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

New Orleans Intl · GraphCast (IFS init) · lead day 1

KMSY · 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 QC5.07 [4.65, 5.46]1.20-4.99 [-5.40, -4.53]5.27 [4.80, 5.68]0% [0%, 0%]4%4%-1.63+0.382026-08-02 → 2026-08-30
tmax00Zbilinear90d27 1 QC5.07 [4.63, 5.47]1.20-4.99 [-5.44, -4.48]5.27 [4.79, 5.69]0% [0%, 0%]4%4%-1.63+0.382026-08-02 → 2026-08-30
tmax00Zbilinear365d33 1 QC5.29 [4.79, 5.85]1.46-5.22 [-5.81, -4.68]5.58 [4.98, 6.23]3% [0%, 11%]6%6%-0.66+0.542026-01-02 → 2026-08-30
tmax00Zbilinearall33 1 QC5.29 [4.82, 5.84]1.46-5.22 [-5.78, -4.71]5.58 [5.03, 6.20]3% [0%, 10%]6%6%-0.66+0.542026-01-02 → 2026-08-30
tmax00Znearest30d27 1 QC5.00 [4.58, 5.39]1.21-4.91 [-5.34, -4.45]5.21 [4.72, 5.63]0% [0%, 0%]4%4%-1.60+0.382026-08-02 → 2026-08-30
tmax00Znearest90d27 1 QC5.00 [4.55, 5.40]1.21-4.91 [-5.37, -4.40]5.21 [4.70, 5.64]0% [0%, 0%]4%4%-1.60+0.382026-08-02 → 2026-08-30
tmax00Znearest365d33 1 QC5.21 [4.71, 5.77]1.46-5.14 [-5.73, -4.61]5.51 [4.90, 6.13]3% [0%, 11%]6%6%-0.64+0.542026-01-02 → 2026-08-30
tmax00Znearestall33 1 QC5.21 [4.74, 5.76]1.46-5.14 [-5.70, -4.63]5.51 [4.94, 6.12]3% [0%, 10%]6%6%-0.64+0.542026-01-02 → 2026-08-30
tmax12Zbilinear30d27 1 QC5.57 [5.23, 5.88]1.28-5.46 [-5.81, -4.98]5.77 [5.43, 6.11]0% [0%, 0%]4%7%-1.89+0.352026-08-02 → 2026-08-30
tmax12Zbilinear90d27 1 QC5.57 [5.22, 5.87]1.28-5.46 [-5.82, -4.92]5.77 [5.45, 6.13]0% [0%, 0%]4%7%-1.89+0.352026-08-02 → 2026-08-30
tmax12Zbilinear365d32 1 QC5.64 [5.30, 5.98]1.45-5.54 [-5.91, -5.11]5.91 [5.54, 6.33]3% [0%, 12%]6%9%-0.73+0.552026-01-02 → 2026-08-30
tmax12Zbilinearall32 1 QC5.64 [5.33, 5.96]1.45-5.54 [-5.93, -5.12]5.91 [5.54, 6.37]3% [0%, 11%]6%9%-0.73+0.552026-01-02 → 2026-08-30
tmax12Znearest30d27 1 QC5.51 [5.17, 5.83]1.29-5.39 [-5.74, -4.92]5.71 [5.36, 6.06]0% [0%, 0%]4%7%-1.86+0.342026-08-02 → 2026-08-30
tmax12Znearest90d27 1 QC5.51 [5.17, 5.81]1.29-5.39 [-5.75, -4.84]5.71 [5.38, 6.08]0% [0%, 0%]4%7%-1.86+0.342026-08-02 → 2026-08-30
tmax12Znearest365d32 1 QC5.57 [5.23, 5.91]1.45-5.47 [-5.83, -5.03]5.84 [5.48, 6.26]3% [0%, 12%]6%9%-0.71+0.552026-01-02 → 2026-08-30
tmax12Znearestall32 1 QC5.57 [5.26, 5.89]1.45-5.47 [-5.85, -5.05]5.84 [5.47, 6.29]3% [0%, 11%]6%9%-0.71+0.552026-01-02 → 2026-08-30
tmin00Zbilinear30d27 1 QC3.06 [2.62, 3.58]1.25+2.82 [2.07, 3.42]3.32 [2.76, 3.92]4% [0%, 11%]22%44%-0.92+0.232026-08-02 → 2026-08-30
tmin00Zbilinear90d27 1 QC3.06 [2.53, 3.56]1.25+2.82 [1.83, 3.39]3.32 [2.65, 3.88]4% [0%, 11%]22%44%-0.92+0.232026-08-02 → 2026-08-30
tmin00Zbilinear365d33 1 QC3.04 [2.57, 3.51]1.53+2.76 [1.94, 3.31]3.45 [2.82, 4.05]6% [0%, 14%]27%48%-0.21+0.422026-01-02 → 2026-08-30
tmin00Zbilinearall33 1 QC3.04 [2.51, 3.53]1.53+2.76 [1.90, 3.29]3.45 [2.77, 4.04]6% [0%, 14%]27%48%-0.21+0.422026-01-02 → 2026-08-30
tmin00Znearest30d27 1 QC2.98 [2.52, 3.51]1.25+2.72 [1.96, 3.32]3.24 [2.68, 3.83]7% [0%, 16%]22%59%-0.87+0.232026-08-02 → 2026-08-30
tmin00Znearest90d27 1 QC2.98 [2.44, 3.50]1.25+2.72 [1.73, 3.30]3.24 [2.56, 3.81]7% [0%, 17%]22%59%-0.87+0.232026-08-02 → 2026-08-30
tmin00Znearest365d33 1 QC2.96 [2.51, 3.44]1.53+2.66 [1.84, 3.22]3.38 [2.75, 3.98]12% [0%, 25%]27%61%-0.18+0.422026-01-02 → 2026-08-30
tmin00Znearestall33 1 QC2.96 [2.43, 3.46]1.53+2.66 [1.81, 3.19]3.38 [2.69, 3.99]12% [2%, 25%]27%61%-0.18+0.422026-01-02 → 2026-08-30
tmin12Zbilinear30d27 1 QC2.81 [2.37, 3.43]1.31+2.54 [1.79, 3.22]3.14 [2.56, 3.86]7% [0%, 16%]33%59%-0.76+0.192026-08-02 → 2026-08-30
tmin12Zbilinear90d27 1 QC2.81 [2.33, 3.45]1.31+2.54 [1.55, 3.15]3.14 [2.50, 3.86]7% [0%, 17%]33%59%-0.76+0.192026-08-02 → 2026-08-30
tmin12Zbilinear365d32 1 QC2.75 [2.32, 3.31]1.51+2.49 [1.63, 3.06]3.18 [2.58, 3.85]12% [0%, 27%]38%59%-0.10+0.432026-01-02 → 2026-08-30
tmin12Zbilinearall32 1 QC2.75 [2.31, 3.33]1.51+2.49 [1.66, 3.10]3.18 [2.55, 3.87]12% [0%, 28%]38%59%-0.10+0.432026-01-02 → 2026-08-30
tmin12Znearest30d27 1 QC2.73 [2.29, 3.37]1.31+2.45 [1.70, 3.12]3.06 [2.48, 3.79]7% [0%, 16%]33%59%-0.71+0.192026-08-02 → 2026-08-30
tmin12Znearest90d27 1 QC2.73 [2.24, 3.38]1.31+2.45 [1.45, 3.06]3.06 [2.43, 3.79]7% [0%, 17%]33%59%-0.71+0.192026-08-02 → 2026-08-30
tmin12Znearest365d32 1 QC2.68 [2.24, 3.25]1.51+2.40 [1.54, 2.97]3.12 [2.51, 3.79]16% [0%, 37%]38%59%-0.07+0.432026-01-02 → 2026-08-30
tmin12Znearestall32 1 QC2.68 [2.22, 3.29]1.51+2.40 [1.57, 3.01]3.12 [2.47, 3.82]16% [2%, 36%]38%59%-0.07+0.432026-01-02 → 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 KMSY, lead day 1, 00Z bilinear tmax+10+50-5-102026-08-02: +1.1 °F2026-08-03: -7.56 °F2026-08-04: -5.34 °F2026-08-05: -6.09 °F2026-08-06: -6.96 °F2026-08-07: -4.09 °F2026-08-08: -4.1 °F2026-08-09: -3.16 °F2026-08-10: -6.74 °F2026-08-11: -6.11 °F2026-08-12: -6.99 °F2026-08-13: -7.79 °F2026-08-14: -4.33 °F2026-08-15: -4.87 °F2026-08-16: -4.01 °F2026-08-17: -3.22 °F2026-08-18: -4.07 °F2026-08-19: -4.61 °F2026-08-20: -5.21 °F2026-08-21: -5.53 °F2026-08-22: -5.18 °F2026-08-23: -4.93 °F2026-08-24: -3.68 °F2026-08-25: -6.02 °F2026-08-26: -4.65 °F2026-08-29: -4.94 °F2026-08-30: -5.58 °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
2026-08-30-5.58
2026-08-29-4.94
2026-08-28—
2026-08-27—
2026-08-26-4.65
2026-08-25-6.02
2026-08-24-3.68
2026-08-23-4.93
2026-08-22-5.18
2026-08-21-5.53
2026-08-20-5.21
2026-08-19-4.61
2026-08-18-4.07
2026-08-17-3.22
2026-08-16-4.01
2026-08-15-4.87
2026-08-14-4.33
2026-08-13-7.79
2026-08-12-6.99
2026-08-11-6.11
2026-08-10-6.74
2026-08-09-3.16
2026-08-08-4.10
2026-08-07-4.09
2026-08-06-6.96
2026-08-05-6.09
2026-08-04-5.34
2026-08-03-7.56
2026-08-02+1.10

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KMSY, lead day 1-10 to -9 °F: 0 days-9 to -8 °F: 1 day-8 to -7 °F: 4 days-7 to -6 °F: 7 days-6 to -5 °F: 6 days-5 to -4 °F: 10 days-4 to -3 °F: 3 days-3 to -2 °F: 0 days-2 to -1 °F: 0 days-1 to 0 °F: 1 day0 to 1 °F: 0 days1 to 2 °F: 1 day2 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| 5.21 · P90 |e| 7.74 °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
-9.00-8.001
-8.00-7.004
-7.00-6.007
-6.00-5.006
-5.00-4.0010
-4.00-3.003
-3.00-2.000
-2.00-1.000
-1.00+0.001
+0.00+1.000
+1.00+2.001
+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
2026-08275.07 -4.99
2026-0166.27 -6.27

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 +0.83 [0.18, 1.48] yes
Aurora (GFS init) 1 -1.63 [-1.63, -1.63] yes
Aurora (IFS init) 2 -1.64 [-1.72, -1.55] yes
FourCastNet v2 (GFS init) 1 +2.70 [2.70, 2.70] yes
FourCastNet v2 (IFS init) 2 +2.08 [0.85, 3.32] yes
NCEP GFS 27 +0.74 [-0.20, 1.43] no
GraphCast (GFS init) 1 +0.27 [0.27, 0.27] yes
ECMWF IFS HRES 21 +0.96 [-1.63, 1.79] no
Pangu-Weather (GFS init) 1 +0.14 [0.14, 0.14] yes
Pangu-Weather (IFS init) 2 +1.02 [0.31, 1.73] yes
Persistence (baseline) 27 +3.14 [0.93, 4.05] yes

Cite this page

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

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KMSY (New Orleans Intl), 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/KMSY/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