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 1

KEWR · graphcast_ifs · lead 1

Target day = initialization date + 1 day. 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
tmax00Zbilinear30d27 1 QC4.87 [4.26, 5.64]1.23-4.87 [-5.64, -4.26]5.12 [4.41, 5.96]0% [0%, 0%]0%7%-0.83+0.542026-08-02 → 2026-08-30
tmax00Zbilinear90d27 1 QC4.87 [4.23, 5.73]1.23-4.87 [-5.73, -4.23]5.12 [4.36, 6.04]0% [0%, 0%]0%7%-0.83+0.542026-08-02 → 2026-08-30
tmax00Zbilinear365d33 1 QC4.55 [3.70, 5.31]1.25-4.55 [-5.31, -3.70]4.83 [3.86, 5.63]0% [0%, 0%]3%15%-0.52+0.592026-01-02 → 2026-08-30
tmax00Zbilinearall33 1 QC4.55 [3.78, 5.40]1.25-4.55 [-5.40, -3.78]4.83 [3.97, 5.75]0% [0%, 0%]3%15%-0.52+0.592026-01-02 → 2026-08-30
tmax00Znearest30d27 1 QC4.39 [3.78, 5.05]1.27-4.39 [-5.05, -3.78]4.66 [3.98, 5.39]0% [0%, 0%]4%19%-0.65+0.522026-08-02 → 2026-08-30
tmax00Znearest90d27 1 QC4.39 [3.75, 5.14]1.27-4.39 [-5.14, -3.75]4.66 [3.95, 5.45]0% [0%, 0%]4%19%-0.65+0.522026-08-02 → 2026-08-30
tmax00Znearest365d33 1 QC4.17 [3.49, 4.84]1.23-4.17 [-4.84, -3.49]4.44 [3.65, 5.12]0% [0%, 0%]6%24%-0.39+0.602026-01-02 → 2026-08-30
tmax00Znearestall33 1 QC4.17 [3.53, 4.89]1.23-4.17 [-4.89, -3.53]4.44 [3.71, 5.22]0% [0%, 0%]6%24%-0.39+0.602026-01-02 → 2026-08-30
tmax12Zbilinear30d27 1 QC4.69 [4.25, 5.24]0.97-4.69 [-5.24, -4.25]4.86 [4.38, 5.44]0% [0%, 0%]0%4%-0.76+0.642026-08-02 → 2026-08-30
tmax12Zbilinear90d27 1 QC4.69 [4.22, 5.32]0.97-4.69 [-5.32, -4.22]4.86 [4.34, 5.52]0% [0%, 0%]0%4%-0.76+0.642026-08-02 → 2026-08-30
tmax12Zbilinear365d32 1 QC4.47 [3.84, 5.02]0.99-4.47 [-5.02, -3.84]4.67 [4.01, 5.23]0% [0%, 0%]3%9%-0.61+0.642026-01-02 → 2026-08-30
tmax12Zbilinearall32 1 QC4.47 [3.89, 5.07]0.99-4.47 [-5.07, -3.89]4.67 [4.07, 5.31]0% [0%, 0%]3%9%-0.61+0.642026-01-02 → 2026-08-30
tmax12Znearest30d27 1 QC4.15 [3.72, 4.61]0.98-4.15 [-4.61, -3.72]4.33 [3.88, 4.83]0% [0%, 0%]4%15%-0.56+0.632026-08-02 → 2026-08-30
tmax12Znearest90d27 1 QC4.15 [3.70, 4.70]0.98-4.15 [-4.70, -3.70]4.33 [3.84, 4.93]0% [0%, 0%]4%15%-0.56+0.632026-08-02 → 2026-08-30
tmax12Znearest365d32 1 QC4.04 [3.57, 4.48]0.96-4.04 [-4.48, -3.57]4.22 [3.72, 4.68]0% [0%, 0%]6%19%-0.45+0.662026-01-02 → 2026-08-30
tmax12Znearestall32 1 QC4.04 [3.60, 4.52]0.96-4.04 [-4.52, -3.60]4.22 [3.75, 4.73]0% [0%, 0%]6%19%-0.45+0.662026-01-02 → 2026-08-30
tmin00Zbilinear30d27 1 QC2.13 [1.53, 2.67]1.99+0.77 [0.22, 1.30]2.53 [2.04, 2.95]30% [14%, 48%]44%78%+0.32+0.372026-08-02 → 2026-08-30
tmin00Zbilinear90d27 1 QC2.13 [1.40, 2.74]1.99+0.77 [0.26, 1.29]2.53 [1.86, 3.02]30% [16%, 50%]44%78%+0.32+0.372026-08-02 → 2026-08-30
tmin00Zbilinear365d33 1 QC1.94 [1.23, 2.51]1.92+0.45 [-0.38, 1.11]2.36 [1.51, 2.84]33% [20%, 52%]52%82%+0.42+0.422026-01-02 → 2026-08-30
tmin00Zbilinearall33 1 QC1.94 [1.29, 2.57]1.92+0.45 [-0.30, 1.06]2.36 [1.70, 2.89]33% [19%, 50%]52%82%+0.42+0.422026-01-02 → 2026-08-30
tmin00Znearest30d27 1 QC2.07 [1.48, 2.63]2.07-0.27 [-0.86, 0.28]2.52 [1.93, 2.97]26% [10%, 44%]56%67%+0.34+0.352026-08-02 → 2026-08-30
tmin00Znearest90d27 1 QC2.07 [1.46, 2.72]2.07-0.27 [-0.95, 0.26]2.52 [1.87, 3.02]26% [7%, 46%]56%67%+0.34+0.352026-08-02 → 2026-08-30
tmin00Znearest365d33 1 QC2.09 [1.54, 2.60]2.00-0.61 [-1.57, 0.11]2.50 [1.97, 2.92]24% [8%, 43%]52%70%+0.37+0.402026-01-02 → 2026-08-30
tmin00Znearestall33 1 QC2.09 [1.55, 2.60]2.00-0.61 [-1.44, 0.07]2.50 [1.98, 2.91]24% [9%, 42%]52%70%+0.37+0.402026-01-02 → 2026-08-30
tmin12Zbilinear30d27 1 QC2.02 [1.44, 2.63]1.99+0.61 [0.02, 1.15]2.46 [1.90, 2.94]26% [10%, 46%]56%70%+0.36+0.372026-08-02 → 2026-08-30
tmin12Zbilinear90d27 1 QC2.02 [1.29, 2.75]1.99+0.61 [0.05, 1.15]2.46 [1.76, 3.03]26% [5%, 50%]56%70%+0.36+0.372026-08-02 → 2026-08-30
tmin12Zbilinear365d32 1 QC1.89 [1.11, 2.49]1.91+0.33 [-0.50, 0.97]2.33 [1.47, 2.84]31% [12%, 59%]56%75%+0.42+0.412026-01-02 → 2026-08-30
tmin12Zbilinearall32 1 QC1.89 [1.20, 2.59]1.91+0.33 [-0.43, 0.97]2.33 [1.64, 2.91]31% [11%, 58%]56%75%+0.42+0.412026-01-02 → 2026-08-30
tmin12Znearest30d27 1 QC2.08 [1.55, 2.63]2.02-0.44 [-1.06, 0.12]2.49 [1.95, 2.96]22% [10%, 36%]56%74%+0.34+0.372026-08-02 → 2026-08-30
tmin12Znearest90d27 1 QC2.08 [1.47, 2.73]2.02-0.44 [-1.05, 0.08]2.49 [1.81, 3.04]22% [8%, 40%]56%74%+0.34+0.372026-08-02 → 2026-08-30
tmin12Znearest365d32 1 QC2.13 [1.61, 2.63]1.96-0.76 [-1.68, -0.06]2.50 [1.97, 2.94]19% [5%, 33%]56%72%+0.34+0.402026-01-02 → 2026-08-30
tmin12Znearestall32 1 QC2.13 [1.60, 2.66]1.96-0.76 [-1.58, -0.07]2.50 [1.96, 2.94]19% [5%, 33%]56%72%+0.34+0.402026-01-02 → 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 1, 00Z bilinear tmax+10+50-5-102026-08-02: -4.51 °F2026-08-03: -8.02 °F2026-08-04: -3.8 °F2026-08-05: -6.64 °F2026-08-06: -7.8 °F2026-08-07: -8.97 °F2026-08-08: -4.05 °F2026-08-09: -3.57 °F2026-08-10: -2.64 °F2026-08-11: -2.9 °F2026-08-12: -5.45 °F2026-08-13: -3.51 °F2026-08-14: -3.54 °F2026-08-15: -5.61 °F2026-08-16: -3.34 °F2026-08-17: -3.27 °F2026-08-18: -4.56 °F2026-08-19: -5.91 °F2026-08-20: -6.43 °F2026-08-21: -4.87 °F2026-08-22: -4.02 °F2026-08-23: -4.13 °F2026-08-24: -5.18 °F2026-08-25: -5.11 °F2026-08-26: -5.1 °F2026-08-29: -4.71 °F2026-08-30: -3.98 °F2026-08-022026-08-30°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 (29 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-3.98
2026-08-29-4.71
2026-08-28—
2026-08-27—
2026-08-26-5.10
2026-08-25-5.11
2026-08-24-5.18
2026-08-23-4.13
2026-08-22-4.02
2026-08-21-4.87
2026-08-20-6.43
2026-08-19-5.91
2026-08-18-4.56
2026-08-17-3.27
2026-08-16-3.34
2026-08-15-5.61
2026-08-14-3.54
2026-08-13-3.51
2026-08-12-5.45
2026-08-11-2.90
2026-08-10-2.64
2026-08-09-3.57
2026-08-08-4.05
2026-08-07-8.97
2026-08-06-7.80
2026-08-05-6.64
2026-08-04-3.80
2026-08-03-8.02
2026-08-02-4.51

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KEWR, lead day 1-10 to -9 °F: 0 days-9 to -8 °F: 2 days-8 to -7 °F: 1 day-7 to -6 °F: 2 days-6 to -5 °F: 6 days-5 to -4 °F: 8 days-4 to -3 °F: 9 days-3 to -2 °F: 4 days-2 to -1 °F: 1 day-1 to 0 °F: 0 days0 to 1 °F: 0 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| 4.13 · P90 |e| 6.6 °F-100+10 °Fn = 33 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
-7.00-6.002
-6.00-5.006
-5.00-4.008
-4.00-3.009
-3.00-2.004
-2.00-1.001
-1.00+0.000
+0.00+1.000
+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
2026-08274.87 -4.87
2026-0163.07 -3.07

Availability

ModelScored period DaysCoverage
GraphCast (IFS init)2026-01-02 → 2026-08-30 33
GraphCast (IFS init)2026-01-02 → 2026-08-30 33
GraphCast (IFS init)2026-01-02 → 2026-08-30 32
GraphCast (IFS init)2026-01-02 → 2026-08-30 32

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 27 +2.25 [1.78, 2.54] yes
Aurora (GFS init) 1 +1.14 [1.14, 1.14] yes
Aurora (IFS init) 2 +1.28 [0.70, 1.86] yes
FourCastNet v2 (GFS init) 1 +1.97 [1.97, 1.97] yes
FourCastNet v2 (IFS init) 2 +2.49 [0.65, 4.34] yes
NCEP GFS 27 +2.77 [2.18, 3.24] yes
GraphCast (GFS init) 1 -0.61 [-0.61, -0.61] yes
ECMWF IFS HRES 21 +0.40 [-0.21, 1.42] no
Pangu-Weather (GFS init) 1 +2.05 [2.05, 2.05] yes
Pangu-Weather (IFS init) 2 +3.73 [2.77, 4.70] yes
Persistence (baseline) 27 +2.21 [1.62, 2.62] yes

Cite this page

ShortCastCheck, KEWR graphcast_ifs lead 1, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KEWR/model/graphcast_ifs/lead/1/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KEWR (Newark Liberty), model graphcast_ifs, lead day 1. 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/1/

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