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 6

KMSY · graphcast_ifs · lead 6

Target day = initialization date + 6 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
tmax00Zbilinear30d24 1 QC5.60 [5.18, 6.08]1.18-5.60 [-6.08, -5.18]5.83 [5.42, 6.30]0% [0%, 0%]0%4%-0.95+0.592026-08-07 → 2026-08-30
tmax00Zbilinear90d24 1 QC5.60 [5.14, 6.15]1.18-5.60 [-6.15, -5.14]5.83 [5.38, 6.42]0% [0%, 0%]0%4%-0.95+0.592026-08-07 → 2026-08-30
tmax00Zbilinear365d30 1 QC5.78 [5.15, 6.50]1.56-5.73 [-6.43, -5.09]6.17 [5.45, 7.07]3% [0%, 13%]3%7%-0.27+0.662026-01-07 → 2026-08-30
tmax00Zbilinearall30 1 QC5.78 [5.19, 6.50]1.56-5.73 [-6.43, -5.11]6.17 [5.50, 7.02]3% [0%, 13%]3%7%-0.27+0.662026-01-07 → 2026-08-30
tmax00Znearest30d24 1 QC5.53 [5.11, 6.01]1.20-5.53 [-6.01, -5.11]5.76 [5.34, 6.25]0% [0%, 0%]0%4%-0.92+0.582026-08-07 → 2026-08-30
tmax00Znearest90d24 1 QC5.53 [5.06, 6.11]1.20-5.53 [-6.11, -5.06]5.76 [5.31, 6.37]0% [0%, 0%]0%4%-0.92+0.582026-08-07 → 2026-08-30
tmax00Znearest365d30 1 QC5.71 [5.09, 6.43]1.57-5.66 [-6.37, -5.02]6.11 [5.38, 7.01]3% [0%, 13%]3%7%-0.25+0.662026-01-07 → 2026-08-30
tmax00Znearestall30 1 QC5.71 [5.13, 6.44]1.57-5.66 [-6.37, -5.04]6.11 [5.44, 6.98]3% [0%, 13%]3%7%-0.25+0.662026-01-07 → 2026-08-30
tmax12Zbilinear30d24 1 QC5.81 [5.35, 6.39]1.27-5.81 [-6.39, -5.35]6.07 [5.49, 6.70]0% [0%, 0%]4%4%-1.02+0.562026-08-07 → 2026-08-30
tmax12Zbilinear90d24 1 QC5.81 [5.33, 6.52]1.27-5.81 [-6.52, -5.33]6.07 [5.48, 6.83]0% [0%, 0%]4%4%-1.02+0.562026-08-07 → 2026-08-30
tmax12Zbilinear365d29 1 QC5.96 [5.46, 6.65]1.35-5.96 [-6.65, -5.46]6.22 [5.62, 6.93]0% [0%, 0%]3%3%-0.59+0.642026-01-07 → 2026-08-30
tmax12Zbilinearall29 1 QC5.96 [5.50, 6.67]1.35-5.96 [-6.67, -5.50]6.22 [5.65, 6.96]0% [0%, 0%]3%3%-0.59+0.642026-01-07 → 2026-08-30
tmax12Znearest30d24 1 QC5.74 [5.28, 6.34]1.27-5.74 [-6.34, -5.28]6.01 [5.41, 6.65]0% [0%, 0%]4%4%-1.00+0.562026-08-07 → 2026-08-30
tmax12Znearest90d24 1 QC5.74 [5.26, 6.46]1.27-5.74 [-6.46, -5.26]6.01 [5.39, 6.78]0% [0%, 0%]4%4%-1.00+0.562026-08-07 → 2026-08-30
tmax12Znearest365d29 1 QC5.89 [5.38, 6.60]1.36-5.89 [-6.60, -5.38]6.16 [5.53, 6.87]0% [0%, 0%]3%3%-0.57+0.632026-01-07 → 2026-08-30
tmax12Znearestall29 1 QC5.89 [5.42, 6.61]1.36-5.89 [-6.61, -5.42]6.16 [5.57, 6.90]0% [0%, 0%]3%3%-0.57+0.632026-01-07 → 2026-08-30
tmin00Zbilinear30d24 1 QC2.88 [2.32, 3.57]1.54+2.59 [1.70, 3.26]3.32 [2.63, 4.06]8% [0%, 15%]29%58%-0.38+0.262026-08-07 → 2026-08-30
tmin00Zbilinear90d24 1 QC2.88 [2.31, 3.65]1.54+2.59 [1.57, 3.30]3.32 [2.58, 4.12]8% [0%, 14%]29%58%-0.38+0.262026-08-07 → 2026-08-30
tmin00Zbilinear365d30 1 QC2.97 [2.41, 3.60]1.86+2.19 [0.84, 3.18]3.47 [2.73, 4.18]10% [0%, 18%]30%57%+0.26+0.532026-01-07 → 2026-08-30
tmin00Zbilinearall30 1 QC2.97 [2.40, 3.65]1.86+2.19 [0.73, 3.17]3.47 [2.72, 4.22]10% [0%, 18%]30%57%+0.26+0.532026-01-07 → 2026-08-30
tmin00Znearest30d24 1 QC2.78 [2.23, 3.48]1.54+2.49 [1.59, 3.15]3.24 [2.55, 3.98]8% [0%, 15%]33%62%-0.34+0.262026-08-07 → 2026-08-30
tmin00Znearest90d24 1 QC2.78 [2.22, 3.56]1.54+2.49 [1.47, 3.19]3.24 [2.50, 4.03]8% [0%, 14%]33%62%-0.34+0.262026-08-07 → 2026-08-30
tmin00Znearest365d30 1 QC2.89 [2.33, 3.53]1.85+2.09 [0.75, 3.08]3.40 [2.65, 4.11]10% [0%, 18%]33%60%+0.28+0.532026-01-07 → 2026-08-30
tmin00Znearestall30 1 QC2.89 [2.32, 3.58]1.85+2.09 [0.65, 3.06]3.40 [2.64, 4.14]10% [0%, 18%]33%60%+0.28+0.532026-01-07 → 2026-08-30
tmin12Zbilinear30d24 1 QC2.85 [2.26, 3.51]1.62+2.46 [1.53, 3.07]3.30 [2.58, 4.02]8% [0%, 18%]38%67%-0.37+0.222026-08-07 → 2026-08-30
tmin12Zbilinear90d24 1 QC2.85 [2.22, 3.52]1.62+2.46 [1.43, 3.09]3.30 [2.44, 4.06]8% [0%, 20%]38%67%-0.37+0.222026-08-07 → 2026-08-30
tmin12Zbilinear365d29 1 QC2.65 [1.96, 3.27]1.85+1.91 [0.24, 2.87]3.14 [2.36, 3.82]14% [3%, 29%]45%69%+0.24+0.472026-01-07 → 2026-08-30
tmin12Zbilinearall29 1 QC2.65 [1.92, 3.35]1.85+1.91 [-0.09, 2.90]3.14 [2.31, 3.87]14% [0%, 33%]45%69%+0.24+0.472026-01-07 → 2026-08-30
tmin12Znearest30d24 1 QC2.76 [2.17, 3.43]1.61+2.36 [1.43, 2.97]3.22 [2.50, 3.94]8% [0%, 18%]38%67%-0.33+0.232026-08-07 → 2026-08-30
tmin12Znearest90d24 1 QC2.76 [2.13, 3.45]1.61+2.36 [1.35, 2.98]3.22 [2.37, 4.00]8% [0%, 20%]38%67%-0.33+0.232026-08-07 → 2026-08-30
tmin12Znearest365d29 1 QC2.58 [1.92, 3.21]1.84+1.81 [0.17, 2.77]3.07 [2.30, 3.75]14% [3%, 29%]45%69%+0.26+0.472026-01-07 → 2026-08-30
tmin12Znearestall29 1 QC2.58 [1.90, 3.28]1.84+1.81 [-0.16, 2.80]3.07 [2.28, 3.80]14% [0%, 33%]45%69%+0.26+0.472026-01-07 → 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 6, 00Z bilinear tmax+10+50-5-102026-08-07: -5.82 °F2026-08-08: -5.78 °F2026-08-09: -3.11 °F2026-08-10: -9.62 °F2026-08-11: -6.85 °F2026-08-12: -5.5 °F2026-08-13: -6.28 °F2026-08-14: -5.2 °F2026-08-15: -6.24 °F2026-08-16: -5.52 °F2026-08-17: -5.55 °F2026-08-18: -3.27 °F2026-08-19: -5.83 °F2026-08-20: -6.32 °F2026-08-21: -5.16 °F2026-08-22: -8.39 °F2026-08-23: -4.76 °F2026-08-24: -3.38 °F2026-08-25: -3.37 °F2026-08-26: -7.34 °F2026-08-27: -2.62 °F2026-08-28: -5.52 °F2026-08-29: -6.23 °F2026-08-30: -6.68 °F2026-08-072026-08-30°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 (24 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-6.68
2026-08-29-6.23
2026-08-28-5.52
2026-08-27-2.62
2026-08-26-7.34
2026-08-25-3.37
2026-08-24-3.38
2026-08-23-4.76
2026-08-22-8.39
2026-08-21-5.16
2026-08-20-6.32
2026-08-19-5.83
2026-08-18-3.27
2026-08-17-5.55
2026-08-16-5.52
2026-08-15-6.24
2026-08-14-5.20
2026-08-13-6.28
2026-08-12-5.50
2026-08-11-6.85
2026-08-10-9.62
2026-08-09-3.11
2026-08-08-5.78
2026-08-07-5.82

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KMSY, lead day 6-20 to -18 °F: 0 days-18 to -16 °F: 0 days-16 to -14 °F: 0 days-14 to -12 °F: 0 days-12 to -10 °F: 1 day-10 to -8 °F: 3 days-8 to -6 °F: 8 days-6 to -4 °F: 12 days-4 to -2 °F: 5 days-2 to 0 °F: 0 days0 to 2 °F: 1 day2 to 4 °F: 0 days4 to 6 °F: 0 days6 to 8 °F: 0 days8 to 10 °F: 0 days10 to 12 °F: 0 days12 to 14 °F: 0 days14 to 16 °F: 0 days16 to 18 °F: 0 days18 to 20 °F: 0 daysdashed: P50 |e| 5.66 · P90 |e| 8.5 °F-200+20 °Fn = 30 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
-20.00-18.000
-18.00-16.000
-16.00-14.000
-14.00-12.000
-12.00-10.001
-10.00-8.003
-8.00-6.008
-6.00-4.0012
-4.00-2.005
-2.00+0.000
+0.00+2.001
+2.00+4.000
+4.00+6.000
+6.00+8.000
+8.00+10.000
+10.00+12.000
+12.00+14.000
+14.00+16.000
+16.00+18.000
+18.00+20.000

Month by month

00Z bilinear daily maximum, newest first.

Monthn MAE °FBias °F
2026-08245.60 -5.60
2026-0166.51 -6.26

Availability

ModelScored period DaysCoverage
GraphCast (IFS init)2026-01-07 → 2026-08-30 30
GraphCast (IFS init)2026-01-07 → 2026-08-30 30
GraphCast (IFS init)2026-01-07 → 2026-08-30 29
GraphCast (IFS init)2026-01-07 → 2026-08-30 29

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 24 +0.61 [-0.21, 1.21] no
NCEP GFS 24 +1.07 [0.11, 2.00] yes
ECMWF IFS HRES 19 +0.81 [-0.26, 2.78] no
Persistence (baseline) 24 +2.72 [1.29, 3.88] yes

Cite this page

ShortCastCheck, KMSY graphcast_ifs lead 6, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KMSY/model/graphcast_ifs/lead/6/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KMSY (New Orleans Intl), model graphcast_ifs, lead day 6. 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/6/

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