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

All stations (mean of daily station errors) · Pangu-Weather (IFS init) · lead day 0

ALL · pangu_ifs · 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, 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, 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
tmax00Zbilinear30d3 2 QC3.62 [3.40, 3.73]0.34-3.08 [-3.39, -2.57]4.04 [3.71, 4.20]12% [9%, 18%]18%38%2026-08-28 → 2026-08-30
tmax00Zbilinear90d3 2 QC3.62 [3.40, 3.73]0.34-3.08 [-3.39, -2.57]4.04 [3.71, 4.20]12% [9%, 18%]18%38%2026-08-28 → 2026-08-30
tmax00Zbilinear365d3 2 QC3.62 [3.40, 3.73]0.34-3.08 [-3.39, -2.57]4.04 [3.71, 4.20]12% [9%, 18%]18%38%2026-08-28 → 2026-08-30
tmax00Zbilinearall3 2 QC3.62 [3.40, 3.73]0.34-3.08 [-3.39, -2.57]4.04 [3.71, 4.20]12% [9%, 18%]18%38%2026-08-28 → 2026-08-30
tmax00Znearest30d3 2 QC3.81 [3.60, 3.91]0.29-3.19 [-3.44, -2.76]4.29 [3.94, 4.46]9% [4%, 14%]16%40%2026-08-28 → 2026-08-30
tmax00Znearest90d3 2 QC3.81 [3.60, 3.91]0.29-3.19 [-3.44, -2.76]4.29 [3.94, 4.46]9% [4%, 14%]16%40%2026-08-28 → 2026-08-30
tmax00Znearest365d3 2 QC3.81 [3.60, 3.91]0.29-3.19 [-3.44, -2.76]4.29 [3.94, 4.46]9% [4%, 14%]16%40%2026-08-28 → 2026-08-30
tmax00Znearestall3 2 QC3.81 [3.60, 3.91]0.29-3.19 [-3.44, -2.76]4.29 [3.94, 4.46]9% [4%, 14%]16%40%2026-08-28 → 2026-08-30
tmin00Zbilinear30d3 2 QC2.07 [1.86, 2.34]0.73+0.60 [-0.50, 1.15]2.64 [2.48, 2.73]34% [18%, 43%]53%72%2026-08-28 → 2026-08-30
tmin00Zbilinear90d3 2 QC2.07 [1.86, 2.34]0.73+0.60 [-0.50, 1.15]2.64 [2.48, 2.73]34% [18%, 43%]53%72%2026-08-28 → 2026-08-30
tmin00Zbilinear365d3 2 QC2.07 [1.86, 2.34]0.73+0.60 [-0.50, 1.15]2.64 [2.48, 2.73]34% [18%, 43%]53%72%2026-08-28 → 2026-08-30
tmin00Zbilinearall3 2 QC2.07 [1.86, 2.34]0.73+0.60 [-0.50, 1.15]2.64 [2.48, 2.73]34% [18%, 43%]53%72%2026-08-28 → 2026-08-30
tmin00Znearest30d3 2 QC2.13 [1.98, 2.32]0.75+0.50 [-0.63, 1.06]2.74 [2.64, 2.79]34% [23%, 43%]57%72%2026-08-28 → 2026-08-30
tmin00Znearest90d3 2 QC2.13 [1.98, 2.32]0.75+0.50 [-0.63, 1.06]2.74 [2.64, 2.79]34% [23%, 43%]57%72%2026-08-28 → 2026-08-30
tmin00Znearest365d3 2 QC2.13 [1.98, 2.32]0.75+0.50 [-0.63, 1.06]2.74 [2.64, 2.79]34% [23%, 43%]57%72%2026-08-28 → 2026-08-30
tmin00Znearestall3 2 QC2.13 [1.98, 2.32]0.75+0.50 [-0.63, 1.06]2.74 [2.64, 2.79]34% [23%, 43%]57%72%2026-08-28 → 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 (IFS init) at ALL, lead day 0, 00Z bilinear tmax+5+2.50-2.5-52026-08-28: -3.39 °F2026-08-29: -3.27 °F2026-08-30: -2.57 °F2026-08-282026-08-30°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 (3 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-2.57
2026-08-29-3.27
2026-08-28-3.39

Error distribution

Distribution of the signed daily error in °F for Pangu-Weather (IFS init) at ALL, lead day 0-5 to -4.5 °F: 0 days-4.5 to -4 °F: 0 days-4 to -3.5 °F: 0 days-3.5 to -3 °F: 2 days-3 to -2.5 °F: 1 day-2.5 to -2 °F: 0 days-2 to -1.5 °F: 0 days-1.5 to -1 °F: 0 days-1 to -0.5 °F: 0 days-0.5 to 0 °F: 0 days0 to 0.5 °F: 0 days0.5 to 1 °F: 0 days1 to 1.5 °F: 0 days1.5 to 2 °F: 0 days2 to 2.5 °F: 0 days2.5 to 3 °F: 0 days3 to 3.5 °F: 0 days3.5 to 4 °F: 0 days4 to 4.5 °F: 0 days4.5 to 5 °F: 0 daysdashed: P50 |e| 3.27 · P90 |e| 3.36 °F-50+5 °Fn = 3 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
-4.00-3.500
-3.50-3.002
-3.00-2.501
-2.50-2.000
-2.00-1.500
-1.50-1.000
-1.00-0.500
-0.50+0.000
+0.00+0.500
+0.50+1.000
+1.00+1.500
+1.50+2.000
+2.00+2.500
+2.50+3.000
+3.00+3.500
+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
2026-0833.08 -3.08

Availability

ModelScored period DaysCoverage
Pangu-Weather (IFS init)2026-08-28 → 2026-08-30 3
Pangu-Weather (IFS init)2026-08-28 → 2026-08-30 3

Compared with other models

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

Other modelCommon days MAE difference °FDistinguishable
ECMWF AIFS Single 3 -0.06 [-0.52, 0.26] no
Aurora (GFS init) 2 -2.14 [-2.14, -2.13] yes
Aurora (IFS init) 3 -1.46 [-1.75, -1.05] yes
FourCastNet v2 (GFS init) 2 -0.70 [-0.81, -0.58] yes
FourCastNet v2 (IFS init) 3 -0.97 [-1.88, -0.52] yes
NCEP GFS 3 +0.80 [0.74, 0.94] yes
GraphCast (GFS init) 2 -1.94 [-1.95, -1.93] yes
GraphCast (IFS init) 3 -1.45 [-1.79, -1.04] yes
ECMWF IFS HRES 3 -0.19 [-0.54, -0.01] yes
Pangu-Weather (GFS init) 2 -0.07 [-0.21, 0.07] no

Cite this page

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

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: ALL (All stations (mean of daily station errors)), model pangu_ifs, 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/ALL/model/pangu_ifs/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