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 2

KPHL · aifs_single · lead 2

Target day = initialization date + 2 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
tmax00Zbilinear30d28 1 QC2.75 [2.12, 3.50]1.98-2.18 [-3.27, -1.30]3.28 [2.57, 3.97]21% [11%, 30%]36%50%+0.01+0.292026-08-03 → 2026-08-30
tmax00Zbilinear90d28 1 QC2.75 [2.01, 3.74]1.98-2.18 [-3.54, -1.23]3.28 [2.41, 4.20]21% [8%, 29%]36%50%+0.01+0.292026-08-03 → 2026-08-30
tmax00Zbilinear365d28 1 QC2.75 [1.93, 3.71]1.98-2.18 [-3.59, -1.17]3.28 [2.34, 4.19]21% [9%, 29%]36%50%+0.01+0.292026-08-03 → 2026-08-30
tmax00Zbilinearall28 1 QC2.75 [1.95, 3.94]1.98-2.18 [-3.76, -1.21]3.28 [2.32, 4.36]21% [7%, 29%]36%50%+0.01+0.292026-08-03 → 2026-08-30
tmax00Znearest30d28 1 QC2.38 [1.82, 3.06]2.04-1.50 [-2.69, -0.53]2.95 [2.28, 3.59]25% [12%, 36%]46%68%+0.14+0.272026-08-03 → 2026-08-30
tmax00Znearest90d28 1 QC2.38 [1.73, 3.27]2.04-1.50 [-2.94, -0.44]2.95 [2.14, 3.78]25% [10%, 34%]46%68%+0.14+0.272026-08-03 → 2026-08-30
tmax00Znearest365d28 1 QC2.38 [1.70, 3.24]2.04-1.50 [-3.03, -0.39]2.95 [2.04, 3.75]25% [10%, 36%]46%68%+0.14+0.272026-08-03 → 2026-08-30
tmax00Znearestall28 1 QC2.38 [1.67, 3.46]2.04-1.50 [-3.21, -0.44]2.95 [2.05, 3.95]25% [8%, 36%]46%68%+0.14+0.272026-08-03 → 2026-08-30
tmax12Zbilinear30d28 1 QC2.76 [2.12, 3.52]1.82-2.58 [-3.51, -1.80]3.39 [2.61, 4.16]25% [11%, 39%]46%57%+0.01+0.352026-08-03 → 2026-08-30
tmax12Zbilinear90d28 1 QC2.76 [2.05, 3.65]1.82-2.58 [-3.63, -1.67]3.39 [2.50, 4.27]25% [10%, 40%]46%57%+0.01+0.352026-08-03 → 2026-08-30
tmax12Zbilinear365d28 1 QC2.76 [1.99, 3.72]1.82-2.58 [-3.72, -1.60]3.39 [2.50, 4.35]25% [9%, 43%]46%57%+0.01+0.352026-08-03 → 2026-08-30
tmax12Zbilinearall28 1 QC2.76 [2.01, 3.80]1.82-2.58 [-3.80, -1.62]3.39 [2.45, 4.39]25% [8%, 42%]46%57%+0.01+0.352026-08-03 → 2026-08-30
tmax12Znearest30d28 1 QC2.33 [1.73, 3.04]1.91-1.91 [-2.91, -1.03]3.00 [2.25, 3.74]32% [19%, 43%]54%68%+0.16+0.312026-08-03 → 2026-08-30
tmax12Znearest90d28 1 QC2.33 [1.72, 3.16]1.91-1.91 [-3.06, -0.93]3.00 [2.17, 3.85]32% [17%, 44%]54%68%+0.16+0.312026-08-03 → 2026-08-30
tmax12Znearest365d28 1 QC2.33 [1.65, 3.21]1.91-1.91 [-3.18, -0.84]3.00 [2.12, 3.93]32% [17%, 46%]54%68%+0.16+0.312026-08-03 → 2026-08-30
tmax12Znearestall28 1 QC2.33 [1.65, 3.29]1.91-1.91 [-3.24, -0.87]3.00 [2.09, 3.99]32% [14%, 46%]54%68%+0.16+0.312026-08-03 → 2026-08-30
tmin00Zbilinear30d28 1 QC1.96 [1.58, 2.33]1.95+0.25 [-0.33, 0.88]2.27 [1.84, 2.63]25% [13%, 40%]54%79%+0.44+0.462026-08-03 → 2026-08-30
tmin00Zbilinear90d28 1 QC1.96 [1.53, 2.36]1.95+0.25 [-0.30, 0.94]2.27 [1.79, 2.65]25% [11%, 39%]54%79%+0.44+0.462026-08-03 → 2026-08-30
tmin00Zbilinear365d28 1 QC1.96 [1.54, 2.37]1.95+0.25 [-0.33, 1.00]2.27 [1.79, 2.66]25% [11%, 39%]54%79%+0.44+0.462026-08-03 → 2026-08-30
tmin00Zbilinearall28 1 QC1.96 [1.54, 2.37]1.95+0.25 [-0.33, 0.96]2.27 [1.76, 2.66]25% [11%, 42%]54%79%+0.44+0.462026-08-03 → 2026-08-30
tmin00Znearest30d28 1 QC2.04 [1.67, 2.41]1.96+0.79 [0.27, 1.36]2.37 [1.96, 2.72]25% [10%, 39%]50%75%+0.42+0.452026-08-03 → 2026-08-30
tmin00Znearest90d28 1 QC2.04 [1.63, 2.45]1.96+0.79 [0.29, 1.44]2.37 [1.94, 2.76]25% [7%, 42%]50%75%+0.42+0.452026-08-03 → 2026-08-30
tmin00Znearest365d28 1 QC2.04 [1.64, 2.45]1.96+0.79 [0.27, 1.46]2.37 [1.94, 2.79]25% [6%, 43%]50%75%+0.42+0.452026-08-03 → 2026-08-30
tmin00Znearestall28 1 QC2.04 [1.64, 2.43]1.96+0.79 [0.27, 1.44]2.37 [1.94, 2.75]25% [8%, 43%]50%75%+0.42+0.452026-08-03 → 2026-08-30
tmin12Zbilinear30d28 1 QC1.73 [1.21, 2.27]1.70+0.38 [-0.07, 0.91]2.09 [1.50, 2.59]36% [20%, 54%]57%82%+0.51+0.522026-08-03 → 2026-08-30
tmin12Zbilinear90d28 1 QC1.73 [1.12, 2.30]1.70+0.38 [-0.06, 0.95]2.09 [1.38, 2.61]36% [20%, 56%]57%82%+0.51+0.522026-08-03 → 2026-08-30
tmin12Zbilinear365d28 1 QC1.73 [1.08, 2.35]1.70+0.38 [-0.07, 1.00]2.09 [1.29, 2.66]36% [18%, 56%]57%82%+0.51+0.522026-08-03 → 2026-08-30
tmin12Zbilinearall28 1 QC1.73 [1.14, 2.30]1.70+0.38 [-0.05, 0.92]2.09 [1.36, 2.61]36% [19%, 57%]57%82%+0.51+0.522026-08-03 → 2026-08-30
tmin12Znearest30d28 1 QC1.87 [1.38, 2.43]1.71+0.93 [0.51, 1.45]2.23 [1.65, 2.76]29% [13%, 44%]57%82%+0.47+0.522026-08-03 → 2026-08-30
tmin12Znearest90d28 1 QC1.87 [1.30, 2.46]1.71+0.93 [0.55, 1.47]2.23 [1.57, 2.82]29% [12%, 45%]57%82%+0.47+0.522026-08-03 → 2026-08-30
tmin12Znearest365d28 1 QC1.87 [1.28, 2.53]1.71+0.93 [0.54, 1.51]2.23 [1.51, 2.84]29% [12%, 45%]57%82%+0.47+0.522026-08-03 → 2026-08-30
tmin12Znearestall28 1 QC1.87 [1.32, 2.46]1.71+0.93 [0.54, 1.46]2.23 [1.56, 2.79]29% [11%, 45%]57%82%+0.47+0.522026-08-03 → 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 2, 00Z bilinear tmax+10+50-5-102026-08-03: -6.61 °F2026-08-04: -5.33 °F2026-08-05: -3.27 °F2026-08-06: -3.03 °F2026-08-07: -5.08 °F2026-08-08: -0.68 °F2026-08-09: -1.05 °F2026-08-10: +0.37 °F2026-08-11: +2.08 °F2026-08-12: -4.21 °F2026-08-13: -1.41 °F2026-08-14: -3.59 °F2026-08-15: -2.89 °F2026-08-16: +4.06 °F2026-08-17: -0.57 °F2026-08-18: -0.78 °F2026-08-19: -3.05 °F2026-08-20: -4.15 °F2026-08-21: -4.75 °F2026-08-22: -5.95 °F2026-08-23: -2 °F2026-08-24: -3.21 °F2026-08-25: +0.09 °F2026-08-26: -2.28 °F2026-08-27: -0.32 °F2026-08-28: -1.73 °F2026-08-29: +1.29 °F2026-08-30: -3.11 °F2026-08-032026-08-30°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 (28 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-3.11
2026-08-29+1.29
2026-08-28-1.73
2026-08-27-0.32
2026-08-26-2.28
2026-08-25+0.09
2026-08-24-3.21
2026-08-23-2.00
2026-08-22-5.95
2026-08-21-4.75
2026-08-20-4.15
2026-08-19-3.05
2026-08-18-0.78
2026-08-17-0.57
2026-08-16+4.06
2026-08-15-2.89
2026-08-14-3.59
2026-08-13-1.41
2026-08-12-4.21
2026-08-11+2.08
2026-08-10+0.37
2026-08-09-1.05
2026-08-08-0.68
2026-08-07-5.08
2026-08-06-3.03
2026-08-05-3.27
2026-08-04-5.33
2026-08-03-6.61

Error distribution

Distribution of the signed daily error in °F for ECMWF AIFS Single at KPHL, lead day 2-10 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: 3 days-5 to -4 °F: 3 days-4 to -3 °F: 6 days-3 to -2 °F: 3 days-2 to -1 °F: 3 days-1 to 0 °F: 4 days0 to 1 °F: 2 days1 to 2 °F: 1 day2 to 3 °F: 1 day3 to 4 °F: 0 days4 to 5 °F: 1 day5 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| 2.96 · P90 |e| 5.16 °F-100+10 °Fn = 28 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
-6.00-5.003
-5.00-4.003
-4.00-3.006
-3.00-2.003
-2.00-1.003
-1.00+0.004
+0.00+1.002
+1.00+2.001
+2.00+3.001
+3.00+4.000
+4.00+5.001
+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
2026-08282.75 -2.18

Availability

ModelScored period DaysCoverage
ECMWF AIFS Single2026-08-03 → 2026-08-30 28
ECMWF AIFS Single2026-08-03 → 2026-08-30 28
ECMWF AIFS Single2026-08-03 → 2026-08-30 28
ECMWF AIFS Single2026-08-03 → 2026-08-30 28

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 (IFS init) 1 -1.37 [-1.37, -1.37] yes
FourCastNet v2 (IFS init) 1 -1.48 [-1.48, -1.48] yes
NCEP GFS 28 -0.85 [-1.62, 0.01] no
GraphCast (IFS init) 26 -2.00 [-2.46, -1.51] yes
ECMWF IFS HRES 22 -0.84 [-1.65, -0.24] yes
Pangu-Weather (IFS init) 1 -0.12 [-0.12, -0.12] yes
Persistence (baseline) 28 -0.04 [-0.71, 1.24] no

Cite this page

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

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

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