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 4

KEWR · gfs · lead 4

Target day = initialization date + 4 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
tmax00Zbilinear30d26 1 QC2.59 [1.91, 3.50]2.57-1.22 [-2.39, 0.04]3.49 [2.52, 4.53]35% [17%, 50%]58%62%+0.37+0.332026-08-05 → 2026-08-30
tmax00Zbilinear90d26 1 QC2.59 [1.90, 3.56]2.57-1.22 [-2.57, 0.39]3.49 [2.48, 4.62]35% [14%, 53%]58%62%+0.37+0.332026-08-05 → 2026-08-30
tmax00Zbilinear365d26 1 QC2.59 [1.88, 3.59]2.57-1.22 [-2.59, 0.46]3.49 [2.47, 4.60]35% [12%, 54%]58%62%+0.37+0.332026-08-05 → 2026-08-30
tmax00Zbilinearall26 1 QC2.59 [1.89, 3.66]2.57-1.22 [-2.59, 0.49]3.49 [2.50, 4.68]35% [11%, 52%]58%62%+0.37+0.332026-08-05 → 2026-08-30
tmax00Znearest30d26 1 QC2.81 [2.06, 3.70]2.86-0.32 [-1.76, 1.22]3.74 [2.62, 4.82]27% [13%, 39%]42%54%+0.31+0.252026-08-05 → 2026-08-30
tmax00Znearest90d26 1 QC2.81 [2.02, 3.81]2.86-0.32 [-1.95, 1.68]3.74 [2.57, 4.93]27% [12%, 40%]42%54%+0.31+0.252026-08-05 → 2026-08-30
tmax00Znearest365d26 1 QC2.81 [1.95, 3.86]2.86-0.32 [-1.92, 1.77]3.74 [2.48, 5.00]27% [12%, 40%]42%54%+0.31+0.252026-08-05 → 2026-08-30
tmax00Znearestall26 1 QC2.81 [1.95, 3.90]2.86-0.32 [-2.00, 1.74]3.74 [2.49, 4.94]27% [11%, 40%]42%54%+0.31+0.252026-08-05 → 2026-08-30
tmax12Zbilinear30d26 1 QC3.52 [2.75, 4.36]2.75-2.11 [-3.51, -0.52]4.19 [3.18, 5.14]12% [4%, 21%]38%50%+0.14+0.282026-08-05 → 2026-08-30
tmax12Zbilinear90d26 1 QC3.52 [2.54, 4.48]2.75-2.11 [-3.66, -0.23]4.19 [2.93, 5.26]12% [0%, 22%]38%50%+0.14+0.282026-08-05 → 2026-08-30
tmax12Zbilinear365d26 1 QC3.52 [2.57, 4.44]2.75-2.11 [-3.78, -0.15]4.19 [2.96, 5.21]12% [0%, 22%]38%50%+0.14+0.282026-08-05 → 2026-08-30
tmax12Zbilinearall26 1 QC3.52 [2.49, 4.62]2.75-2.11 [-3.76, -0.23]4.19 [2.82, 5.35]12% [0%, 23%]38%50%+0.14+0.282026-08-05 → 2026-08-30
tmax12Znearest30d26 1 QC3.68 [2.68, 4.52]3.50-1.50 [-3.12, 0.42]4.64 [3.50, 5.54]23% [10%, 40%]35%54%+0.10+0.082026-08-05 → 2026-08-30
tmax12Znearest90d26 1 QC3.68 [2.47, 4.68]3.50-1.50 [-3.22, 0.64]4.64 [3.25, 5.70]23% [10%, 43%]35%54%+0.10+0.082026-08-05 → 2026-08-30
tmax12Znearest365d26 1 QC3.68 [2.54, 4.64]3.50-1.50 [-3.32, 0.88]4.64 [3.31, 5.65]23% [8%, 40%]35%54%+0.10+0.082026-08-05 → 2026-08-30
tmax12Znearestall26 1 QC3.68 [2.35, 4.80]3.50-1.50 [-3.31, 0.84]4.64 [3.14, 5.79]23% [9%, 44%]35%54%+0.10+0.082026-08-05 → 2026-08-30
tmin00Zbilinear30d26 1 QC4.12 [3.39, 4.86]2.39+3.80 [2.99, 4.50]4.77 [3.88, 5.41]15% [0%, 35%]19%38%-0.32+0.222026-08-05 → 2026-08-30
tmin00Zbilinear90d26 1 QC4.12 [3.39, 4.97]2.39+3.80 [3.03, 4.61]4.77 [3.87, 5.52]15% [0%, 34%]19%38%-0.32+0.222026-08-05 → 2026-08-30
tmin00Zbilinear365d26 1 QC4.12 [3.33, 4.94]2.39+3.80 [2.94, 4.62]4.77 [3.70, 5.50]15% [0%, 38%]19%38%-0.32+0.222026-08-05 → 2026-08-30
tmin00Zbilinearall26 1 QC4.12 [3.27, 5.01]2.39+3.80 [2.88, 4.66]4.77 [3.72, 5.47]15% [0%, 35%]19%38%-0.32+0.222026-08-05 → 2026-08-30
tmin00Znearest30d26 1 QC3.59 [2.83, 4.29]2.36+2.95 [2.16, 3.64]4.09 [3.25, 4.68]8% [0%, 18%]31%42%-0.15+0.232026-08-05 → 2026-08-30
tmin00Znearest90d26 1 QC3.59 [2.81, 4.39]2.36+2.95 [2.19, 3.75]4.09 [3.18, 4.74]8% [0%, 19%]31%42%-0.15+0.232026-08-05 → 2026-08-30
tmin00Znearest365d26 1 QC3.59 [2.63, 4.38]2.36+2.95 [2.11, 3.76]4.09 [2.99, 4.73]8% [0%, 20%]31%42%-0.15+0.232026-08-05 → 2026-08-30
tmin00Znearestall26 1 QC3.59 [2.65, 4.43]2.36+2.95 [2.05, 3.80]4.09 [3.09, 4.72]8% [0%, 19%]31%42%-0.15+0.232026-08-05 → 2026-08-30
tmin12Zbilinear30d26 1 QC3.56 [2.76, 4.55]2.40+3.00 [2.19, 3.92]4.21 [3.36, 5.03]8% [0%, 14%]31%50%-0.14+0.222026-08-05 → 2026-08-30
tmin12Zbilinear90d26 1 QC3.56 [2.74, 4.75]2.40+3.00 [2.14, 4.09]4.21 [3.27, 5.17]8% [0%, 14%]31%50%-0.14+0.222026-08-05 → 2026-08-30
tmin12Zbilinear365d26 1 QC3.56 [2.66, 4.78]2.40+3.00 [2.10, 4.04]4.21 [3.21, 5.18]8% [0%, 14%]31%50%-0.14+0.222026-08-05 → 2026-08-30
tmin12Zbilinearall26 1 QC3.56 [2.51, 4.73]2.40+3.00 [2.10, 4.10]4.21 [2.98, 5.24]8% [0%, 14%]31%50%-0.14+0.222026-08-05 → 2026-08-30
tmin12Znearest30d26 1 QC3.12 [2.18, 4.17]2.61+2.16 [1.28, 3.06]3.85 [2.95, 4.59]19% [4%, 36%]38%54%-0.00+0.152026-08-05 → 2026-08-30
tmin12Znearest90d26 1 QC3.12 [2.12, 4.31]2.61+2.16 [1.23, 3.28]3.85 [2.92, 4.70]19% [0%, 37%]38%54%-0.00+0.152026-08-05 → 2026-08-30
tmin12Znearest365d26 1 QC3.12 [2.04, 4.32]2.61+2.16 [1.24, 3.24]3.85 [2.79, 4.73]19% [0%, 40%]38%54%-0.00+0.152026-08-05 → 2026-08-30
tmin12Znearestall26 1 QC3.12 [1.96, 4.39]2.61+2.16 [1.15, 3.33]3.85 [2.69, 4.75]19% [0%, 41%]38%54%-0.00+0.152026-08-05 → 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 4, 00Z bilinear tmax+10+50-5-102026-08-05: -5.05 °F2026-08-06: -3.22 °F2026-08-07: -0.85 °F2026-08-08: -0.52 °F2026-08-09: +1.54 °F2026-08-10: +1.09 °F2026-08-11: +2.02 °F2026-08-12: -1.33 °F2026-08-13: -6.37 °F2026-08-14: -9.89 °F2026-08-15: -5.06 °F2026-08-16: +1.79 °F2026-08-17: +1.06 °F2026-08-18: +0.2 °F2026-08-19: -0.47 °F2026-08-20: -4.85 °F2026-08-21: -0.32 °F2026-08-22: -1.52 °F2026-08-23: -4.83 °F2026-08-24: -3.47 °F2026-08-25: +0.73 °F2026-08-26: -0.81 °F2026-08-27: +4.92 °F2026-08-28: +0.59 °F2026-08-29: -0.99 °F2026-08-30: +3.79 °F2026-08-052026-08-30°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 (26 days, newest first) · download CSV
Climatological dayError °F
2026-08-30+3.79
2026-08-29-0.99
2026-08-28+0.59
2026-08-27+4.92
2026-08-26-0.81
2026-08-25+0.73
2026-08-24-3.47
2026-08-23-4.83
2026-08-22-1.52
2026-08-21-0.32
2026-08-20-4.85
2026-08-19-0.47
2026-08-18+0.20
2026-08-17+1.06
2026-08-16+1.79
2026-08-15-5.06
2026-08-14-9.89
2026-08-13-6.37
2026-08-12-1.33
2026-08-11+2.02
2026-08-10+1.09
2026-08-09+1.54
2026-08-08-0.52
2026-08-07-0.85
2026-08-06-3.22
2026-08-05-5.05

Error distribution

Distribution of the signed daily error in °F for NCEP GFS at KEWR, lead day 4-10 to -9 °F: 1 day-9 to -8 °F: 0 days-8 to -7 °F: 0 days-7 to -6 °F: 1 day-6 to -5 °F: 2 days-5 to -4 °F: 2 days-4 to -3 °F: 2 days-3 to -2 °F: 0 days-2 to -1 °F: 2 days-1 to 0 °F: 6 days0 to 1 °F: 3 days1 to 2 °F: 4 days2 to 3 °F: 1 day3 to 4 °F: 1 day4 to 5 °F: 1 day5 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| 1.53 · P90 |e| 5.05 °F-100+10 °Fn = 26 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
-10.00-9.001
-9.00-8.000
-8.00-7.000
-7.00-6.001
-6.00-5.002
-5.00-4.002
-4.00-3.002
-3.00-2.000
-2.00-1.002
-1.00+0.006
+0.00+1.003
+1.00+2.004
+2.00+3.001
+3.00+4.001
+4.00+5.001
+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
2026-08262.59 -1.22

Availability

ModelScored period DaysCoverage
NCEP GFS2026-08-05 → 2026-08-30 26
NCEP GFS2026-08-05 → 2026-08-30 26
NCEP GFS2026-08-05 → 2026-08-30 26
NCEP GFS2026-08-05 → 2026-08-30 26

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 26 -0.90 [-1.86, 0.14] no
GraphCast (IFS init) 25 -2.21 [-3.91, -0.62] yes
ECMWF IFS HRES 20 -0.29 [-1.32, 1.56] no
Persistence (baseline) 26 -1.49 [-3.16, -0.29] yes

Cite this page

ShortCastCheck, KEWR gfs lead 4, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KEWR/model/gfs/lead/4/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KEWR (Newark Liberty), model gfs, lead day 4. 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/4/

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