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

Philadelphia Intl · ECMWF AIFS Single · lead day 0

KPHL · 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 QC2.32 [1.75, 2.97]1.16-2.27 [-2.95, -1.72]2.73 [2.08, 3.31]20% [7%, 33%]40%77%——2026-08-01 → 2026-08-30
tmax00Zbilinear90d30 1 QC2.32 [1.76, 3.10]1.16-2.27 [-3.09, -1.72]2.73 [2.08, 3.43]20% [6%, 32%]40%77%——2026-08-01 → 2026-08-30
tmax00Zbilinear365d30 1 QC2.32 [1.73, 3.11]1.16-2.27 [-3.07, -1.68]2.73 [2.02, 3.40]20% [0%, 32%]40%77%——2026-08-01 → 2026-08-30
tmax00Zbilinearall30 1 QC2.32 [1.74, 3.16]1.16-2.27 [-3.12, -1.68]2.73 [2.09, 3.50]20% [0%, 33%]40%77%——2026-08-01 → 2026-08-30
tmax00Znearest30d30 1 QC1.84 [1.26, 2.42]1.23-1.59 [-2.31, -0.93]2.25 [1.57, 2.80]33% [13%, 50%]70%83%——2026-08-01 → 2026-08-30
tmax00Znearest90d30 1 QC1.84 [1.28, 2.55]1.23-1.59 [-2.43, -0.91]2.25 [1.56, 2.91]33% [11%, 48%]70%83%——2026-08-01 → 2026-08-30
tmax00Znearest365d30 1 QC1.84 [1.20, 2.53]1.23-1.59 [-2.44, -0.86]2.25 [1.39, 2.88]33% [12%, 49%]70%83%——2026-08-01 → 2026-08-30
tmax00Znearestall30 1 QC1.84 [1.26, 2.62]1.23-1.59 [-2.48, -0.88]2.25 [1.54, 2.97]33% [9%, 49%]70%83%——2026-08-01 → 2026-08-30
tmin00Zbilinear30d30 1 QC1.57 [1.35, 1.80]1.52-0.35 [-0.79, 0.06]1.85 [1.64, 2.09]43% [27%, 57%]63%93%——2026-08-01 → 2026-08-30
tmin00Zbilinear90d30 1 QC1.57 [1.37, 1.83]1.52-0.35 [-0.93, 0.07]1.85 [1.66, 2.15]43% [27%, 58%]63%93%——2026-08-01 → 2026-08-30
tmin00Zbilinear365d30 1 QC1.57 [1.35, 1.84]1.52-0.35 [-0.97, 0.09]1.85 [1.63, 2.16]43% [26%, 61%]63%93%——2026-08-01 → 2026-08-30
tmin00Zbilinearall30 1 QC1.57 [1.34, 1.86]1.52-0.35 [-0.89, 0.04]1.85 [1.62, 2.16]43% [27%, 60%]63%93%——2026-08-01 → 2026-08-30
tmin00Znearest30d30 1 QC1.50 [1.24, 1.79]1.52+0.12 [-0.32, 0.50]1.82 [1.57, 2.05]40% [23%, 53%]67%90%——2026-08-01 → 2026-08-30
tmin00Znearest90d30 1 QC1.50 [1.25, 1.82]1.52+0.12 [-0.43, 0.51]1.82 [1.58, 2.08]40% [23%, 55%]67%90%——2026-08-01 → 2026-08-30
tmin00Znearest365d30 1 QC1.50 [1.23, 1.84]1.52+0.12 [-0.47, 0.54]1.82 [1.58, 2.10]40% [21%, 56%]67%90%——2026-08-01 → 2026-08-30
tmin00Znearestall30 1 QC1.50 [1.23, 1.84]1.52+0.12 [-0.41, 0.49]1.82 [1.55, 2.11]40% [22%, 55%]67%90%——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 KPHL, lead day 0, 00Z bilinear tmax+10+50-5-102026-08-01: -2.41 °F2026-08-02: -3.39 °F2026-08-03: -5.68 °F2026-08-04: -4.01 °F2026-08-05: -4.07 °F2026-08-06: -1.83 °F2026-08-07: -2.74 °F2026-08-08: +0.23 °F2026-08-09: -1.06 °F2026-08-10: -0.22 °F2026-08-11: -2.56 °F2026-08-12: -2.64 °F2026-08-13: -0.92 °F2026-08-14: -2.3 °F2026-08-15: -1.72 °F2026-08-16: -0.38 °F2026-08-17: -1.87 °F2026-08-18: -1.57 °F2026-08-19: -2.99 °F2026-08-20: -3.58 °F2026-08-21: -4.86 °F2026-08-22: -2.91 °F2026-08-23: -1.24 °F2026-08-24: -2.17 °F2026-08-25: +0.4 °F2026-08-26: -2.27 °F2026-08-27: -0.02 °F2026-08-28: -5.01 °F2026-08-29: -2.02 °F2026-08-30: -2.43 °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
2026-08-30-2.43
2026-08-29-2.02
2026-08-28-5.01
2026-08-27-0.02
2026-08-26-2.27
2026-08-25+0.40
2026-08-24-2.17
2026-08-23-1.24
2026-08-22-2.91
2026-08-21-4.86
2026-08-20-3.58
2026-08-19-2.99
2026-08-18-1.57
2026-08-17-1.87
2026-08-16-0.38
2026-08-15-1.72
2026-08-14-2.30
2026-08-13-0.92
2026-08-12-2.64
2026-08-11-2.56
2026-08-10-0.22
2026-08-09-1.06
2026-08-08+0.23
2026-08-07-2.74
2026-08-06-1.83
2026-08-05-4.07
2026-08-04-4.01
2026-08-03-5.68
2026-08-02-3.39
2026-08-01-2.41

Error distribution

Distribution of the signed daily error in °F for ECMWF AIFS Single at KPHL, 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: 2 days-5 to -4 °F: 3 days-4 to -3 °F: 2 days-3 to -2 °F: 11 days-2 to -1 °F: 6 days-1 to 0 °F: 4 days0 to 1 °F: 2 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| 2.28 · P90 |e| 4.15 °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
-7.00-6.000
-6.00-5.002
-5.00-4.003
-4.00-3.002
-3.00-2.0011
-2.00-1.006
-1.00+0.004
+0.00+1.002
+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
2026-08302.32 -2.27

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 -2.78 [-3.56, -2.00] yes
Aurora (IFS init) 3 -1.48 [-1.89, -0.68] yes
FourCastNet v2 (GFS init) 2 -1.71 [-4.19, 0.77] no
FourCastNet v2 (IFS init) 3 -1.96 [-3.97, -0.95] yes
NCEP GFS 30 -0.48 [-1.53, 0.47] no
GraphCast (GFS init) 2 -3.03 [-3.49, -2.56] yes
GraphCast (IFS init) 28 -2.36 [-2.64, -1.98] yes
ECMWF IFS HRES 24 -0.69 [-1.16, -0.32] yes
Pangu-Weather (GFS init) 2 +0.14 [-0.88, 1.16] no
Pangu-Weather (IFS init) 3 +0.47 [-0.51, 0.96] no

Cite this page

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

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