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 · NCEP GFS · lead day 0

KEWR · gfs · lead 0

Target day = initialization date + 0 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, gfs-0p25, 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
tmax00Zbilinear30d30 1 QC1.70 [1.22, 2.20]1.52-1.09 [-1.80, -0.38]2.38 [1.58, 3.17]37% [23%, 50%]80%87%——2026-08-01 → 2026-08-30
tmax00Zbilinear90d30 1 QC1.70 [1.14, 2.27]1.52-1.09 [-1.98, -0.10]2.38 [1.41, 3.35]37% [23%, 52%]80%87%——2026-08-01 → 2026-08-30
tmax00Zbilinear365d30 1 QC1.70 [1.07, 2.32]1.52-1.09 [-2.12, 0.12]2.38 [1.30, 3.35]37% [23%, 52%]80%87%——2026-08-01 → 2026-08-30
tmax00Zbilinearall30 1 QC1.70 [1.13, 2.41]1.52-1.09 [-2.14, -0.14]2.38 [1.37, 3.51]37% [23%, 51%]80%87%——2026-08-01 → 2026-08-30
tmax00Znearest30d30 1 QC1.72 [1.38, 2.11]1.75-0.11 [-1.14, 0.77]2.41 [1.73, 3.08]47% [33%, 60%]67%83%——2026-08-01 → 2026-08-30
tmax00Znearest90d30 1 QC1.72 [1.36, 2.17]1.75-0.11 [-1.20, 0.99]2.41 [1.63, 3.22]47% [32%, 63%]67%83%——2026-08-01 → 2026-08-30
tmax00Znearest365d30 1 QC1.72 [1.33, 2.18]1.75-0.11 [-1.24, 1.21]2.41 [1.63, 3.21]47% [31%, 61%]67%83%——2026-08-01 → 2026-08-30
tmax00Znearestall30 1 QC1.72 [1.32, 2.27]1.75-0.11 [-1.25, 0.98]2.41 [1.60, 3.40]47% [33%, 62%]67%83%——2026-08-01 → 2026-08-30
tmin00Zbilinear30d30 1 QC3.58 [3.00, 4.26]2.01+3.28 [2.71, 3.89]4.11 [3.47, 4.72]7% [0%, 13%]30%50%——2026-08-01 → 2026-08-30
tmin00Zbilinear90d30 1 QC3.58 [2.97, 4.27]2.01+3.28 [2.78, 3.88]4.11 [3.42, 4.75]7% [0%, 15%]30%50%——2026-08-01 → 2026-08-30
tmin00Zbilinear365d30 1 QC3.58 [2.89, 4.27]2.01+3.28 [2.71, 3.89]4.11 [3.34, 4.76]7% [0%, 15%]30%50%——2026-08-01 → 2026-08-30
tmin00Zbilinearall30 1 QC3.58 [2.95, 4.28]2.01+3.28 [2.70, 3.92]4.11 [3.38, 4.82]7% [0%, 17%]30%50%——2026-08-01 → 2026-08-30
tmin00Znearest30d30 1 QC2.91 [2.27, 3.61]1.99+2.45 [1.87, 3.03]3.45 [2.80, 4.09]23% [10%, 40%]43%57%——2026-08-01 → 2026-08-30
tmin00Znearest90d30 1 QC2.91 [2.26, 3.68]1.99+2.45 [1.93, 3.02]3.45 [2.69, 4.09]23% [5%, 41%]43%57%——2026-08-01 → 2026-08-30
tmin00Znearest365d30 1 QC2.91 [2.14, 3.67]1.99+2.45 [1.87, 3.03]3.45 [2.65, 4.12]23% [0%, 43%]43%57%——2026-08-01 → 2026-08-30
tmin00Znearestall30 1 QC2.91 [2.21, 3.72]1.99+2.45 [1.85, 3.06]3.45 [2.68, 4.19]23% [6%, 39%]43%57%——2026-08-01 → 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 NCEP GFS at KEWR, lead day 0, 00Z bilinear tmax+10+50-5-102026-08-01: -1.48 °F2026-08-02: -0.81 °F2026-08-03: -8.68 °F2026-08-04: +0.66 °F2026-08-05: -1.99 °F2026-08-06: -1.3 °F2026-08-07: -2 °F2026-08-08: +1.48 °F2026-08-09: +1.38 °F2026-08-10: -1.91 °F2026-08-11: -0.28 °F2026-08-12: +0.41 °F2026-08-13: +0.24 °F2026-08-14: +1.31 °F2026-08-15: -1.09 °F2026-08-16: +1.1 °F2026-08-17: -0.39 °F2026-08-18: -3.82 °F2026-08-19: -2.37 °F2026-08-20: -2.14 °F2026-08-21: -0.76 °F2026-08-22: -1.66 °F2026-08-23: -3.67 °F2026-08-24: -0.86 °F2026-08-25: -4.47 °F2026-08-26: -1.41 °F2026-08-27: +0.22 °F2026-08-28: -0.77 °F2026-08-29: +0.47 °F2026-08-30: +1.96 °F2026-08-012026-08-30°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 (30 days, newest first) · download CSV
Climatological dayError °F
2026-08-30+1.96
2026-08-29+0.47
2026-08-28-0.77
2026-08-27+0.22
2026-08-26-1.41
2026-08-25-4.47
2026-08-24-0.86
2026-08-23-3.67
2026-08-22-1.66
2026-08-21-0.76
2026-08-20-2.14
2026-08-19-2.37
2026-08-18-3.82
2026-08-17-0.39
2026-08-16+1.10
2026-08-15-1.09
2026-08-14+1.31
2026-08-13+0.24
2026-08-12+0.41
2026-08-11-0.28
2026-08-10-1.91
2026-08-09+1.38
2026-08-08+1.48
2026-08-07-2.00
2026-08-06-1.30
2026-08-05-1.99
2026-08-04+0.66
2026-08-03-8.68
2026-08-02-0.81
2026-08-01-1.48

Error distribution

Distribution of the signed daily error in °F for NCEP GFS at KEWR, lead day 0-10 to -9 °F: 0 days-9 to -8 °F: 1 day-8 to -7 °F: 0 days-7 to -6 °F: 0 days-6 to -5 °F: 0 days-5 to -4 °F: 1 day-4 to -3 °F: 2 days-3 to -2 °F: 2 days-2 to -1 °F: 8 days-1 to 0 °F: 6 days0 to 1 °F: 5 days1 to 2 °F: 5 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| 1.35 · P90 |e| 3.69 °F-100+10 °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
-10.00-9.000
-9.00-8.001
-8.00-7.000
-7.00-6.000
-6.00-5.000
-5.00-4.001
-4.00-3.002
-3.00-2.002
-2.00-1.008
-1.00+0.006
+0.00+1.005
+1.00+2.005
+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
2026-08301.70 -1.09

Availability

ModelScored period DaysCoverage
NCEP GFS2026-08-01 → 2026-08-30 30
NCEP GFS2026-08-01 → 2026-08-30 30

Compared with other models

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

Other modelCommon days MAE difference °FDistinguishable
ECMWF AIFS Single 30 -0.88 [-1.26, -0.50] yes
Aurora (GFS init) 2 -2.74 [-3.55, -1.94] yes
Aurora (IFS init) 3 -3.15 [-6.39, 1.02] no
FourCastNet v2 (GFS init) 2 -1.57 [-2.15, -0.99] yes
FourCastNet v2 (IFS init) 3 -3.69 [-8.23, -1.38] yes
GraphCast (GFS init) 2 -2.66 [-3.91, -1.42] yes
GraphCast (IFS init) 28 -2.81 [-3.17, -2.36] yes
ECMWF IFS HRES 24 -1.98 [-2.57, -1.15] yes
Pangu-Weather (GFS init) 2 -0.06 [-0.30, 0.18] no
Pangu-Weather (IFS init) 3 -1.40 [-3.67, -0.18] yes

Cite this page

ShortCastCheck, KEWR gfs lead 0, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KEWR/model/gfs/lead/0/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KEWR (Newark Liberty), model gfs, lead day 0. Methodology version 0.2, schema version 0.1, data through 2026-08-30. Accessed 2026-08-31. https://castcheck.zifanzhang.com/station/KEWR/model/gfs/lead/0/

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