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 · Pangu-Weather (GFS init) · lead day 1

KMSP · pangu_gfs · 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, PANG_v100, starting 2026-08-28 — 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
tmax00Zbilinear30d1 1 QC0.54 [0.54, 0.54]0.00-0.54 [-0.54, -0.54]0.54 [0.54, 0.54]100% [100%, 100%]100%100%+0.82—2026-08-30 → 2026-08-30
tmax00Zbilinear90d1 1 QC0.54 [0.54, 0.54]0.00-0.54 [-0.54, -0.54]0.54 [0.54, 0.54]100% [100%, 100%]100%100%+0.82—2026-08-30 → 2026-08-30
tmax00Zbilinear365d1 1 QC0.54 [0.54, 0.54]0.00-0.54 [-0.54, -0.54]0.54 [0.54, 0.54]100% [100%, 100%]100%100%+0.82—2026-08-30 → 2026-08-30
tmax00Zbilinearall1 1 QC0.54 [0.54, 0.54]0.00-0.54 [-0.54, -0.54]0.54 [0.54, 0.54]100% [100%, 100%]100%100%+0.82—2026-08-30 → 2026-08-30
tmax00Znearest30d1 1 QC0.96 [0.96, 0.96]0.00-0.96 [-0.96, -0.96]0.96 [0.96, 0.96]100% [100%, 100%]100%100%+0.68—2026-08-30 → 2026-08-30
tmax00Znearest90d1 1 QC0.96 [0.96, 0.96]0.00-0.96 [-0.96, -0.96]0.96 [0.96, 0.96]100% [100%, 100%]100%100%+0.68—2026-08-30 → 2026-08-30
tmax00Znearest365d1 1 QC0.96 [0.96, 0.96]0.00-0.96 [-0.96, -0.96]0.96 [0.96, 0.96]100% [100%, 100%]100%100%+0.68—2026-08-30 → 2026-08-30
tmax00Znearestall1 1 QC0.96 [0.96, 0.96]0.00-0.96 [-0.96, -0.96]0.96 [0.96, 0.96]100% [100%, 100%]100%100%+0.68—2026-08-30 → 2026-08-30
tmax12Zbilinear30d2 1 QC6.57 [3.15, 9.99]3.42-6.57 [-9.99, -3.15]7.41 [3.15, 9.99]0% [0%, 0%]0%0%-3.38-1.282026-08-29 → 2026-08-30
tmax12Zbilinear90d2 1 QC6.57 [3.15, 9.99]3.42-6.57 [-9.99, -3.15]7.41 [3.15, 9.99]0% [0%, 0%]0%0%-3.38-1.282026-08-29 → 2026-08-30
tmax12Zbilinear365d2 1 QC6.57 [3.15, 9.99]3.42-6.57 [-9.99, -3.15]7.41 [3.15, 9.99]0% [0%, 0%]0%0%-3.38-1.282026-08-29 → 2026-08-30
tmax12Zbilinearall2 1 QC6.57 [3.15, 9.99]3.42-6.57 [-9.99, -3.15]7.41 [3.15, 9.99]0% [0%, 0%]0%0%-3.38-1.282026-08-29 → 2026-08-30
tmax12Znearest30d2 1 QC6.61 [3.41, 9.80]3.20-6.61 [-9.80, -3.41]7.34 [3.41, 9.80]0% [0%, 0%]0%0%-3.40-1.132026-08-29 → 2026-08-30
tmax12Znearest90d2 1 QC6.61 [3.41, 9.80]3.20-6.61 [-9.80, -3.41]7.34 [3.41, 9.80]0% [0%, 0%]0%0%-3.40-1.132026-08-29 → 2026-08-30
tmax12Znearest365d2 1 QC6.61 [3.41, 9.80]3.20-6.61 [-9.80, -3.41]7.34 [3.41, 9.80]0% [0%, 0%]0%0%-3.40-1.132026-08-29 → 2026-08-30
tmax12Znearestall2 1 QC6.61 [3.41, 9.80]3.20-6.61 [-9.80, -3.41]7.34 [3.41, 9.80]0% [0%, 0%]0%0%-3.40-1.132026-08-29 → 2026-08-30
tmin00Zbilinear30d1 1 QC1.26 [1.26, 1.26]0.00-1.26 [-1.26, -1.26]1.26 [1.26, 1.26]0% [0%, 0%]100%100%+0.37—2026-08-30 → 2026-08-30
tmin00Zbilinear90d1 1 QC1.26 [1.26, 1.26]0.00-1.26 [-1.26, -1.26]1.26 [1.26, 1.26]0% [0%, 0%]100%100%+0.37—2026-08-30 → 2026-08-30
tmin00Zbilinear365d1 1 QC1.26 [1.26, 1.26]0.00-1.26 [-1.26, -1.26]1.26 [1.26, 1.26]0% [0%, 0%]100%100%+0.37—2026-08-30 → 2026-08-30
tmin00Zbilinearall1 1 QC1.26 [1.26, 1.26]0.00-1.26 [-1.26, -1.26]1.26 [1.26, 1.26]0% [0%, 0%]100%100%+0.37—2026-08-30 → 2026-08-30
tmin00Znearest30d1 1 QC1.62 [1.62, 1.62]0.00-1.62 [-1.62, -1.62]1.62 [1.62, 1.62]0% [0%, 0%]100%100%+0.19—2026-08-30 → 2026-08-30
tmin00Znearest90d1 1 QC1.62 [1.62, 1.62]0.00-1.62 [-1.62, -1.62]1.62 [1.62, 1.62]0% [0%, 0%]100%100%+0.19—2026-08-30 → 2026-08-30
tmin00Znearest365d1 1 QC1.62 [1.62, 1.62]0.00-1.62 [-1.62, -1.62]1.62 [1.62, 1.62]0% [0%, 0%]100%100%+0.19—2026-08-30 → 2026-08-30
tmin00Znearestall1 1 QC1.62 [1.62, 1.62]0.00-1.62 [-1.62, -1.62]1.62 [1.62, 1.62]0% [0%, 0%]100%100%+0.19—2026-08-30 → 2026-08-30
tmin12Zbilinear30d2 1 QC1.92 [1.49, 2.36]1.92-0.43 [-2.36, 1.49]1.97 [1.49, 2.36]0% [0%, 0%]50%100%+0.62+0.362026-08-29 → 2026-08-30
tmin12Zbilinear90d2 1 QC1.92 [1.49, 2.36]1.92-0.43 [-2.36, 1.49]1.97 [1.49, 2.36]0% [0%, 0%]50%100%+0.62+0.362026-08-29 → 2026-08-30
tmin12Zbilinear365d2 1 QC1.92 [1.49, 2.36]1.92-0.43 [-2.36, 1.49]1.97 [1.49, 2.36]0% [0%, 0%]50%100%+0.62+0.362026-08-29 → 2026-08-30
tmin12Zbilinearall2 1 QC1.92 [1.49, 2.36]1.92-0.43 [-2.36, 1.49]1.97 [1.49, 2.36]0% [0%, 0%]50%100%+0.62+0.362026-08-29 → 2026-08-30
tmin12Znearest30d2 1 QC2.29 [2.15, 2.44]2.29-0.15 [-2.44, 2.15]2.30 [2.15, 2.44]0% [0%, 0%]0%100%+0.54+0.242026-08-29 → 2026-08-30
tmin12Znearest90d2 1 QC2.29 [2.15, 2.44]2.29-0.15 [-2.44, 2.15]2.30 [2.15, 2.44]0% [0%, 0%]0%100%+0.54+0.242026-08-29 → 2026-08-30
tmin12Znearest365d2 1 QC2.29 [2.15, 2.44]2.29-0.15 [-2.44, 2.15]2.30 [2.15, 2.44]0% [0%, 0%]0%100%+0.54+0.242026-08-29 → 2026-08-30
tmin12Znearestall2 1 QC2.29 [2.15, 2.44]2.29-0.15 [-2.44, 2.15]2.30 [2.15, 2.44]0% [0%, 0%]0%100%+0.54+0.242026-08-29 → 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 Pangu-Weather (GFS init) at KMSP, lead day 1, 00Z bilinear tmax+1+0.50-0.5-12026-08-30: -0.54 °F2026-08-30°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 (1 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-0.54

Error distribution

Distribution of the signed daily error in °F for Pangu-Weather (GFS init) at KMSP, lead day 1-1 to -0.9 °F: 0 days-0.9 to -0.8 °F: 0 days-0.8 to -0.7 °F: 0 days-0.7 to -0.6 °F: 0 days-0.6 to -0.5 °F: 1 day-0.5 to -0.4 °F: 0 days-0.4 to -0.3 °F: 0 days-0.3 to -0.2 °F: 0 days-0.2 to -0.1 °F: 0 days-0.1 to 0 °F: 0 days0 to 0.1 °F: 0 days0.1 to 0.2 °F: 0 days0.2 to 0.3 °F: 0 days0.3 to 0.4 °F: 0 days0.4 to 0.5 °F: 0 days0.5 to 0.6 °F: 0 days0.6 to 0.7 °F: 0 days0.7 to 0.8 °F: 0 days0.8 to 0.9 °F: 0 days0.9 to 1 °F: 0 daysdashed: P50 |e| 0.54 · P90 |e| 0.54 °F-10+1 °Fn = 1 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
-1.00-0.900
-0.90-0.800
-0.80-0.700
-0.70-0.600
-0.60-0.501
-0.50-0.400
-0.40-0.300
-0.30-0.200
-0.20-0.100
-0.10+0.000
+0.00+0.100
+0.10+0.200
+0.20+0.300
+0.30+0.400
+0.40+0.500
+0.50+0.600
+0.60+0.700
+0.70+0.800
+0.80+0.900
+0.90+1.000

Month by month

00Z bilinear daily maximum, newest first.

Monthn MAE °FBias °F
2026-0810.54 -0.54

Availability

ModelScored period DaysCoverage
Pangu-Weather (GFS init)2026-08-30 → 2026-08-30 1
Pangu-Weather (GFS init)2026-08-30 → 2026-08-30 1
Pangu-Weather (GFS init)2026-08-29 → 2026-08-30 2
Pangu-Weather (GFS init)2026-08-29 → 2026-08-30 2

Compared with other models

Paired bootstrap on the days both models cover (90d, 00Z, bilinear, daily maximum). Negative means Pangu-Weather (GFS init) has the lower MAE. "Distinguishable" means the 95 % interval excludes zero.

Other modelCommon days MAE difference °FDistinguishable
ECMWF AIFS Single 1 -3.13 [-3.13, -3.13] yes
Aurora (GFS init) 1 -7.57 [-7.57, -7.57] yes
Aurora (IFS init) 1 -5.58 [-5.58, -5.58] yes
FourCastNet v2 (GFS init) 1 -5.46 [-5.46, -5.46] yes
FourCastNet v2 (IFS init) 1 -5.58 [-5.58, -5.58] yes
NCEP GFS 1 -2.93 [-2.93, -2.93] yes
GraphCast (GFS init) 1 -7.06 [-7.06, -7.06] yes
GraphCast (IFS init) 1 -5.49 [-5.49, -5.49] yes
ECMWF IFS HRES 1 -2.90 [-2.90, -2.90] yes
Pangu-Weather (IFS init) 1 -1.66 [-1.66, -1.66] yes
Persistence (baseline) 1 -2.46 [-2.46, -2.46] yes

Cite this page

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

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