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 7

KMSY · graphcast_ifs · lead 7

Target day = initialization date + 7 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
tmax00Zbilinear30d23 1 QC5.38 [4.79, 6.02]1.34-5.38 [-6.02, -4.79]5.63 [5.02, 6.30]0% [0%, 0%]0%9%-0.85+0.542026-08-08 → 2026-08-30
tmax00Zbilinear90d23 1 QC5.38 [4.76, 6.11]1.34-5.38 [-6.11, -4.76]5.63 [4.96, 6.37]0% [0%, 0%]0%9%-0.85+0.542026-08-08 → 2026-08-30
tmax00Zbilinear365d29 1 QC5.71 [4.96, 6.61]1.47-5.71 [-6.61, -4.96]5.99 [5.17, 6.89]0% [0%, 0%]0%7%-0.29+0.682026-01-08 → 2026-08-30
tmax00Zbilinearall29 1 QC5.71 [4.98, 6.64]1.47-5.71 [-6.64, -4.98]5.99 [5.22, 6.94]0% [0%, 0%]0%7%-0.29+0.682026-01-08 → 2026-08-30
tmax00Znearest30d23 1 QC5.30 [4.70, 5.96]1.35-5.30 [-5.96, -4.70]5.56 [4.95, 6.25]0% [0%, 0%]0%9%-0.82+0.542026-08-08 → 2026-08-30
tmax00Znearest90d23 1 QC5.30 [4.68, 6.06]1.35-5.30 [-6.06, -4.68]5.56 [4.88, 6.32]0% [0%, 0%]0%9%-0.82+0.542026-08-08 → 2026-08-30
tmax00Znearest365d29 1 QC5.64 [4.87, 6.58]1.48-5.64 [-6.58, -4.87]5.94 [5.10, 6.87]0% [0%, 0%]0%7%-0.28+0.682026-01-08 → 2026-08-30
tmax00Znearestall29 1 QC5.64 [4.89, 6.62]1.48-5.64 [-6.62, -4.89]5.94 [5.16, 6.92]0% [0%, 0%]0%7%-0.28+0.682026-01-08 → 2026-08-30
tmax12Zbilinear30d23 1 QC5.52 [4.87, 6.30]1.06-5.52 [-6.30, -4.87]5.69 [5.07, 6.40]0% [0%, 0%]4%4%-0.89+0.642026-08-08 → 2026-08-30
tmax12Zbilinear90d23 1 QC5.52 [4.75, 6.47]1.06-5.52 [-6.47, -4.75]5.69 [4.96, 6.56]0% [0%, 0%]4%4%-0.89+0.642026-08-08 → 2026-08-30
tmax12Zbilinear365d28 1 QC5.75 [4.97, 6.69]1.21-5.75 [-6.69, -4.97]5.98 [5.17, 6.92]0% [0%, 0%]4%4%-0.52+0.682026-01-08 → 2026-08-30
tmax12Zbilinearall28 1 QC5.75 [4.98, 6.68]1.21-5.75 [-6.68, -4.98]5.98 [5.21, 6.91]0% [0%, 0%]4%4%-0.52+0.682026-01-08 → 2026-08-30
tmax12Znearest30d23 1 QC5.44 [4.78, 6.25]1.08-5.44 [-6.25, -4.78]5.63 [4.98, 6.34]0% [0%, 0%]4%4%-0.87+0.632026-08-08 → 2026-08-30
tmax12Znearest90d23 1 QC5.44 [4.66, 6.41]1.08-5.44 [-6.41, -4.66]5.63 [4.87, 6.51]0% [0%, 0%]4%4%-0.87+0.632026-08-08 → 2026-08-30
tmax12Znearest365d28 1 QC5.68 [4.87, 6.65]1.23-5.68 [-6.65, -4.87]5.92 [5.10, 6.89]0% [0%, 0%]4%4%-0.50+0.682026-01-08 → 2026-08-30
tmax12Znearestall28 1 QC5.68 [4.90, 6.64]1.23-5.68 [-6.64, -4.90]5.92 [5.13, 6.87]0% [0%, 0%]4%4%-0.50+0.682026-01-08 → 2026-08-30
tmin00Zbilinear30d23 1 QC2.87 [2.20, 3.63]1.69+2.42 [1.48, 3.03]3.30 [2.52, 4.00]4% [0%, 12%]35%65%-0.44+0.152026-08-08 → 2026-08-30
tmin00Zbilinear90d23 1 QC2.87 [2.14, 3.66]1.69+2.42 [1.37, 3.05]3.30 [2.40, 4.05]4% [0%, 12%]35%65%-0.44+0.152026-08-08 → 2026-08-30
tmin00Zbilinear365d29 1 QC3.14 [2.33, 4.29]2.40+2.13 [0.73, 3.31]4.09 [2.64, 6.03]7% [0%, 16%]38%66%+0.30+0.472026-01-08 → 2026-08-30
tmin00Zbilinearall29 1 QC3.14 [2.30, 4.26]2.40+2.13 [0.71, 3.30]4.09 [2.62, 5.96]7% [0%, 16%]38%66%+0.30+0.472026-01-08 → 2026-08-30
tmin00Znearest30d23 1 QC2.79 [2.11, 3.56]1.69+2.31 [1.38, 2.92]3.22 [2.44, 3.93]13% [0%, 24%]35%61%-0.39+0.152026-08-08 → 2026-08-30
tmin00Znearest90d23 1 QC2.79 [2.05, 3.58]1.69+2.31 [1.26, 2.95]3.22 [2.33, 3.98]13% [0%, 25%]35%61%-0.39+0.152026-08-08 → 2026-08-30
tmin00Znearest365d29 1 QC3.08 [2.25, 4.25]2.40+2.03 [0.62, 3.21]4.03 [2.57, 5.98]14% [3%, 24%]34%62%+0.32+0.472026-01-08 → 2026-08-30
tmin00Znearestall29 1 QC3.08 [2.22, 4.24]2.40+2.03 [0.61, 3.20]4.03 [2.58, 5.92]14% [0%, 24%]34%62%+0.32+0.472026-01-08 → 2026-08-30
tmin12Zbilinear30d23 1 QC2.89 [2.27, 3.58]1.68+2.43 [1.33, 3.11]3.33 [2.62, 4.00]4% [0%, 12%]43%61%-0.44+0.162026-08-08 → 2026-08-30
tmin12Zbilinear90d23 1 QC2.89 [2.27, 3.61]1.68+2.43 [1.16, 3.14]3.33 [2.56, 4.01]4% [0%, 12%]43%61%-0.44+0.162026-08-08 → 2026-08-30
tmin12Zbilinear365d28 1 QC2.66 [1.94, 3.35]1.91+1.80 [-0.20, 2.87]3.13 [2.32, 3.83]11% [0%, 29%]46%64%+0.30+0.492026-01-08 → 2026-08-30
tmin12Zbilinearall28 1 QC2.66 [1.86, 3.40]1.91+1.80 [-0.68, 2.93]3.13 [2.26, 3.86]11% [0%, 31%]46%64%+0.30+0.492026-01-08 → 2026-08-30
tmin12Znearest30d23 1 QC2.80 [2.18, 3.51]1.67+2.33 [1.23, 3.01]3.25 [2.53, 3.93]4% [0%, 15%]43%61%-0.40+0.162026-08-08 → 2026-08-30
tmin12Znearest90d23 1 QC2.80 [2.17, 3.54]1.67+2.33 [1.06, 3.04]3.25 [2.47, 3.96]4% [0%, 18%]43%61%-0.40+0.162026-08-08 → 2026-08-30
tmin12Znearest365d28 1 QC2.60 [1.93, 3.29]1.91+1.70 [-0.32, 2.76]3.07 [2.29, 3.75]7% [0%, 20%]46%64%+0.31+0.492026-01-08 → 2026-08-30
tmin12Znearestall28 1 QC2.60 [1.90, 3.34]1.91+1.70 [-0.78, 2.83]3.07 [2.23, 3.80]7% [0%, 21%]46%64%+0.31+0.492026-01-08 → 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 7, 00Z bilinear tmax+10+50-5-102026-08-08: -5.86 °F2026-08-09: -3.19 °F2026-08-10: -8.32 °F2026-08-11: -9.15 °F2026-08-12: -4.91 °F2026-08-13: -6.38 °F2026-08-14: -4.65 °F2026-08-15: -6.01 °F2026-08-16: -6.18 °F2026-08-17: -4.62 °F2026-08-18: -5.64 °F2026-08-19: -3.28 °F2026-08-20: -5.81 °F2026-08-21: -6.64 °F2026-08-22: -4.25 °F2026-08-23: -8 °F2026-08-24: -2.82 °F2026-08-25: -2.75 °F2026-08-26: -4.55 °F2026-08-27: -5.39 °F2026-08-28: -5.8 °F2026-08-29: -6.16 °F2026-08-30: -3.37 °F2026-08-082026-08-30°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 (23 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-3.37
2026-08-29-6.16
2026-08-28-5.80
2026-08-27-5.39
2026-08-26-4.55
2026-08-25-2.75
2026-08-24-2.82
2026-08-23-8.00
2026-08-22-4.25
2026-08-21-6.64
2026-08-20-5.81
2026-08-19-3.28
2026-08-18-5.64
2026-08-17-4.62
2026-08-16-6.18
2026-08-15-6.01
2026-08-14-4.65
2026-08-13-6.38
2026-08-12-4.91
2026-08-11-9.15
2026-08-10-8.32
2026-08-09-3.19
2026-08-08-5.86

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KMSY, lead day 7-10 to -9 °F: 2 days-9 to -8 °F: 4 days-8 to -7 °F: 0 days-7 to -6 °F: 7 days-6 to -5 °F: 5 days-5 to -4 °F: 5 days-4 to -3 °F: 4 days-3 to -2 °F: 2 days-2 to -1 °F: 0 days-1 to 0 °F: 0 days0 to 1 °F: 0 days1 to 2 °F: 0 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| 5.81 · P90 |e| 8.29 °F-100+10 °Fn = 29 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
-10.00-9.002
-9.00-8.004
-8.00-7.000
-7.00-6.007
-6.00-5.005
-5.00-4.005
-4.00-3.004
-3.00-2.002
-2.00-1.000
-1.00+0.000
+0.00+1.000
+1.00+2.000
+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
2026-08235.38 -5.38
2026-0166.97 -6.97

Availability

ModelScored period DaysCoverage
GraphCast (IFS init)2026-01-08 → 2026-08-30 29
GraphCast (IFS init)2026-01-08 → 2026-08-30 29
GraphCast (IFS init)2026-01-08 → 2026-08-30 28
GraphCast (IFS init)2026-01-08 → 2026-08-30 28

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 23 +0.35 [-0.60, 1.32] no
NCEP GFS 23 +1.24 [-0.20, 2.34] no
ECMWF IFS HRES 18 +0.95 [-0.58, 2.97] no
Persistence (baseline) 23 +2.47 [0.65, 3.59] yes

Cite this page

ShortCastCheck, KMSY graphcast_ifs lead 7, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KMSY/model/graphcast_ifs/lead/7/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KMSY (New Orleans Intl), model graphcast_ifs, lead day 7. 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/7/

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