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

Newark Liberty · GraphCast (IFS init) · lead day 7

KEWR · graphcast_ifs · lead 7

Target day = initialization date + 7 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
tmax00Zbilinear30d23 1 QC4.28 [3.64, 4.86]2.20-4.21 [-4.77, -3.58]4.92 [4.37, 5.34]17% [4%, 32%]17%35%-0.03+0.412026-08-08 → 2026-08-30
tmax00Zbilinear90d23 1 QC4.28 [3.62, 4.91]2.20-4.21 [-4.80, -3.60]4.92 [4.33, 5.36]17% [0%, 33%]17%35%-0.03+0.412026-08-08 → 2026-08-30
tmax00Zbilinear365d29 1 QC4.06 [3.13, 4.83]2.35-3.91 [-4.70, -2.92]4.77 [3.96, 5.38]21% [6%, 35%]21%41%+0.35+0.632026-01-08 → 2026-08-30
tmax00Zbilinearall29 1 QC4.06 [3.20, 4.75]2.35-3.91 [-4.67, -2.95]4.77 [4.02, 5.32]21% [5%, 34%]21%41%+0.35+0.632026-01-08 → 2026-08-30
tmax00Znearest30d23 1 QC3.87 [3.16, 4.56]2.42-3.70 [-4.30, -3.07]4.60 [3.93, 5.12]17% [0%, 33%]30%43%+0.07+0.362026-08-08 → 2026-08-30
tmax00Znearest90d23 1 QC3.87 [3.07, 4.61]2.42-3.70 [-4.33, -3.03]4.60 [3.82, 5.15]17% [0%, 33%]30%43%+0.07+0.362026-08-08 → 2026-08-30
tmax00Znearest365d29 1 QC3.76 [2.96, 4.52]2.51-3.48 [-4.25, -2.59]4.52 [3.71, 5.14]17% [3%, 30%]31%45%+0.40+0.602026-01-08 → 2026-08-30
tmax00Znearestall29 1 QC3.76 [2.99, 4.55]2.51-3.48 [-4.26, -2.60]4.52 [3.70, 5.15]17% [2%, 29%]31%45%+0.40+0.602026-01-08 → 2026-08-30
tmax12Zbilinear30d23 1 QC4.35 [3.47, 5.22]2.17-4.35 [-5.22, -3.47]5.02 [4.14, 5.80]13% [4%, 25%]30%30%-0.04+0.422026-08-08 → 2026-08-30
tmax12Zbilinear90d23 1 QC4.35 [3.38, 5.30]2.17-4.35 [-5.30, -3.38]5.02 [4.00, 5.87]13% [0%, 25%]30%30%-0.04+0.422026-08-08 → 2026-08-30
tmax12Zbilinear365d28 1 QC4.11 [3.20, 5.06]2.53-3.63 [-4.98, -1.71]4.75 [3.68, 5.63]11% [0%, 21%]32%32%+0.34+0.602026-01-08 → 2026-08-30
tmax12Zbilinearall28 1 QC4.11 [3.01, 4.93]2.53-3.63 [-4.91, -1.45]4.75 [3.51, 5.55]11% [0%, 20%]32%32%+0.34+0.602026-01-08 → 2026-08-30
tmax12Znearest30d23 1 QC3.82 [2.79, 4.91]2.30-3.78 [-4.86, -2.76]4.64 [3.55, 5.64]26% [10%, 43%]30%39%+0.09+0.392026-08-08 → 2026-08-30
tmax12Znearest90d23 1 QC3.82 [2.66, 4.99]2.30-3.78 [-4.96, -2.63]4.64 [3.44, 5.74]26% [7%, 45%]30%39%+0.09+0.392026-08-08 → 2026-08-30
tmax12Znearest365d28 1 QC3.63 [2.68, 4.65]2.59-3.06 [-4.48, -1.08]4.40 [3.27, 5.41]25% [8%, 41%]32%39%+0.42+0.592026-01-08 → 2026-08-30
tmax12Znearestall28 1 QC3.63 [2.54, 4.63]2.59-3.06 [-4.47, -0.73]4.40 [3.11, 5.41]25% [11%, 40%]32%39%+0.42+0.592026-01-08 → 2026-08-30
tmin00Zbilinear30d23 1 QC2.90 [2.07, 3.55]2.73+1.13 [0.04, 2.50]3.46 [2.42, 4.25]17% [0%, 32%]35%57%+0.31+0.302026-08-08 → 2026-08-30
tmin00Zbilinear90d23 1 QC2.90 [1.95, 3.58]2.73+1.13 [0.03, 2.72]3.46 [2.29, 4.27]17% [0%, 33%]35%57%+0.31+0.302026-08-08 → 2026-08-30
tmin00Zbilinear365d29 1 QC3.23 [2.37, 4.12]2.89+1.40 [0.27, 2.83]3.78 [2.79, 4.62]14% [0%, 29%]31%48%+0.45+0.522026-01-08 → 2026-08-30
tmin00Zbilinearall29 1 QC3.23 [2.30, 4.08]2.89+1.40 [0.18, 2.79]3.78 [2.69, 4.57]14% [0%, 28%]31%48%+0.45+0.522026-01-08 → 2026-08-30
tmin00Znearest30d23 1 QC2.93 [2.12, 3.55]2.90+0.23 [-0.97, 1.66]3.47 [2.51, 4.04]22% [8%, 38%]26%57%+0.30+0.262026-08-08 → 2026-08-30
tmin00Znearest90d23 1 QC2.93 [1.93, 3.57]2.90+0.23 [-0.95, 2.02]3.47 [2.39, 4.05]22% [6%, 43%]26%57%+0.30+0.262026-08-08 → 2026-08-30
tmin00Znearest365d29 1 QC3.16 [2.37, 3.91]3.09+0.51 [-0.67, 1.99]3.72 [2.79, 4.41]21% [8%, 34%]24%48%+0.46+0.482026-01-08 → 2026-08-30
tmin00Znearestall29 1 QC3.16 [2.27, 3.87]3.09+0.51 [-0.80, 1.96]3.72 [2.73, 4.36]21% [8%, 36%]24%48%+0.46+0.482026-01-08 → 2026-08-30
tmin12Zbilinear30d23 1 QC2.22 [1.73, 2.74]2.09+1.04 [0.11, 2.15]2.79 [2.11, 3.48]26% [12%, 39%]43%78%+0.47+0.472026-08-08 → 2026-08-30
tmin12Zbilinear90d23 1 QC2.22 [1.73, 2.80]2.09+1.04 [0.08, 2.30]2.79 [2.12, 3.56]26% [12%, 42%]43%78%+0.47+0.472026-08-08 → 2026-08-30
tmin12Zbilinear365d28 1 QC2.80 [1.90, 4.40]2.60+1.12 [-0.04, 2.39]3.73 [2.26, 5.48]25% [12%, 38%]39%71%+0.53+0.572026-01-08 → 2026-08-30
tmin12Zbilinearall28 1 QC2.80 [1.92, 4.55]2.60+1.12 [-0.13, 2.43]3.73 [2.29, 5.67]25% [12%, 39%]39%71%+0.53+0.572026-01-08 → 2026-08-30
tmin12Znearest30d23 1 QC2.18 [1.72, 2.56]2.17+0.18 [-0.79, 1.32]2.70 [1.99, 3.26]22% [7%, 38%]61%78%+0.48+0.442026-08-08 → 2026-08-30
tmin12Znearest90d23 1 QC2.18 [1.69, 2.60]2.17+0.18 [-0.80, 1.45]2.70 [1.98, 3.31]22% [0%, 39%]61%78%+0.48+0.442026-08-08 → 2026-08-30
tmin12Znearest365d28 1 QC2.75 [1.88, 4.31]2.73+0.25 [-0.86, 1.60]3.75 [2.17, 5.59]21% [6%, 37%]57%71%+0.54+0.552026-01-08 → 2026-08-30
tmin12Znearestall28 1 QC2.75 [1.89, 4.43]2.73+0.25 [-1.03, 1.55]3.75 [2.21, 5.88]21% [7%, 36%]57%71%+0.54+0.552026-01-08 → 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 KEWR, lead day 7, 00Z bilinear tmax+10+50-5-102026-08-08: -3.84 °F2026-08-09: -6.8 °F2026-08-10: -2.37 °F2026-08-11: -3.09 °F2026-08-12: -6.87 °F2026-08-13: -2.2 °F2026-08-14: -5.41 °F2026-08-15: -8 °F2026-08-16: -0.36 °F2026-08-17: -0.17 °F2026-08-18: -5.53 °F2026-08-19: -5.9 °F2026-08-20: -0.96 °F2026-08-21: -5.51 °F2026-08-22: -2.09 °F2026-08-23: -2.91 °F2026-08-24: -8.41 °F2026-08-25: -6.58 °F2026-08-26: -5.01 °F2026-08-27: +0.81 °F2026-08-28: -6.43 °F2026-08-29: -5.39 °F2026-08-30: -3.82 °F2026-08-082026-08-30°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 (23 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-3.82
2026-08-29-5.39
2026-08-28-6.43
2026-08-27+0.81
2026-08-26-5.01
2026-08-25-6.58
2026-08-24-8.41
2026-08-23-2.91
2026-08-22-2.09
2026-08-21-5.51
2026-08-20-0.96
2026-08-19-5.90
2026-08-18-5.53
2026-08-17-0.17
2026-08-16-0.36
2026-08-15-8.00
2026-08-14-5.41
2026-08-13-2.20
2026-08-12-6.87
2026-08-11-3.09
2026-08-10-2.37
2026-08-09-6.80
2026-08-08-3.84

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KEWR, lead day 7-10 to -9 °F: 0 days-9 to -8 °F: 2 days-8 to -7 °F: 1 day-7 to -6 °F: 4 days-6 to -5 °F: 6 days-5 to -4 °F: 1 day-4 to -3 °F: 3 days-3 to -2 °F: 6 days-2 to -1 °F: 0 days-1 to 0 °F: 3 days0 to 1 °F: 3 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| 3.84 · P90 |e| 7.09 °F-100+10 °Fn = 29 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
-9.00-8.002
-8.00-7.001
-7.00-6.004
-6.00-5.006
-5.00-4.001
-4.00-3.003
-3.00-2.006
-2.00-1.000
-1.00+0.003
+0.00+1.003
+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
2026-08234.28 -4.21
2026-0163.20 -2.76

Availability

ModelScored period DaysCoverage
GraphCast (IFS init)2026-01-08 → 2026-08-30 29
GraphCast (IFS init)2026-01-08 → 2026-08-30 29
GraphCast (IFS init)2026-01-08 → 2026-08-30 28
GraphCast (IFS init)2026-01-08 → 2026-08-30 28

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 23 +0.42 [-0.11, 1.07] no
NCEP GFS 23 +1.55 [0.83, 2.68] yes
ECMWF IFS HRES 18 +1.11 [-0.84, 2.10] no
Persistence (baseline) 23 +0.11 [-1.23, 1.61] no

Cite this page

ShortCastCheck, KEWR graphcast_ifs lead 7, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KEWR/model/graphcast_ifs/lead/7/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KEWR (Newark Liberty), model graphcast_ifs, lead day 7. Methodology version 0.2, schema version 0.1, data through 2026-08-30. Accessed 2026-08-31. https://castcheck.zifanzhang.com/station/KEWR/model/graphcast_ifs/lead/7/

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