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

Miami Intl · Pangu-Weather (IFS init) · lead day 0

KMIA · 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 QC4.65 [3.82, 5.06]0.68-4.65 [-5.06, -3.82]4.71 [3.82, 5.10]0% [0%, 0%]0%0%——2026-08-28 → 2026-08-30
tmax00Zbilinear90d3 2 QC4.65 [3.82, 5.06]0.68-4.65 [-5.06, -3.82]4.71 [3.82, 5.10]0% [0%, 0%]0%0%——2026-08-28 → 2026-08-30
tmax00Zbilinear365d3 2 QC4.65 [3.82, 5.06]0.68-4.65 [-5.06, -3.82]4.71 [3.82, 5.10]0% [0%, 0%]0%0%——2026-08-28 → 2026-08-30
tmax00Zbilinearall3 2 QC4.65 [3.82, 5.06]0.68-4.65 [-5.06, -3.82]4.71 [3.82, 5.10]0% [0%, 0%]0%0%——2026-08-28 → 2026-08-30
tmax00Znearest30d3 2 QC4.97 [4.19, 5.36]0.70-4.97 [-5.36, -4.19]5.03 [4.19, 5.40]0% [0%, 0%]0%0%——2026-08-28 → 2026-08-30
tmax00Znearest90d3 2 QC4.97 [4.19, 5.36]0.70-4.97 [-5.36, -4.19]5.03 [4.19, 5.40]0% [0%, 0%]0%0%——2026-08-28 → 2026-08-30
tmax00Znearest365d3 2 QC4.97 [4.19, 5.36]0.70-4.97 [-5.36, -4.19]5.03 [4.19, 5.40]0% [0%, 0%]0%0%——2026-08-28 → 2026-08-30
tmax00Znearestall3 2 QC4.97 [4.19, 5.36]0.70-4.97 [-5.36, -4.19]5.03 [4.19, 5.40]0% [0%, 0%]0%0%——2026-08-28 → 2026-08-30
tmin00Zbilinear30d3 2 QC1.32 [0.09, 1.94]1.38+1.27 [-0.09, 1.94]1.95 [0.09, 2.39]67% [50%, 100%]67%67%——2026-08-28 → 2026-08-30
tmin00Zbilinear90d3 2 QC1.32 [0.09, 1.94]1.38+1.27 [-0.09, 1.94]1.95 [0.09, 2.39]67% [50%, 100%]67%67%——2026-08-28 → 2026-08-30
tmin00Zbilinear365d3 2 QC1.32 [0.09, 1.94]1.38+1.27 [-0.09, 1.94]1.95 [0.09, 2.39]67% [50%, 100%]67%67%——2026-08-28 → 2026-08-30
tmin00Zbilinearall3 2 QC1.32 [0.09, 1.94]1.38+1.27 [-0.09, 1.94]1.95 [0.09, 2.39]67% [50%, 100%]67%67%——2026-08-28 → 2026-08-30
tmin00Znearest30d3 2 QC1.86 [0.32, 2.63]1.23+1.86 [0.32, 2.63]2.33 [0.32, 2.84]33% [0%, 100%]67%67%——2026-08-28 → 2026-08-30
tmin00Znearest90d3 2 QC1.86 [0.32, 2.63]1.23+1.86 [0.32, 2.63]2.33 [0.32, 2.84]33% [0%, 100%]67%67%——2026-08-28 → 2026-08-30
tmin00Znearest365d3 2 QC1.86 [0.32, 2.63]1.23+1.86 [0.32, 2.63]2.33 [0.32, 2.84]33% [0%, 100%]67%67%——2026-08-28 → 2026-08-30
tmin00Znearestall3 2 QC1.86 [0.32, 2.63]1.23+1.86 [0.32, 2.63]2.33 [0.32, 2.84]33% [0%, 100%]67%67%——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 KMIA, lead day 0, 00Z bilinear tmax+10+50-5-102026-08-28: -4.46 °F2026-08-29: -5.67 °F2026-08-30: -3.82 °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
2026-08-30-3.82
2026-08-29-5.67
2026-08-28-4.46

Error distribution

Distribution of the signed daily error in °F for Pangu-Weather (IFS init) at KMIA, 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: 0 days-6 to -5 °F: 1 day-5 to -4 °F: 1 day-4 to -3 °F: 1 day-3 to -2 °F: 0 days-2 to -1 °F: 0 days-1 to 0 °F: 0 days0 to 1 °F: 0 days1 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| 4.46 · P90 |e| 5.43 °F-100+10 °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
-10.00-9.000
-9.00-8.000
-8.00-7.000
-7.00-6.000
-6.00-5.001
-5.00-4.001
-4.00-3.001
-3.00-2.000
-2.00-1.000
-1.00+0.000
+0.00+1.000
+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
2026-0834.65 -4.65

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 -0.87 [-1.27, -0.67] yes
Aurora (GFS init) 2 -2.21 [-3.63, -0.79] yes
Aurora (IFS init) 3 -2.28 [-2.40, -2.21] yes
FourCastNet v2 (GFS init) 2 +0.20 [-1.13, 1.54] no
FourCastNet v2 (IFS init) 3 -0.43 [-1.31, 0.00] no
NCEP GFS 3 +3.21 [2.10, 3.77] yes
GraphCast (GFS init) 2 -1.30 [-2.69, 0.09] no
GraphCast (IFS init) 3 -1.28 [-1.82, -0.18] yes
ECMWF IFS HRES 3 -0.67 [-5.94, 2.45] no
Pangu-Weather (GFS init) 2 -1.09 [-2.58, 0.41] no

Cite this page

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

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KMIA (Miami Intl), 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/KMIA/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