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 5

KPHL · aifs_single · lead 5

Target day = initialization date + 5 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
tmax00Zbilinear30d25 1 QC2.95 [2.38, 3.44]1.95-2.47 [-3.23, -1.59]3.50 [2.76, 4.10]16% [6%, 27%]36%48%+0.20+0.462026-08-06 → 2026-08-30
tmax00Zbilinear90d25 1 QC2.95 [2.25, 3.39]1.95-2.47 [-3.20, -1.63]3.50 [2.50, 4.05]16% [5%, 29%]36%48%+0.20+0.462026-08-06 → 2026-08-30
tmax00Zbilinear365d25 1 QC2.95 [2.31, 3.45]1.95-2.47 [-3.26, -1.54]3.50 [2.58, 4.11]16% [0%, 29%]36%48%+0.20+0.462026-08-06 → 2026-08-30
tmax00Zbilinearall25 1 QC2.95 [2.27, 3.42]1.95-2.47 [-3.28, -1.45]3.50 [2.49, 4.09]16% [0%, 29%]36%48%+0.20+0.462026-08-06 → 2026-08-30
tmax00Znearest30d25 1 QC2.57 [2.02, 2.98]1.96-1.82 [-2.55, -0.98]3.07 [2.42, 3.54]24% [14%, 35%]40%64%+0.30+0.452026-08-06 → 2026-08-30
tmax00Znearest90d25 1 QC2.57 [1.87, 2.95]1.96-1.82 [-2.51, -1.00]3.07 [2.16, 3.51]24% [14%, 38%]40%64%+0.30+0.452026-08-06 → 2026-08-30
tmax00Znearest365d25 1 QC2.57 [1.94, 3.00]1.96-1.82 [-2.59, -0.91]3.07 [2.20, 3.57]24% [13%, 38%]40%64%+0.30+0.452026-08-06 → 2026-08-30
tmax00Znearestall25 1 QC2.57 [1.81, 2.97]1.96-1.82 [-2.57, -0.84]3.07 [2.11, 3.54]24% [14%, 40%]40%64%+0.30+0.452026-08-06 → 2026-08-30
tmax12Zbilinear30d24 1 QC2.83 [2.10, 3.61]1.76-2.72 [-3.54, -1.99]3.60 [2.55, 4.73]21% [0%, 40%]42%54%+0.21+0.492026-08-06 → 2026-08-30
tmax12Zbilinear90d24 1 QC2.83 [2.09, 3.63]1.76-2.72 [-3.56, -1.92]3.60 [2.53, 4.69]21% [0%, 41%]42%54%+0.21+0.492026-08-06 → 2026-08-30
tmax12Zbilinear365d24 1 QC2.83 [1.99, 3.65]1.76-2.72 [-3.60, -1.86]3.60 [2.49, 4.79]21% [0%, 43%]42%54%+0.21+0.492026-08-06 → 2026-08-30
tmax12Zbilinearall24 1 QC2.83 [1.96, 3.62]1.76-2.72 [-3.58, -1.85]3.60 [2.43, 4.73]21% [0%, 40%]42%54%+0.21+0.492026-08-06 → 2026-08-30
tmax12Znearest30d24 1 QC2.42 [1.78, 3.13]1.78-2.12 [-2.86, -1.43]3.17 [2.15, 4.24]29% [5%, 50%]50%62%+0.32+0.482026-08-06 → 2026-08-30
tmax12Znearest90d24 1 QC2.42 [1.71, 3.10]1.78-2.12 [-2.86, -1.34]3.17 [2.13, 4.20]29% [0%, 50%]50%62%+0.32+0.482026-08-06 → 2026-08-30
tmax12Znearest365d24 1 QC2.42 [1.65, 3.17]1.78-2.12 [-2.92, -1.30]3.17 [2.04, 4.29]29% [0%, 52%]50%62%+0.32+0.482026-08-06 → 2026-08-30
tmax12Znearestall24 1 QC2.42 [1.65, 3.15]1.78-2.12 [-2.89, -1.32]3.17 [2.01, 4.23]29% [0%, 50%]50%62%+0.32+0.482026-08-06 → 2026-08-30
tmin00Zbilinear30d25 1 QC2.78 [1.62, 3.84]2.79-0.13 [-1.46, 1.08]3.47 [2.23, 4.27]32% [10%, 53%]44%48%+0.07+0.112026-08-06 → 2026-08-30
tmin00Zbilinear90d25 1 QC2.78 [1.43, 3.89]2.79-0.13 [-1.40, 1.13]3.47 [2.01, 4.32]32% [9%, 56%]44%48%+0.07+0.112026-08-06 → 2026-08-30
tmin00Zbilinear365d25 1 QC2.78 [1.41, 4.02]2.79-0.13 [-1.56, 1.19]3.47 [2.01, 4.39]32% [5%, 57%]44%48%+0.07+0.112026-08-06 → 2026-08-30
tmin00Zbilinearall25 1 QC2.78 [1.45, 3.95]2.79-0.13 [-1.52, 1.20]3.47 [2.03, 4.34]32% [0%, 56%]44%48%+0.07+0.112026-08-06 → 2026-08-30
tmin00Znearest30d25 1 QC2.79 [1.78, 3.70]2.74+0.39 [-0.85, 1.55]3.44 [2.35, 4.20]36% [16%, 58%]44%48%+0.07+0.132026-08-06 → 2026-08-30
tmin00Znearest90d25 1 QC2.79 [1.61, 3.79]2.74+0.39 [-0.81, 1.61]3.44 [2.19, 4.22]36% [14%, 62%]44%48%+0.07+0.132026-08-06 → 2026-08-30
tmin00Znearest365d25 1 QC2.79 [1.62, 3.90]2.74+0.39 [-0.96, 1.67]3.44 [2.19, 4.35]36% [14%, 62%]44%48%+0.07+0.132026-08-06 → 2026-08-30
tmin00Znearestall25 1 QC2.79 [1.65, 3.84]2.74+0.39 [-0.92, 1.67]3.44 [2.20, 4.25]36% [14%, 60%]44%48%+0.07+0.132026-08-06 → 2026-08-30
tmin12Zbilinear30d24 1 QC2.67 [1.50, 3.61]2.67-0.21 [-1.41, 0.81]3.28 [2.05, 4.01]33% [10%, 58%]46%46%+0.12+0.162026-08-06 → 2026-08-30
tmin12Zbilinear90d24 1 QC2.67 [1.31, 3.70]2.67-0.21 [-1.42, 0.88]3.28 [1.76, 4.10]33% [10%, 64%]46%46%+0.12+0.162026-08-06 → 2026-08-30
tmin12Zbilinear365d24 1 QC2.67 [1.22, 3.84]2.67-0.21 [-1.52, 0.98]3.28 [1.75, 4.19]33% [6%, 67%]46%46%+0.12+0.162026-08-06 → 2026-08-30
tmin12Zbilinearall24 1 QC2.67 [1.29, 3.74]2.67-0.21 [-1.51, 0.94]3.28 [1.64, 4.09]33% [7%, 67%]46%46%+0.12+0.162026-08-06 → 2026-08-30
tmin12Znearest30d24 1 QC2.67 [1.70, 3.49]2.64+0.31 [-0.83, 1.29]3.26 [2.14, 3.99]25% [13%, 38%]46%54%+0.12+0.172026-08-06 → 2026-08-30
tmin12Znearest90d24 1 QC2.67 [1.56, 3.58]2.64+0.31 [-0.83, 1.38]3.26 [1.94, 4.08]25% [11%, 39%]46%54%+0.12+0.172026-08-06 → 2026-08-30
tmin12Znearest365d24 1 QC2.67 [1.50, 3.71]2.64+0.31 [-0.94, 1.45]3.26 [1.87, 4.18]25% [11%, 42%]46%54%+0.12+0.172026-08-06 → 2026-08-30
tmin12Znearestall24 1 QC2.67 [1.49, 3.56]2.64+0.31 [-0.90, 1.42]3.26 [1.91, 4.07]25% [11%, 40%]46%54%+0.12+0.172026-08-06 → 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 5, 00Z bilinear tmax+10+50-5-102026-08-06: -2.51 °F2026-08-07: -1.2 °F2026-08-08: -3.2 °F2026-08-09: -3.2 °F2026-08-10: +1.73 °F2026-08-11: -0.35 °F2026-08-12: -5.72 °F2026-08-13: -2.04 °F2026-08-14: -4.82 °F2026-08-15: -7.49 °F2026-08-16: -1.08 °F2026-08-17: -0.38 °F2026-08-18: -5.43 °F2026-08-19: -4.06 °F2026-08-20: -0.14 °F2026-08-21: -1.51 °F2026-08-22: +4.27 °F2026-08-23: -3.88 °F2026-08-24: -3.54 °F2026-08-25: -1.26 °F2026-08-26: -3.1 °F2026-08-27: -5.47 °F2026-08-28: -3.85 °F2026-08-29: -2.7 °F2026-08-30: -0.86 °F2026-08-062026-08-30°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 (25 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-0.86
2026-08-29-2.70
2026-08-28-3.85
2026-08-27-5.47
2026-08-26-3.10
2026-08-25-1.26
2026-08-24-3.54
2026-08-23-3.88
2026-08-22+4.27
2026-08-21-1.51
2026-08-20-0.14
2026-08-19-4.06
2026-08-18-5.43
2026-08-17-0.38
2026-08-16-1.08
2026-08-15-7.49
2026-08-14-4.82
2026-08-13-2.04
2026-08-12-5.72
2026-08-11-0.35
2026-08-10+1.73
2026-08-09-3.20
2026-08-08-3.20
2026-08-07-1.20
2026-08-06-2.51

Error distribution

Distribution of the signed daily error in °F for ECMWF AIFS Single at KPHL, lead day 5-10 to -9 °F: 0 days-9 to -8 °F: 0 days-8 to -7 °F: 1 day-7 to -6 °F: 0 days-6 to -5 °F: 3 days-5 to -4 °F: 2 days-4 to -3 °F: 6 days-3 to -2 °F: 3 days-2 to -1 °F: 4 days-1 to 0 °F: 4 days0 to 1 °F: 0 days1 to 2 °F: 1 day2 to 3 °F: 0 days3 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| 3.1 · P90 |e| 5.45 °F-100+10 °Fn = 25 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
-8.00-7.001
-7.00-6.000
-6.00-5.003
-5.00-4.002
-4.00-3.006
-3.00-2.003
-2.00-1.004
-1.00+0.004
+0.00+1.000
+1.00+2.001
+2.00+3.000
+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
2026-08252.95 -2.47

Availability

ModelScored period DaysCoverage
ECMWF AIFS Single2026-08-06 → 2026-08-30 25
ECMWF AIFS Single2026-08-06 → 2026-08-30 25
ECMWF AIFS Single2026-08-06 → 2026-08-30 24
ECMWF AIFS Single2026-08-06 → 2026-08-30 24

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
NCEP GFS 25 -1.38 [-2.62, 0.06] no
GraphCast (IFS init) 25 -1.53 [-2.34, -0.69] yes
ECMWF IFS HRES 18 -1.22 [-2.84, -0.20] yes
Persistence (baseline) 25 -0.73 [-1.76, 0.24] no

Cite this page

ShortCastCheck, KPHL aifs_single lead 5, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KPHL/model/aifs_single/lead/5/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KPHL (Philadelphia Intl), model aifs_single, lead day 5. 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/5/

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