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 0

KMSY · graphcast_ifs · 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, 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
tmax00Zbilinear30d28 1 QC4.83 [4.48, 5.15]1.25-4.76 [-5.14, -4.29]5.06 [4.68, 5.38]0% [0%, 0%]4%14%——2026-08-01 → 2026-08-30
tmax00Zbilinear90d28 1 QC4.83 [4.36, 5.23]1.25-4.76 [-5.22, -4.14]5.06 [4.65, 5.42]0% [0%, 0%]4%14%——2026-08-01 → 2026-08-30
tmax00Zbilinear365d34 1 QC4.95 [4.56, 5.40]1.45-4.89 [-5.38, -4.37]5.27 [4.83, 5.79]3% [0%, 11%]6%15%——2026-01-01 → 2026-08-30
tmax00Zbilinearall34 1 QC4.95 [4.54, 5.39]1.45-4.89 [-5.37, -4.35]5.27 [4.81, 5.76]3% [0%, 10%]6%15%——2026-01-01 → 2026-08-30
tmax00Znearest30d28 1 QC4.76 [4.42, 5.07]1.26-4.68 [-5.07, -4.22]4.99 [4.61, 5.31]0% [0%, 0%]7%14%——2026-08-01 → 2026-08-30
tmax00Znearest90d28 1 QC4.76 [4.29, 5.15]1.26-4.68 [-5.15, -4.07]4.99 [4.57, 5.36]0% [0%, 0%]7%14%——2026-08-01 → 2026-08-30
tmax00Znearest365d34 1 QC4.88 [4.48, 5.32]1.45-4.81 [-5.30, -4.29]5.20 [4.75, 5.71]3% [0%, 11%]9%15%——2026-01-01 → 2026-08-30
tmax00Znearestall34 1 QC4.88 [4.48, 5.30]1.45-4.81 [-5.29, -4.27]5.20 [4.73, 5.68]3% [0%, 10%]9%15%——2026-01-01 → 2026-08-30
tmin00Zbilinear30d28 1 QC3.11 [2.64, 3.51]1.03+2.98 [2.31, 3.50]3.34 [2.84, 3.77]7% [0%, 18%]14%43%——2026-08-01 → 2026-08-30
tmin00Zbilinear90d28 1 QC3.11 [2.49, 3.53]1.03+2.98 [2.01, 3.53]3.34 [2.70, 3.78]7% [0%, 21%]14%43%——2026-08-01 → 2026-08-30
tmin00Zbilinear365d34 1 QC3.26 [2.70, 3.82]1.32+3.12 [2.29, 3.73]3.65 [2.99, 4.33]12% [0%, 28%]18%41%——2026-01-01 → 2026-08-30
tmin00Zbilinearall34 1 QC3.26 [2.64, 3.78]1.32+3.12 [2.21, 3.72]3.65 [2.92, 4.30]12% [0%, 26%]18%41%——2026-01-01 → 2026-08-30
tmin00Znearest30d28 1 QC3.02 [2.55, 3.42]1.04+2.88 [2.21, 3.42]3.26 [2.75, 3.70]7% [0%, 18%]18%43%——2026-08-01 → 2026-08-30
tmin00Znearest90d28 1 QC3.02 [2.40, 3.44]1.04+2.88 [1.92, 3.44]3.26 [2.61, 3.71]7% [0%, 21%]18%43%——2026-08-01 → 2026-08-30
tmin00Znearest365d34 1 QC3.17 [2.61, 3.74]1.33+3.02 [2.21, 3.63]3.57 [2.90, 4.26]12% [0%, 28%]21%41%——2026-01-01 → 2026-08-30
tmin00Znearestall34 1 QC3.17 [2.56, 3.70]1.33+3.02 [2.13, 3.63]3.57 [2.83, 4.23]12% [0%, 26%]21%41%——2026-01-01 → 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 GraphCast (IFS init) at KMSY, lead day 0, 00Z bilinear tmax+10+50-5-102026-08-01: -2.96 °F2026-08-02: +1.03 °F2026-08-03: -6.29 °F2026-08-04: -4.7 °F2026-08-05: -6.44 °F2026-08-06: -6.16 °F2026-08-07: -5.33 °F2026-08-08: -2.46 °F2026-08-09: -2.07 °F2026-08-10: -7.5 °F2026-08-11: -5.54 °F2026-08-12: -6.95 °F2026-08-13: -6.14 °F2026-08-14: -4.15 °F2026-08-15: -3.83 °F2026-08-16: -5.21 °F2026-08-17: -3.35 °F2026-08-18: -4.22 °F2026-08-19: -4.83 °F2026-08-20: -4.95 °F2026-08-21: -5.14 °F2026-08-22: -5.62 °F2026-08-23: -4.28 °F2026-08-24: -4.14 °F2026-08-25: -6.66 °F2026-08-28: -4.72 °F2026-08-29: -4.48 °F2026-08-30: -6.16 °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
2026-08-30-6.16
2026-08-29-4.48
2026-08-28-4.72
2026-08-27—
2026-08-26—
2026-08-25-6.66
2026-08-24-4.14
2026-08-23-4.28
2026-08-22-5.62
2026-08-21-5.14
2026-08-20-4.95
2026-08-19-4.83
2026-08-18-4.22
2026-08-17-3.35
2026-08-16-5.21
2026-08-15-3.83
2026-08-14-4.15
2026-08-13-6.14
2026-08-12-6.95
2026-08-11-5.54
2026-08-10-7.50
2026-08-09-2.07
2026-08-08-2.46
2026-08-07-5.33
2026-08-06-6.16
2026-08-05-6.44
2026-08-04-4.70
2026-08-03-6.29
2026-08-02+1.03
2026-08-01-2.96

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KMSY, lead day 0-10 to -9 °F: 0 days-9 to -8 °F: 1 day-8 to -7 °F: 2 days-7 to -6 °F: 8 days-6 to -5 °F: 6 days-5 to -4 °F: 10 days-4 to -3 °F: 2 days-3 to -2 °F: 3 days-2 to -1 °F: 0 days-1 to 0 °F: 0 days0 to 1 °F: 1 day1 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| 5.04 · P90 |e| 6.93 °F-100+10 °Fn = 34 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
-8.00-7.002
-7.00-6.008
-6.00-5.006
-5.00-4.0010
-4.00-3.002
-3.00-2.003
-2.00-1.000
-1.00+0.000
+0.00+1.001
+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
2026-08284.83 -4.76
2026-0165.52 -5.50

Availability

ModelScored period DaysCoverage
GraphCast (IFS init)2026-01-01 → 2026-08-30 34
GraphCast (IFS init)2026-01-01 → 2026-08-30 34

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 28 +0.83 [0.43, 1.18] yes
Aurora (GFS init) 2 -1.71 [-1.75, -1.68] yes
Aurora (IFS init) 3 -1.54 [-2.24, -0.71] yes
FourCastNet v2 (GFS init) 2 +1.25 [0.75, 1.75] yes
FourCastNet v2 (IFS init) 3 +1.27 [-0.75, 3.85] no
NCEP GFS 28 -0.09 [-0.98, 0.55] no
GraphCast (GFS init) 2 -0.25 [-0.42, -0.08] yes
ECMWF IFS HRES 22 +0.50 [-0.66, 1.11] no
Pangu-Weather (GFS init) 2 +0.58 [-0.27, 1.44] no
Pangu-Weather (IFS init) 3 +0.85 [0.18, 1.27] yes

Cite this page

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

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