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 9

KPHL · graphcast_ifs · lead 9

Target day = initialization date + 9 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
tmax00Zbilinear30d21 1 QC5.87 [4.58, 7.08]4.70-3.45 [-6.72, -0.19]6.81 [5.39, 7.94]5% [0%, 13%]10%33%-0.47-0.562026-08-10 → 2026-08-30
tmax00Zbilinear90d21 1 QC5.87 [4.28, 7.16]4.70-3.45 [-6.78, 0.04]6.81 [5.08, 8.02]5% [0%, 13%]10%33%-0.47-0.562026-08-10 → 2026-08-30
tmax00Zbilinear365d27 1 QC6.65 [5.22, 8.54]5.14-4.16 [-7.41, -0.92]7.49 [6.13, 9.00]4% [0%, 11%]7%26%-0.17+0.112026-01-10 → 2026-08-30
tmax00Zbilinearall27 1 QC6.65 [5.06, 8.80]5.14-4.16 [-7.64, -0.73]7.49 [5.97, 9.10]4% [0%, 11%]7%26%-0.17+0.112026-01-10 → 2026-08-30
tmax00Znearest30d21 1 QC5.69 [4.38, 6.85]4.69-3.21 [-6.40, -0.02]6.66 [5.25, 7.71]5% [0%, 13%]10%38%-0.42-0.552026-08-10 → 2026-08-30
tmax00Znearest90d21 1 QC5.69 [4.13, 6.97]4.69-3.21 [-6.46, 0.22]6.66 [4.99, 7.79]5% [0%, 13%]10%38%-0.42-0.552026-08-10 → 2026-08-30
tmax00Znearest365d27 1 QC6.42 [5.05, 8.24]5.08-3.86 [-7.02, -0.67]7.28 [6.01, 8.69]4% [0%, 11%]7%30%-0.13+0.122026-01-10 → 2026-08-30
tmax00Znearestall27 1 QC6.42 [4.92, 8.38]5.08-3.86 [-7.22, -0.48]7.28 [5.87, 8.76]4% [0%, 11%]7%30%-0.13+0.122026-01-10 → 2026-08-30
tmax12Zbilinear30d21 1 QC6.45 [5.00, 8.25]4.82-5.37 [-8.07, -2.79]7.67 [6.14, 9.26]5% [0%, 12%]14%29%-0.61-0.602026-08-10 → 2026-08-30
tmax12Zbilinear90d21 1 QC6.45 [4.76, 8.51]4.82-5.37 [-8.29, -2.59]7.67 [5.73, 9.46]5% [0%, 14%]14%29%-0.61-0.602026-08-10 → 2026-08-30
tmax12Zbilinear365d26 1 QC6.86 [5.43, 8.74]5.35-5.15 [-7.87, -2.17]8.09 [6.48, 9.80]8% [0%, 18%]15%27%-0.16+0.112026-01-10 → 2026-08-30
tmax12Zbilinearall26 1 QC6.86 [5.28, 8.79]5.35-5.15 [-8.02, -2.51]8.09 [6.49, 9.83]8% [0%, 20%]15%27%-0.16+0.112026-01-10 → 2026-08-30
tmax12Znearest30d21 1 QC6.30 [4.94, 7.99]4.79-5.13 [-7.81, -2.52]7.49 [6.08, 8.98]10% [0%, 24%]14%29%-0.58-0.592026-08-10 → 2026-08-30
tmax12Znearest90d21 1 QC6.30 [4.74, 8.22]4.79-5.13 [-8.02, -2.29]7.49 [5.75, 9.19]10% [0%, 27%]14%29%-0.58-0.592026-08-10 → 2026-08-30
tmax12Znearest365d26 1 QC6.71 [5.35, 8.55]5.31-4.84 [-7.52, -1.84]7.89 [6.42, 9.47]8% [0%, 21%]15%27%-0.13+0.112026-01-10 → 2026-08-30
tmax12Znearestall26 1 QC6.71 [5.25, 8.59]5.31-4.84 [-7.73, -2.17]7.89 [6.48, 9.58]8% [0%, 22%]15%27%-0.13+0.112026-01-10 → 2026-08-30
tmin00Zbilinear30d21 1 QC3.64 [2.07, 5.00]3.67-0.75 [-3.04, 1.46]4.67 [2.38, 6.08]14% [5%, 25%]38%48%+0.20-0.052026-08-10 → 2026-08-30
tmin00Zbilinear90d21 1 QC3.64 [1.80, 5.17]3.67-0.75 [-3.03, 1.69]4.67 [2.10, 6.26]14% [0%, 26%]38%48%+0.20-0.052026-08-10 → 2026-08-30
tmin00Zbilinear365d27 1 QC3.56 [2.25, 4.77]3.41-1.32 [-3.38, 0.86]4.85 [2.68, 6.20]19% [7%, 33%]41%56%+0.40+0.412026-01-10 → 2026-08-30
tmin00Zbilinearall27 1 QC3.56 [2.13, 4.74]3.41-1.32 [-3.53, 0.92]4.85 [2.47, 6.11]19% [8%, 33%]41%56%+0.40+0.412026-01-10 → 2026-08-30
tmin00Znearest30d21 1 QC3.60 [2.06, 4.98]3.61-0.34 [-2.59, 1.76]4.57 [2.25, 6.09]5% [0%, 14%]38%57%+0.21-0.042026-08-10 → 2026-08-30
tmin00Znearest90d21 1 QC3.60 [1.89, 5.09]3.61-0.34 [-2.57, 2.00]4.57 [2.00, 6.24]5% [0%, 15%]38%57%+0.21-0.042026-08-10 → 2026-08-30
tmin00Znearest365d27 1 QC3.46 [2.14, 4.68]3.38-0.93 [-2.95, 1.19]4.71 [2.53, 6.08]15% [0%, 38%]44%63%+0.42+0.422026-01-10 → 2026-08-30
tmin00Znearestall27 1 QC3.46 [2.09, 4.68]3.38-0.93 [-3.10, 1.26]4.71 [2.35, 6.10]15% [0%, 40%]44%63%+0.42+0.422026-01-10 → 2026-08-30
tmin12Zbilinear30d21 1 QC4.07 [3.12, 4.68]3.80-1.43 [-3.75, 1.09]4.75 [3.83, 5.28]10% [0%, 25%]14%43%+0.11-0.092026-08-10 → 2026-08-30
tmin12Zbilinear90d21 1 QC4.07 [2.81, 4.69]3.80-1.43 [-4.15, 1.31]4.75 [3.54, 5.28]10% [0%, 26%]14%43%+0.11-0.092026-08-10 → 2026-08-30
tmin12Zbilinear365d26 1 QC4.11 [3.35, 4.87]3.88-1.08 [-3.35, 1.48]4.88 [4.10, 5.66]8% [0%, 18%]19%46%+0.31+0.342026-01-10 → 2026-08-30
tmin12Zbilinearall26 1 QC4.11 [3.28, 4.77]3.88-1.08 [-3.46, 1.32]4.88 [4.08, 5.64]8% [0%, 19%]19%46%+0.31+0.342026-01-10 → 2026-08-30
tmin12Znearest30d21 1 QC3.92 [2.98, 4.54]3.77-0.94 [-3.24, 1.54]4.58 [3.56, 5.23]14% [0%, 31%]14%38%+0.14-0.082026-08-10 → 2026-08-30
tmin12Znearest90d21 1 QC3.92 [2.74, 4.55]3.77-0.94 [-3.66, 1.76]4.58 [3.29, 5.26]14% [0%, 34%]14%38%+0.14-0.082026-08-10 → 2026-08-30
tmin12Znearest365d26 1 QC3.99 [3.26, 4.77]3.88-0.61 [-2.87, 1.87]4.76 [3.85, 5.69]12% [0%, 25%]19%42%+0.33+0.342026-01-10 → 2026-08-30
tmin12Znearestall26 1 QC3.99 [3.23, 4.68]3.88-0.61 [-2.96, 1.75]4.76 [3.81, 5.64]12% [0%, 26%]19%42%+0.33+0.342026-01-10 → 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 9, 00Z bilinear tmax+20+100-10-202026-08-10: -2.61 °F2026-08-11: -3.02 °F2026-08-12: -2.18 °F2026-08-13: -10.6 °F2026-08-14: -7.24 °F2026-08-15: -10.82 °F2026-08-16: -0.61 °F2026-08-17: -10.88 °F2026-08-18: -7.13 °F2026-08-19: -8.35 °F2026-08-20: +2.62 °F2026-08-21: +8.88 °F2026-08-22: +9.58 °F2026-08-23: -2.15 °F2026-08-24: +2.58 °F2026-08-25: -3.48 °F2026-08-26: -7.77 °F2026-08-27: +1.67 °F2026-08-28: -4.68 °F2026-08-29: -5.71 °F2026-08-30: -10.63 °F2026-08-102026-08-30°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 (21 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-10.63
2026-08-29-5.71
2026-08-28-4.68
2026-08-27+1.67
2026-08-26-7.77
2026-08-25-3.48
2026-08-24+2.58
2026-08-23-2.15
2026-08-22+9.58
2026-08-21+8.88
2026-08-20+2.62
2026-08-19-8.35
2026-08-18-7.13
2026-08-17-10.88
2026-08-16-0.61
2026-08-15-10.82
2026-08-14-7.24
2026-08-13-10.60
2026-08-12-2.18
2026-08-11-3.02
2026-08-10-2.61

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KPHL, lead day 9-20 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: 7 days-10 to -8 °F: 2 days-8 to -6 °F: 4 days-6 to -4 °F: 2 days-4 to -2 °F: 5 days-2 to 0 °F: 1 day0 to 2 °F: 1 day2 to 4 °F: 2 days4 to 6 °F: 0 days6 to 8 °F: 0 days8 to 10 °F: 3 days10 to 12 °F: 0 days12 to 14 °F: 0 days14 to 16 °F: 0 days16 to 18 °F: 0 days18 to 20 °F: 0 daysdashed: P50 |e| 7.24 · P90 |e| 10.72 °F-200+20 °Fn = 27 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
-12.00-10.007
-10.00-8.002
-8.00-6.004
-6.00-4.002
-4.00-2.005
-2.00+0.001
+0.00+2.001
+2.00+4.002
+4.00+6.000
+6.00+8.000
+8.00+10.003
+10.00+12.000
+12.00+14.000
+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
2026-08215.87 -3.45
2026-0169.38 -6.64

Availability

ModelScored period DaysCoverage
GraphCast (IFS init)2026-01-10 → 2026-08-30 27
GraphCast (IFS init)2026-01-10 → 2026-08-30 27
GraphCast (IFS init)2026-01-10 → 2026-08-30 26
GraphCast (IFS init)2026-01-10 → 2026-08-30 26

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 21 +0.91 [-0.14, 2.34] no
NCEP GFS 21 +0.72 [-1.09, 2.71] no
ECMWF IFS HRES 16 +0.40 [-5.89, 3.13] no
Persistence (baseline) 21 +1.87 [0.44, 3.66] yes

Cite this page

ShortCastCheck, KPHL graphcast_ifs lead 9, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KPHL/model/graphcast_ifs/lead/9/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KPHL (Philadelphia Intl), model graphcast_ifs, lead day 9. 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/9/

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