, 0.50]2.14 [1.71, 2.54]32% [21%, 43%]61%86%+0.44+0.472026-08-03 → 2026-08-30
tmin12Zbilinear30d28 1 QC1.55 [1.34, 1.76]1.55+0.28 [-0.76, 1.04]1.87 [1.61, 2.11]32% [19%, 44%]68%89%+0.51+0.512026-08-03 → 2026-08-30
tmin12Zbilinear90d28 1 QC1.55 [1.31, 1.83]1.55+0.28 [-0.83, 1.13]1.87 [1.53, 2.15]32% [17%, 46%]68%89%+0.51+0.512026-08-03 → 2026-08-30
tmin12Zbilinear365d28 1 QC1.55 [1.28, 1.81]1.55+0.28 [-1.01, 1.18]1.87 [1.53, 2.13]32% [14%, 48%]68%89%+0.51+0.512026-08-03 → 2026-08-30
tmin12Zbilinearall28 1 QC1.55 [1.31, 1.85]1.55+0.28 [-0.87, 1.15]1.87 [1.53, 2.16]32% [14%, 47%]68%89%+0.51+0.512026-08-03 → 2026-08-30
tmin12Znearest30d28 1 QC1.70 [1.37, 2.11]1.68-0.34 [-1.54, 0.53]2.01 [1.57, 2.48]32% [23%, 42%]64%86%+0.46+0.472026-08-03 → 2026-08-30
tmin12Znearest90d28 1 QC1.70 [1.32, 2.14]1.68-0.34 [-1.61, 0.63]2.01 [1.50, 2.51]32% [24%, 43%]64%86%+0.46+0.472026-08-03 → 2026-08-30
tmin12Znearest365d28 1 QC1.70 [1.31, 2.19]1.68-0.34 [-1.85, 0.65]2.01 [1.50, 2.56]32% [23%, 43%]64%86%+0.46+0.472026-08-03 → 2026-08-30
tmin12Znearestall28 1 QC1.70 [1.33, 2.16]1.68-0.34 [-1.70, 0.65]2.01 [1.49, 2.53]32% [24%, 43%]64%86%+0.46+0.472026-08-03 → 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 KORD, lead day 2, 00Z bilinear tmax+10+50-5-102026-08-03: -4.93 °F2026-08-04: -3.87 °F2026-08-05: -6.52 °F2026-08-06: -4.28 °F2026-08-07: -4.31 °F2026-08-08: -2.63 °F2026-08-09: -6.07 °F2026-08-10: -8.39 °F2026-08-11: -5.93 °F2026-08-12: -5.55 °F2026-08-13: -2.46 °F2026-08-14: -3.24 °F2026-08-15: +0.26 °F2026-08-16: -3.26 °F2026-08-17: -2.99 °F2026-08-18: -0.34 °F2026-08-19: -1.26 °F2026-08-20: -1.01 °F2026-08-21: -3.06 °F2026-08-22: -3.53 °F2026-08-23: -3.32 °F2026-08-24: -4.45 °F2026-08-25: -4.77 °F2026-08-26: -2.42 °F2026-08-27: -3.18 °F2026-08-28: -3.98 °F2026-08-29: -1.99 °F2026-08-30: -2.18 °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
2026-08-30-2.18
2026-08-29-1.99
2026-08-28-3.98
2026-08-27-3.18
2026-08-26-2.42
2026-08-25-4.77
2026-08-24-4.45
2026-08-23-3.32
2026-08-22-3.53
2026-08-21-3.06
2026-08-20-1.01
2026-08-19-1.26
2026-08-18-0.34
2026-08-17-2.99
2026-08-16-3.26
2026-08-15+0.26
2026-08-14-3.24
2026-08-13-2.46
2026-08-12-5.55
2026-08-11-5.93
2026-08-10-8.39
2026-08-09-6.07
2026-08-08-2.63
2026-08-07-4.31
2026-08-06-4.28
2026-08-05-6.52
2026-08-04-3.87
2026-08-03-4.93

Error distribution

Distribution of the signed daily error in °F for ECMWF AIFS Single at KORD, lead day 2-10 to -9 °F: 0 days-9 to -8 °F: 1 day-8 to -7 °F: 0 days-7 to -6 °F: 2 days-6 to -5 °F: 2 days-5 to -4 °F: 5 days-4 to -3 °F: 8 days-3 to -2 °F: 5 days-2 to -1 °F: 3 days-1 to 0 °F: 1 day0 to 1 °F: 1 day1 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| 3.29 · P90 |e| 5.97 °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
-9.00-8.001
-8.00-7.000
-7.00-6.002
-6.00-5.002
-5.00-4.005
-4.00-3.008
-3.00-2.005
-2.00-1.003
-1.00+0.001
+0.00+1.001
+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
2026-08283.58 -3.56

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 +0.76 [0.76, 0.76] yes
FourCastNet v2 (IFS init) 1 +2.17 [2.17, 2.17] yes
NCEP GFS 28 +0.64 [-0.31, 1.64] no
GraphCast (IFS init) 26 -0.67 [-1.35, -0.27] yes
ECMWF IFS HRES 22 +0.29 [-0.76, 1.26] no
Pangu-Weather (IFS init) 1 +0.74 [0.74, 0.74] yes
Persistence (baseline) 28 +0.36 [-0.75, 1.51] no

Cite this page

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

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KORD (Chicago O'Hare), 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/KORD/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