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 · Pangu-Weather (IFS init) · lead day 1

KEWR · pangu_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, PANG_v100, starting 2026-08-28 — 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
tmax00Zbilinear30d2 1 QC0.62 [0.01, 1.22]0.62+0.60 [-0.01, 1.22]0.86 [0.01, 1.22]50% [0%, 100%]100%100%+0.85+0.852026-08-29 → 2026-08-30
tmax00Zbilinear90d2 1 QC0.62 [0.01, 1.22]0.62+0.60 [-0.01, 1.22]0.86 [0.01, 1.22]50% [0%, 100%]100%100%+0.85+0.852026-08-29 → 2026-08-30
tmax00Zbilinear365d2 1 QC0.62 [0.01, 1.22]0.62+0.60 [-0.01, 1.22]0.86 [0.01, 1.22]50% [0%, 100%]100%100%+0.85+0.852026-08-29 → 2026-08-30
tmax00Zbilinearall2 1 QC0.62 [0.01, 1.22]0.62+0.60 [-0.01, 1.22]0.86 [0.01, 1.22]50% [0%, 100%]100%100%+0.85+0.852026-08-29 → 2026-08-30
tmax00Znearest30d2 1 QC0.74 [0.16, 1.31]0.58+0.74 [0.16, 1.31]0.94 [0.16, 1.31]50% [0%, 100%]100%100%+0.82+0.862026-08-29 → 2026-08-30
tmax00Znearest90d2 1 QC0.74 [0.16, 1.31]0.58+0.74 [0.16, 1.31]0.94 [0.16, 1.31]50% [0%, 100%]100%100%+0.82+0.862026-08-29 → 2026-08-30
tmax00Znearest365d2 1 QC0.74 [0.16, 1.31]0.58+0.74 [0.16, 1.31]0.94 [0.16, 1.31]50% [0%, 100%]100%100%+0.82+0.862026-08-29 → 2026-08-30
tmax00Znearestall2 1 QC0.74 [0.16, 1.31]0.58+0.74 [0.16, 1.31]0.94 [0.16, 1.31]50% [0%, 100%]100%100%+0.82+0.862026-08-29 → 2026-08-30
tmax12Zbilinear30d2 1 QC1.41 [1.02, 1.80]1.41+0.39 [-1.02, 1.80]1.46 [1.02, 1.80]0% [0%, 0%]100%100%+0.65+0.652026-08-29 → 2026-08-30
tmax12Zbilinear90d2 1 QC1.41 [1.02, 1.80]1.41+0.39 [-1.02, 1.80]1.46 [1.02, 1.80]0% [0%, 0%]100%100%+0.65+0.652026-08-29 → 2026-08-30
tmax12Zbilinear365d2 1 QC1.41 [1.02, 1.80]1.41+0.39 [-1.02, 1.80]1.46 [1.02, 1.80]0% [0%, 0%]100%100%+0.65+0.652026-08-29 → 2026-08-30
tmax12Zbilinearall2 1 QC1.41 [1.02, 1.80]1.41+0.39 [-1.02, 1.80]1.46 [1.02, 1.80]0% [0%, 0%]100%100%+0.65+0.652026-08-29 → 2026-08-30
tmax12Znearest30d2 1 QC1.33 [0.81, 1.85]1.33+0.52 [-0.81, 1.85]1.43 [0.81, 1.85]50% [0%, 100%]100%100%+0.67+0.672026-08-29 → 2026-08-30
tmax12Znearest90d2 1 QC1.33 [0.81, 1.85]1.33+0.52 [-0.81, 1.85]1.43 [0.81, 1.85]50% [0%, 100%]100%100%+0.67+0.672026-08-29 → 2026-08-30
tmax12Znearest365d2 1 QC1.33 [0.81, 1.85]1.33+0.52 [-0.81, 1.85]1.43 [0.81, 1.85]50% [0%, 100%]100%100%+0.67+0.672026-08-29 → 2026-08-30
tmax12Znearestall2 1 QC1.33 [0.81, 1.85]1.33+0.52 [-0.81, 1.85]1.43 [0.81, 1.85]50% [0%, 100%]100%100%+0.67+0.672026-08-29 → 2026-08-30
tmin00Zbilinear30d2 1 QC2.32 [1.26, 3.37]2.32+1.05 [-1.26, 3.37]2.54 [1.26, 3.37]0% [0%, 0%]50%50%+0.34+0.342026-08-29 → 2026-08-30
tmin00Zbilinear90d2 1 QC2.32 [1.26, 3.37]2.32+1.05 [-1.26, 3.37]2.54 [1.26, 3.37]0% [0%, 0%]50%50%+0.34+0.342026-08-29 → 2026-08-30
tmin00Zbilinear365d2 1 QC2.32 [1.26, 3.37]2.32+1.05 [-1.26, 3.37]2.54 [1.26, 3.37]0% [0%, 0%]50%50%+0.34+0.342026-08-29 → 2026-08-30
tmin00Zbilinearall2 1 QC2.32 [1.26, 3.37]2.32+1.05 [-1.26, 3.37]2.54 [1.26, 3.37]0% [0%, 0%]50%50%+0.34+0.342026-08-29 → 2026-08-30
tmin00Znearest30d2 1 QC2.37 [2.34, 2.40]2.37-0.03 [-2.40, 2.34]2.37 [2.34, 2.40]0% [0%, 0%]0%100%+0.32+0.322026-08-29 → 2026-08-30
tmin00Znearest90d2 1 QC2.37 [2.34, 2.40]2.37-0.03 [-2.40, 2.34]2.37 [2.34, 2.40]0% [0%, 0%]0%100%+0.32+0.322026-08-29 → 2026-08-30
tmin00Znearest365d2 1 QC2.37 [2.34, 2.40]2.37-0.03 [-2.40, 2.34]2.37 [2.34, 2.40]0% [0%, 0%]0%100%+0.32+0.322026-08-29 → 2026-08-30
tmin00Znearestall2 1 QC2.37 [2.34, 2.40]2.37-0.03 [-2.40, 2.34]2.37 [2.34, 2.40]0% [0%, 0%]0%100%+0.32+0.322026-08-29 → 2026-08-30
tmin12Zbilinear30d2 1 QC0.99 [0.47, 1.52]0.53+0.99 [0.47, 1.52]1.12 [0.47, 1.52]50% [0%, 100%]100%100%+0.72+0.852026-08-29 → 2026-08-30
tmin12Zbilinear90d2 1 QC0.99 [0.47, 1.52]0.53+0.99 [0.47, 1.52]1.12 [0.47, 1.52]50% [0%, 100%]100%100%+0.72+0.852026-08-29 → 2026-08-30
tmin12Zbilinear365d2 1 QC0.99 [0.47, 1.52]0.53+0.99 [0.47, 1.52]1.12 [0.47, 1.52]50% [0%, 100%]100%100%+0.72+0.852026-08-29 → 2026-08-30
tmin12Zbilinearall2 1 QC0.99 [0.47, 1.52]0.53+0.99 [0.47, 1.52]1.12 [0.47, 1.52]50% [0%, 100%]100%100%+0.72+0.852026-08-29 → 2026-08-30
tmin12Znearest30d2 1 QC0.52 [0.41, 0.64]0.52+0.11 [-0.41, 0.64]0.54 [0.41, 0.64]100% [100%, 100%]100%100%+0.85+0.852026-08-29 → 2026-08-30
tmin12Znearest90d2 1 QC0.52 [0.41, 0.64]0.52+0.11 [-0.41, 0.64]0.54 [0.41, 0.64]100% [100%, 100%]100%100%+0.85+0.852026-08-29 → 2026-08-30
tmin12Znearest365d2 1 QC0.52 [0.41, 0.64]0.52+0.11 [-0.41, 0.64]0.54 [0.41, 0.64]100% [100%, 100%]100%100%+0.85+0.852026-08-29 → 2026-08-30
tmin12Znearestall2 1 QC0.52 [0.41, 0.64]0.52+0.11 [-0.41, 0.64]0.54 [0.41, 0.64]100% [100%, 100%]100%100%+0.85+0.852026-08-29 → 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 Pangu-Weather (IFS init) at KEWR, lead day 1, 00Z bilinear tmax+2+10-1-22026-08-29: -0.01 °F2026-08-30: +1.22 °F2026-08-292026-08-30°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 (2 days, newest first) · download CSV
Climatological dayError °F
2026-08-30+1.22
2026-08-29-0.01

Error distribution

Distribution of the signed daily error in °F for Pangu-Weather (IFS init) at KEWR, lead day 1-2 to -1.8 °F: 0 days-1.8 to -1.6 °F: 0 days-1.6 to -1.4 °F: 0 days-1.4 to -1.2 °F: 0 days-1.2 to -1 °F: 0 days-1 to -0.8 °F: 0 days-0.8 to -0.6 °F: 0 days-0.6 to -0.4 °F: 0 days-0.4 to -0.2 °F: 0 days-0.2 to 0 °F: 1 day0 to 0.2 °F: 0 days0.2 to 0.4 °F: 0 days0.4 to 0.6 °F: 0 days0.6 to 0.8 °F: 0 days0.8 to 1 °F: 0 days1 to 1.2 °F: 0 days1.2 to 1.4 °F: 1 day1.4 to 1.6 °F: 0 days1.6 to 1.8 °F: 0 days1.8 to 2 °F: 0 daysdashed: P50 |e| 0.62 · P90 |e| 1.1 °F-20+2 °Fn = 2 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
-2.00-1.800
-1.80-1.600
-1.60-1.400
-1.40-1.200
-1.20-1.000
-1.00-0.800
-0.80-0.600
-0.60-0.400
-0.40-0.200
-0.20+0.001
+0.00+0.200
+0.20+0.400
+0.40+0.600
+0.60+0.800
+0.80+1.000
+1.00+1.200
+1.20+1.401
+1.40+1.600
+1.60+1.800
+1.80+2.000

Month by month

00Z bilinear daily maximum, newest first.

Monthn MAE °FBias °F
2026-0820.62 +0.60

Availability

ModelScored period DaysCoverage
Pangu-Weather (IFS init)2026-08-29 → 2026-08-30 2
Pangu-Weather (IFS init)2026-08-29 → 2026-08-30 2
Pangu-Weather (IFS init)2026-08-29 → 2026-08-30 2
Pangu-Weather (IFS init)2026-08-29 → 2026-08-30 2

Compared with other models

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

Other modelCommon days MAE difference °FDistinguishable
ECMWF AIFS Single 2 -1.82 [-2.86, -0.79] yes
Aurora (GFS init) 1 -1.63 [-1.63, -1.63] yes
Aurora (IFS init) 2 -2.45 [-3.99, -0.91] yes
FourCastNet v2 (GFS init) 1 -0.79 [-0.79, -0.79] yes
FourCastNet v2 (IFS init) 2 -1.24 [-2.11, -0.36] yes
NCEP GFS 2 -1.90 [-2.80, -0.99] yes
GraphCast (GFS init) 1 -3.37 [-3.37, -3.37] yes
GraphCast (IFS init) 2 -3.73 [-4.70, -2.77] yes
ECMWF IFS HRES 2 -2.36 [-5.26, 0.54] no
Pangu-Weather (GFS init) 1 -0.71 [-0.71, -0.71] yes
Persistence (baseline) 2 -3.38 [-6.99, 0.22] no

Cite this page

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

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