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

Minneapolis-St Paul · ECMWF AIFS Single · lead day 0

KMSP · 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, 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
tmax00Zbilinear30d30 1 QC3.15 [2.57, 3.69]1.48-2.94 [-3.48, -2.41]3.53 [2.95, 4.00]10% [3%, 17%]27%47%——2026-08-01 → 2026-08-30
tmax00Zbilinear90d30 1 QC3.15 [2.44, 3.76]1.48-2.94 [-3.56, -2.37]3.53 [2.82, 4.07]10% [0%, 17%]27%47%——2026-08-01 → 2026-08-30
tmax00Zbilinear365d30 1 QC3.15 [2.50, 3.86]1.48-2.94 [-3.56, -2.39]3.53 [2.85, 4.12]10% [0%, 17%]27%47%——2026-08-01 → 2026-08-30
tmax00Zbilinearall30 1 QC3.15 [2.48, 3.77]1.48-2.94 [-3.51, -2.34]3.53 [2.84, 4.06]10% [0%, 17%]27%47%——2026-08-01 → 2026-08-30
tmax00Znearest30d30 1 QC3.02 [2.32, 3.65]1.58-2.79 [-3.42, -2.16]3.44 [2.76, 3.95]17% [3%, 30%]30%53%——2026-08-01 → 2026-08-30
tmax00Znearest90d30 1 QC3.02 [2.15, 3.80]1.58-2.79 [-3.56, -2.06]3.44 [2.61, 4.11]17% [0%, 32%]30%53%——2026-08-01 → 2026-08-30
tmax00Znearest365d30 1 QC3.02 [2.22, 3.88]1.58-2.79 [-3.60, -2.12]3.44 [2.62, 4.17]17% [0%, 30%]30%53%——2026-08-01 → 2026-08-30
tmax00Znearestall30 1 QC3.02 [2.21, 3.76]1.58-2.79 [-3.50, -2.09]3.44 [2.62, 4.06]17% [0%, 33%]30%53%——2026-08-01 → 2026-08-30
tmin00Zbilinear30d30 1 QC2.52 [2.00, 3.02]1.80-2.07 [-2.66, -1.51]2.95 [2.51, 3.34]27% [13%, 40%]40%53%——2026-08-01 → 2026-08-30
tmin00Zbilinear90d30 1 QC2.52 [1.94, 3.02]1.80-2.07 [-2.59, -1.42]2.95 [2.45, 3.32]27% [14%, 44%]40%53%——2026-08-01 → 2026-08-30
tmin00Zbilinear365d30 1 QC2.52 [1.87, 3.02]1.80-2.07 [-2.62, -1.40]2.95 [2.38, 3.32]27% [14%, 44%]40%53%——2026-08-01 → 2026-08-30
tmin00Zbilinearall30 1 QC2.52 [1.88, 3.02]1.80-2.07 [-2.68, -1.36]2.95 [2.38, 3.32]27% [14%, 45%]40%53%——2026-08-01 → 2026-08-30
tmin00Znearest30d30 1 QC2.60 [2.09, 3.11]1.77-2.18 [-2.73, -1.64]3.04 [2.59, 3.44]23% [10%, 37%]40%53%——2026-08-01 → 2026-08-30
tmin00Znearest90d30 1 QC2.60 [2.00, 3.13]1.77-2.18 [-2.71, -1.54]3.04 [2.52, 3.45]23% [12%, 40%]40%53%——2026-08-01 → 2026-08-30
tmin00Znearest365d30 1 QC2.60 [1.94, 3.07]1.77-2.18 [-2.73, -1.51]3.04 [2.47, 3.41]23% [13%, 42%]40%53%——2026-08-01 → 2026-08-30
tmin00Znearestall30 1 QC2.60 [1.95, 3.11]1.77-2.18 [-2.75, -1.46]3.04 [2.49, 3.44]23% [12%, 42%]40%53%——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 KMSP, lead day 0, 00Z bilinear tmax+10+50-5-102026-08-01: -3.52 °F2026-08-02: -3.34 °F2026-08-03: -1.67 °F2026-08-04: -3.08 °F2026-08-05: -2.15 °F2026-08-06: -1.52 °F2026-08-07: -0.06 °F2026-08-08: -1.42 °F2026-08-09: -5.38 °F2026-08-10: -3.09 °F2026-08-11: -2.78 °F2026-08-12: -2.58 °F2026-08-13: +0.32 °F2026-08-14: -2.97 °F2026-08-15: -3.67 °F2026-08-16: -5.28 °F2026-08-17: -3.85 °F2026-08-18: -5.09 °F2026-08-19: -4.66 °F2026-08-20: +0.92 °F2026-08-21: -5.37 °F2026-08-22: -1.44 °F2026-08-23: -2.62 °F2026-08-24: -6.24 °F2026-08-25: +1.86 °F2026-08-26: -3.19 °F2026-08-27: -4.28 °F2026-08-28: -3.14 °F2026-08-29: -5.96 °F2026-08-30: -2.88 °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
2026-08-30-2.88
2026-08-29-5.96
2026-08-28-3.14
2026-08-27-4.28
2026-08-26-3.19
2026-08-25+1.86
2026-08-24-6.24
2026-08-23-2.62
2026-08-22-1.44
2026-08-21-5.37
2026-08-20+0.92
2026-08-19-4.66
2026-08-18-5.09
2026-08-17-3.85
2026-08-16-5.28
2026-08-15-3.67
2026-08-14-2.97
2026-08-13+0.32
2026-08-12-2.58
2026-08-11-2.78
2026-08-10-3.09
2026-08-09-5.38
2026-08-08-1.42
2026-08-07-0.06
2026-08-06-1.52
2026-08-05-2.15
2026-08-04-3.08
2026-08-03-1.67
2026-08-02-3.34
2026-08-01-3.52

Error distribution

Distribution of the signed daily error in °F for ECMWF AIFS Single at KMSP, lead day 0-10 to -9 °F: 0 days-9 to -8 °F: 0 days-8 to -7 °F: 0 days-7 to -6 °F: 1 day-6 to -5 °F: 5 days-5 to -4 °F: 2 days-4 to -3 °F: 8 days-3 to -2 °F: 6 days-2 to -1 °F: 4 days-1 to 0 °F: 1 day0 to 1 °F: 2 days1 to 2 °F: 1 day2 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| 3.09 · P90 |e| 5.37 °F-100+10 °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
-10.00-9.000
-9.00-8.000
-8.00-7.000
-7.00-6.001
-6.00-5.005
-5.00-4.002
-4.00-3.008
-3.00-2.006
-2.00-1.004
-1.00+0.001
+0.00+1.002
+1.00+2.001
+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
2026-08303.15 -2.94

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 -1.95 [-2.98, -0.93] yes
Aurora (IFS init) 3 -1.75 [-2.83, -1.21] yes
FourCastNet v2 (GFS init) 2 -0.78 [-0.88, -0.68] yes
FourCastNet v2 (IFS init) 3 -1.89 [-2.64, -1.52] yes
NCEP GFS 30 +1.07 [0.41, 1.77] yes
GraphCast (GFS init) 2 -2.56 [-3.39, -1.73] yes
GraphCast (IFS init) 28 -2.45 [-2.81, -2.11] yes
ECMWF IFS HRES 24 +0.51 [-0.13, 1.15] no
Pangu-Weather (GFS init) 2 -0.00 [-1.21, 1.20] no
Pangu-Weather (IFS init) 3 -0.60 [-1.27, 0.10] no

Cite this page

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

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KMSP (Minneapolis-St Paul), 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/KMSP/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