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 · GraphCast (IFS init) · lead day 6

KPHL · graphcast_ifs · lead 6

Target day = initialization date + 6 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, GRAP_v100, starting 2026-01-01 — 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
tmax00Zbilinear30d24 1 QC4.47 [3.80, 5.09]1.98-4.39 [-5.08, -3.64]5.01 [4.42, 5.51]17% [4%, 30%]17%25%-0.29+0.422026-08-07 → 2026-08-30
tmax00Zbilinear90d24 1 QC4.47 [3.76, 5.16]1.98-4.39 [-5.16, -3.60]5.01 [4.38, 5.54]17% [0%, 32%]17%25%-0.29+0.422026-08-07 → 2026-08-30
tmax00Zbilinear365d30 1 QC5.20 [4.03, 6.79]3.19-3.48 [-5.02, -0.85]5.96 [4.60, 7.67]13% [0%, 26%]13%20%+0.08+0.472026-01-07 → 2026-08-30
tmax00Zbilinearall30 1 QC5.20 [4.13, 6.99]3.19-3.48 [-4.99, -0.65]5.96 [4.71, 7.85]13% [0%, 25%]13%20%+0.08+0.472026-01-07 → 2026-08-30
tmax00Znearest30d24 1 QC4.23 [3.61, 4.84]1.99-4.10 [-4.84, -3.33]4.77 [4.19, 5.26]12% [4%, 22%]17%29%-0.22+0.412026-08-07 → 2026-08-30
tmax00Znearest90d24 1 QC4.23 [3.54, 4.92]1.99-4.10 [-4.92, -3.29]4.77 [4.19, 5.29]12% [0%, 23%]17%29%-0.22+0.412026-08-07 → 2026-08-30
tmax00Znearest365d30 1 QC4.99 [3.80, 6.67]3.20-3.17 [-4.74, -0.51]5.81 [4.37, 7.62]10% [0%, 19%]13%27%+0.11+0.472026-01-07 → 2026-08-30
tmax00Znearestall30 1 QC4.99 [3.92, 6.83]3.20-3.17 [-4.74, -0.33]5.81 [4.46, 7.83]10% [0%, 17%]13%27%+0.11+0.472026-01-07 → 2026-08-30
tmax12Zbilinear30d24 1 QC4.57 [3.80, 5.40]2.16-4.44 [-5.29, -3.66]5.29 [4.44, 6.13]12% [4%, 21%]21%21%-0.32+0.372026-08-07 → 2026-08-30
tmax12Zbilinear90d24 1 QC4.57 [3.72, 5.46]2.16-4.44 [-5.29, -3.54]5.29 [4.39, 6.20]12% [3%, 22%]21%21%-0.32+0.372026-08-07 → 2026-08-30
tmax12Zbilinear365d29 1 QC5.05 [3.96, 6.42]3.21-3.40 [-5.08, -0.49]5.88 [4.64, 7.26]10% [0%, 19%]17%21%+0.13+0.482026-01-07 → 2026-08-30
tmax12Zbilinearall29 1 QC5.05 [4.10, 6.56]3.21-3.40 [-5.02, -0.28]5.88 [4.71, 7.42]10% [0%, 17%]17%21%+0.13+0.482026-01-07 → 2026-08-30
tmax12Znearest30d24 1 QC4.39 [3.63, 5.26]2.21-4.21 [-5.09, -3.39]5.11 [4.21, 5.98]17% [7%, 26%]21%21%-0.27+0.352026-08-07 → 2026-08-30
tmax12Znearest90d24 1 QC4.39 [3.56, 5.27]2.21-4.21 [-5.15, -3.28]5.11 [4.16, 6.05]17% [6%, 28%]21%21%-0.27+0.352026-08-07 → 2026-08-30
tmax12Znearest365d29 1 QC4.90 [3.81, 6.24]3.24-3.15 [-4.88, -0.19]5.78 [4.43, 7.33]14% [2%, 24%]17%21%+0.16+0.482026-01-07 → 2026-08-30
tmax12Znearestall29 1 QC4.90 [3.92, 6.51]3.24-3.15 [-4.82, 0.00]5.78 [4.48, 7.48]14% [0%, 23%]17%21%+0.16+0.482026-01-07 → 2026-08-30
tmin00Zbilinear30d24 1 QC2.76 [2.07, 3.36]2.76-0.07 [-1.40, 1.23]3.30 [2.58, 3.87]25% [12%, 42%]42%58%+0.19+0.152026-08-07 → 2026-08-30
tmin00Zbilinear90d24 1 QC2.76 [2.01, 3.42]2.76-0.07 [-1.49, 1.49]3.30 [2.49, 3.94]25% [10%, 42%]42%58%+0.19+0.152026-08-07 → 2026-08-30
tmin00Zbilinear365d30 1 QC3.15 [2.16, 4.22]3.17+0.73 [-1.14, 3.02]3.97 [2.64, 5.33]23% [11%, 40%]43%57%+0.34+0.352026-01-07 → 2026-08-30
tmin00Zbilinearall30 1 QC3.15 [2.24, 4.27]3.17+0.73 [-0.99, 3.16]3.97 [2.80, 5.37]23% [11%, 39%]43%57%+0.34+0.352026-01-07 → 2026-08-30
tmin00Znearest30d24 1 QC2.79 [2.18, 3.38]2.77+0.36 [-0.96, 1.69]3.34 [2.65, 3.99]25% [4%, 50%]29%58%+0.18+0.152026-08-07 → 2026-08-30
tmin00Znearest90d24 1 QC2.79 [2.11, 3.46]2.77+0.36 [-1.07, 1.96]3.34 [2.62, 4.04]25% [0%, 52%]29%58%+0.18+0.152026-08-07 → 2026-08-30
tmin00Znearest365d30 1 QC3.22 [2.26, 4.41]3.17+1.16 [-0.71, 3.44]4.10 [2.66, 5.59]23% [5%, 45%]30%57%+0.32+0.342026-01-07 → 2026-08-30
tmin00Znearestall30 1 QC3.22 [2.36, 4.42]3.17+1.16 [-0.57, 3.61]4.10 [2.85, 5.64]23% [5%, 44%]30%57%+0.32+0.342026-01-07 → 2026-08-30
tmin12Zbilinear30d24 1 QC3.05 [2.04, 3.77]3.02-0.34 [-2.05, 1.36]3.59 [2.46, 4.31]17% [4%, 32%]38%54%+0.11+0.072026-08-07 → 2026-08-30
tmin12Zbilinear90d24 1 QC3.05 [1.85, 3.93]3.02-0.34 [-2.08, 1.51]3.59 [2.29, 4.44]17% [4%, 35%]38%54%+0.11+0.072026-08-07 → 2026-08-30
tmin12Zbilinear365d29 1 QC3.36 [2.17, 4.54]3.34+0.47 [-1.68, 3.19]4.32 [2.57, 6.04]17% [6%, 33%]38%52%+0.31+0.332026-01-07 → 2026-08-30
tmin12Zbilinearall29 1 QC3.36 [2.16, 4.50]3.34+0.47 [-1.68, 3.25]4.32 [2.63, 5.94]17% [5%, 30%]38%52%+0.31+0.332026-01-07 → 2026-08-30
tmin12Znearest30d24 1 QC3.03 [2.12, 3.86]3.04+0.03 [-1.67, 1.72]3.59 [2.52, 4.42]17% [5%, 27%]42%46%+0.11+0.072026-08-07 → 2026-08-30
tmin12Znearest90d24 1 QC3.03 [1.93, 3.98]3.04+0.03 [-1.72, 1.90]3.59 [2.37, 4.53]17% [5%, 27%]42%46%+0.11+0.072026-08-07 → 2026-08-30
tmin12Znearest365d29 1 QC3.38 [2.17, 4.64]3.36+0.82 [-1.30, 3.53]4.39 [2.60, 6.24]17% [6%, 27%]41%45%+0.30+0.322026-01-07 → 2026-08-30
tmin12Znearestall29 1 QC3.38 [2.21, 4.67]3.36+0.82 [-1.32, 3.55]4.39 [2.71, 6.13]17% [5%, 27%]41%45%+0.30+0.322026-01-07 → 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 GraphCast (IFS init) at KPHL, lead day 6, 00Z bilinear tmax+10+50-5-102026-08-07: -5.38 °F2026-08-08: -5.02 °F2026-08-09: -5.44 °F2026-08-10: -2.43 °F2026-08-11: -5.3 °F2026-08-12: -6.57 °F2026-08-13: -3.58 °F2026-08-14: -8.67 °F2026-08-15: -6.78 °F2026-08-16: -0.66 °F2026-08-17: -3.27 °F2026-08-18: -6.12 °F2026-08-19: -5.97 °F2026-08-20: +0.86 °F2026-08-21: -5.06 °F2026-08-22: -0.14 °F2026-08-23: -5.1 °F2026-08-24: -5.76 °F2026-08-25: -3.12 °F2026-08-26: -6.81 °F2026-08-27: -2.96 °F2026-08-28: -7.23 °F2026-08-29: -0.49 °F2026-08-30: -4.49 °F2026-08-072026-08-30°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 (24 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-4.49
2026-08-29-0.49
2026-08-28-7.23
2026-08-27-2.96
2026-08-26-6.81
2026-08-25-3.12
2026-08-24-5.76
2026-08-23-5.10
2026-08-22-0.14
2026-08-21-5.06
2026-08-20+0.86
2026-08-19-5.97
2026-08-18-6.12
2026-08-17-3.27
2026-08-16-0.66
2026-08-15-6.78
2026-08-14-8.67
2026-08-13-3.58
2026-08-12-6.57
2026-08-11-5.30
2026-08-10-2.43
2026-08-09-5.44
2026-08-08-5.02
2026-08-07-5.38

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KPHL, lead day 6-20 to -18 °F: 0 days-18 to -16 °F: 0 days-16 to -14 °F: 0 days-14 to -12 °F: 0 days-12 to -10 °F: 0 days-10 to -8 °F: 1 day-8 to -6 °F: 8 days-6 to -4 °F: 9 days-4 to -2 °F: 6 days-2 to 0 °F: 3 days0 to 2 °F: 1 day2 to 4 °F: 0 days4 to 6 °F: 0 days6 to 8 °F: 0 days8 to 10 °F: 0 days10 to 12 °F: 0 days12 to 14 °F: 2 days14 to 16 °F: 0 days16 to 18 °F: 0 days18 to 20 °F: 0 daysdashed: P50 |e| 5.34 · P90 |e| 7.4 °F-200+20 °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
-20.00-18.000
-18.00-16.000
-16.00-14.000
-14.00-12.000
-12.00-10.000
-10.00-8.001
-8.00-6.008
-6.00-4.009
-4.00-2.006
-2.00+0.003
+0.00+2.001
+2.00+4.000
+4.00+6.000
+6.00+8.000
+8.00+10.000
+10.00+12.000
+12.00+14.002
+14.00+16.000
+16.00+18.000
+18.00+20.000

Month by month

00Z bilinear daily maximum, newest first.

Monthn MAE °FBias °F
2026-08244.47 -4.39
2026-0168.12 +0.18

Availability

ModelScored period DaysCoverage
GraphCast (IFS init)2026-01-07 → 2026-08-30 30
GraphCast (IFS init)2026-01-07 → 2026-08-30 30
GraphCast (IFS init)2026-01-07 → 2026-08-30 29
GraphCast (IFS init)2026-01-07 → 2026-08-30 29

Compared with other models

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

Other modelCommon days MAE difference °FDistinguishable
ECMWF AIFS Single 24 +1.22 [0.11, 2.50] yes
NCEP GFS 24 +0.38 [-0.70, 2.45] no
ECMWF IFS HRES 19 -0.20 [-1.95, 1.10] no
Persistence (baseline) 24 +1.01 [-0.26, 2.36] no

Cite this page

ShortCastCheck, KPHL graphcast_ifs lead 6, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KPHL/model/graphcast_ifs/lead/6/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KPHL (Philadelphia Intl), model graphcast_ifs, lead day 6. Methodology version 0.2, schema version 0.1, data through 2026-08-30. Accessed 2026-08-31. https://castcheck.zifanzhang.com/station/KPHL/model/graphcast_ifs/lead/6/

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