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 5

KMSY · graphcast_ifs · lead 5

Target day = initialization date + 5 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
tmax00Zbilinear30d25 1 QC5.25 [4.75, 5.70]1.27-5.25 [-5.70, -4.75]5.50 [4.99, 5.94]0% [0%, 0%]4%8%-0.96+0.532026-08-06 → 2026-08-30
tmax00Zbilinear90d25 1 QC5.25 [4.69, 5.73]1.27-5.25 [-5.73, -4.69]5.50 [4.96, 5.98]0% [0%, 0%]4%8%-0.96+0.532026-08-06 → 2026-08-30
tmax00Zbilinear365d31 1 QC5.54 [4.90, 6.27]1.38-5.54 [-6.27, -4.90]5.83 [5.16, 6.58]0% [0%, 0%]3%6%-0.31+0.672026-01-06 → 2026-08-30
tmax00Zbilinearall31 1 QC5.54 [4.91, 6.29]1.38-5.54 [-6.29, -4.91]5.83 [5.16, 6.61]0% [0%, 0%]3%6%-0.31+0.672026-01-06 → 2026-08-30
tmax00Znearest30d25 1 QC5.18 [4.68, 5.63]1.27-5.18 [-5.63, -4.68]5.43 [4.92, 5.88]0% [0%, 0%]4%8%-0.93+0.532026-08-06 → 2026-08-30
tmax00Znearest90d25 1 QC5.18 [4.63, 5.67]1.27-5.18 [-5.67, -4.63]5.43 [4.90, 5.92]0% [0%, 0%]4%8%-0.93+0.532026-08-06 → 2026-08-30
tmax00Znearest365d31 1 QC5.47 [4.82, 6.21]1.37-5.47 [-6.21, -4.82]5.76 [5.09, 6.51]0% [0%, 0%]3%6%-0.30+0.672026-01-06 → 2026-08-30
tmax00Znearestall31 1 QC5.47 [4.84, 6.21]1.37-5.47 [-6.21, -4.84]5.76 [5.10, 6.54]0% [0%, 0%]3%6%-0.30+0.672026-01-06 → 2026-08-30
tmax12Zbilinear30d25 1 QC5.80 [5.20, 6.19]1.25-5.80 [-6.19, -5.20]6.01 [5.42, 6.39]0% [0%, 0%]0%4%-1.16+0.542026-08-06 → 2026-08-30
tmax12Zbilinear90d25 1 QC5.80 [5.14, 6.22]1.25-5.80 [-6.22, -5.14]6.01 [5.37, 6.46]0% [0%, 0%]0%4%-1.16+0.542026-08-06 → 2026-08-30
tmax12Zbilinear365d30 1 QC6.05 [5.45, 6.73]1.32-6.05 [-6.73, -5.45]6.29 [5.63, 7.02]0% [0%, 0%]0%3%-0.64+0.642026-01-06 → 2026-08-30
tmax12Zbilinearall30 1 QC6.05 [5.42, 6.75]1.32-6.05 [-6.75, -5.42]6.29 [5.63, 7.03]0% [0%, 0%]0%3%-0.64+0.642026-01-06 → 2026-08-30
tmax12Znearest30d25 1 QC5.73 [5.14, 6.12]1.26-5.73 [-6.12, -5.14]5.94 [5.34, 6.33]0% [0%, 0%]0%4%-1.14+0.532026-08-06 → 2026-08-30
tmax12Znearest90d25 1 QC5.73 [5.08, 6.16]1.26-5.73 [-6.16, -5.08]5.94 [5.30, 6.41]0% [0%, 0%]0%4%-1.14+0.532026-08-06 → 2026-08-30
tmax12Znearest365d30 1 QC5.98 [5.38, 6.66]1.32-5.98 [-6.66, -5.38]6.22 [5.57, 6.94]0% [0%, 0%]0%3%-0.62+0.642026-01-06 → 2026-08-30
tmax12Znearestall30 1 QC5.98 [5.35, 6.67]1.32-5.98 [-6.67, -5.35]6.22 [5.56, 6.95]0% [0%, 0%]0%3%-0.62+0.642026-01-06 → 2026-08-30
tmin00Zbilinear30d25 1 QC2.94 [2.35, 3.62]1.59+2.60 [1.82, 3.18]3.37 [2.57, 4.12]4% [0%, 12%]36%60%-0.75+0.072026-08-06 → 2026-08-30
tmin00Zbilinear90d25 1 QC2.94 [2.30, 3.66]1.59+2.60 [1.73, 3.16]3.37 [2.49, 4.21]4% [0%, 12%]36%60%-0.75+0.072026-08-06 → 2026-08-30
tmin00Zbilinear365d31 1 QC2.78 [2.14, 3.48]1.73+2.09 [0.62, 3.00]3.22 [2.43, 3.97]10% [0%, 25%]39%61%+0.24+0.562026-01-06 → 2026-08-30
tmin00Zbilinearall31 1 QC2.78 [2.14, 3.48]1.73+2.09 [0.55, 2.98]3.22 [2.44, 4.01]10% [0%, 25%]39%61%+0.24+0.562026-01-06 → 2026-08-30
tmin00Znearest30d25 1 QC2.85 [2.26, 3.54]1.59+2.49 [1.72, 3.07]3.29 [2.48, 4.05]4% [0%, 12%]44%60%-0.70+0.072026-08-06 → 2026-08-30
tmin00Znearest90d25 1 QC2.85 [2.21, 3.59]1.59+2.49 [1.62, 3.06]3.29 [2.41, 4.15]4% [0%, 12%]44%60%-0.70+0.072026-08-06 → 2026-08-30
tmin00Znearest365d31 1 QC2.70 [2.07, 3.40]1.73+2.00 [0.54, 2.89]3.15 [2.38, 3.89]10% [0%, 25%]45%61%+0.26+0.562026-01-06 → 2026-08-30
tmin00Znearestall31 1 QC2.70 [2.07, 3.40]1.73+2.00 [0.48, 2.87]3.15 [2.39, 3.94]10% [0%, 25%]45%61%+0.26+0.562026-01-06 → 2026-08-30
tmin12Zbilinear30d25 1 QC2.78 [2.20, 3.46]1.57+2.36 [1.42, 2.95]3.15 [2.47, 3.84]4% [0%, 12%]40%60%-0.65+0.082026-08-06 → 2026-08-30
tmin12Zbilinear90d25 1 QC2.78 [2.14, 3.56]1.57+2.36 [1.27, 2.98]3.15 [2.36, 3.91]4% [0%, 12%]40%60%-0.65+0.082026-08-06 → 2026-08-30
tmin12Zbilinear365d30 1 QC2.56 [1.79, 3.33]1.81+1.79 [0.04, 2.78]2.99 [2.21, 3.72]13% [0%, 38%]43%63%+0.25+0.522026-01-06 → 2026-08-30
tmin12Zbilinearall30 1 QC2.56 [1.75, 3.33]1.81+1.79 [-0.06, 2.79]2.99 [2.12, 3.75]13% [0%, 38%]43%63%+0.25+0.522026-01-06 → 2026-08-30
tmin12Znearest30d25 1 QC2.69 [2.10, 3.39]1.57+2.25 [1.31, 2.84]3.08 [2.39, 3.77]4% [0%, 12%]44%60%-0.60+0.082026-08-06 → 2026-08-30
tmin12Znearest90d25 1 QC2.69 [2.03, 3.48]1.57+2.25 [1.16, 2.87]3.08 [2.28, 3.84]4% [0%, 12%]44%60%-0.60+0.082026-08-06 → 2026-08-30
tmin12Znearest365d30 1 QC2.49 [1.77, 3.26]1.80+1.70 [-0.03, 2.68]2.92 [2.16, 3.65]13% [0%, 38%]47%63%+0.27+0.522026-01-06 → 2026-08-30
tmin12Znearestall30 1 QC2.49 [1.70, 3.26]1.80+1.70 [-0.15, 2.68]2.92 [2.10, 3.68]13% [0%, 38%]47%63%+0.27+0.522026-01-06 → 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 5, 00Z bilinear tmax+10+50-5-102026-08-06: -5.19 °F2026-08-07: -4.21 °F2026-08-08: -4.43 °F2026-08-09: -3.24 °F2026-08-10: -9.11 °F2026-08-11: -6.46 °F2026-08-12: -5.58 °F2026-08-13: -7.16 °F2026-08-14: -5.14 °F2026-08-15: -5.69 °F2026-08-16: -6.01 °F2026-08-17: -2.62 °F2026-08-18: -5.2 °F2026-08-19: -7.57 °F2026-08-20: -4.02 °F2026-08-21: -6.52 °F2026-08-22: -4.93 °F2026-08-23: -5.79 °F2026-08-24: -4.31 °F2026-08-25: -4.33 °F2026-08-26: -5.97 °F2026-08-27: -1.51 °F2026-08-28: -5.75 °F2026-08-29: -7.27 °F2026-08-30: -3.23 °F2026-08-062026-08-30°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 (25 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-3.23
2026-08-29-7.27
2026-08-28-5.75
2026-08-27-1.51
2026-08-26-5.97
2026-08-25-4.33
2026-08-24-4.31
2026-08-23-5.79
2026-08-22-4.93
2026-08-21-6.52
2026-08-20-4.02
2026-08-19-7.57
2026-08-18-5.20
2026-08-17-2.62
2026-08-16-6.01
2026-08-15-5.69
2026-08-14-5.14
2026-08-13-7.16
2026-08-12-5.58
2026-08-11-6.46
2026-08-10-9.11
2026-08-09-3.24
2026-08-08-4.43
2026-08-07-4.21
2026-08-06-5.19

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KMSY, lead day 5-10 to -9 °F: 2 days-9 to -8 °F: 1 day-8 to -7 °F: 3 days-7 to -6 °F: 5 days-6 to -5 °F: 9 days-5 to -4 °F: 7 days-4 to -3 °F: 2 days-3 to -2 °F: 1 day-2 to -1 °F: 1 day-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| 5.58 · P90 |e| 7.57 °F-100+10 °Fn = 31 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
-9.00-8.001
-8.00-7.003
-7.00-6.005
-6.00-5.009
-5.00-4.007
-4.00-3.002
-3.00-2.001
-2.00-1.001
-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
2026-08255.25 -5.25
2026-0166.76 -6.76

Availability

ModelScored period DaysCoverage
GraphCast (IFS init)2026-01-06 → 2026-08-30 31
GraphCast (IFS init)2026-01-06 → 2026-08-30 31
GraphCast (IFS init)2026-01-06 → 2026-08-30 30
GraphCast (IFS init)2026-01-06 → 2026-08-30 30

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 25 +0.74 [0.25, 1.15] yes
NCEP GFS 25 +1.87 [0.95, 2.83] yes
ECMWF IFS HRES 18 +0.00 [-1.31, 1.70] no
Persistence (baseline) 25 +2.57 [0.89, 3.85] yes

Cite this page

ShortCastCheck, KMSY graphcast_ifs lead 5, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KMSY/model/graphcast_ifs/lead/5/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KMSY (New Orleans Intl), model graphcast_ifs, lead day 5. 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/5/

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