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 9

KMSY · graphcast_ifs · lead 9

Target day = initialization date + 9 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
tmax00Zbilinear30d21 1 QC5.15 [4.27, 6.42]2.07-4.76 [-6.32, -3.67]5.53 [4.57, 6.65]0% [0%, 0%]5%14%-0.57+0.382026-08-10 → 2026-08-30
tmax00Zbilinear90d21 1 QC5.15 [4.27, 6.77]2.07-4.76 [-6.77, -3.50]5.53 [4.57, 6.95]0% [0%, 0%]5%14%-0.57+0.382026-08-10 → 2026-08-30
tmax00Zbilinear365d27 1 QC5.21 [4.36, 6.36]2.84-4.07 [-5.87, -1.77]5.80 [4.81, 6.95]4% [0%, 13%]7%22%+0.03+0.512026-01-10 → 2026-08-30
tmax00Zbilinearall27 1 QC5.21 [4.45, 6.20]2.84-4.07 [-5.80, -1.65]5.80 [4.94, 6.90]4% [0%, 14%]7%22%+0.03+0.512026-01-10 → 2026-08-30
tmax00Znearest30d21 1 QC5.07 [4.17, 6.36]2.10-4.67 [-6.25, -3.57]5.46 [4.47, 6.59]5% [0%, 12%]5%19%-0.54+0.372026-08-10 → 2026-08-30
tmax00Znearest90d21 1 QC5.07 [4.17, 6.71]2.10-4.67 [-6.71, -3.38]5.46 [4.47, 6.89]5% [0%, 14%]5%19%-0.54+0.372026-08-10 → 2026-08-30
tmax00Znearest365d27 1 QC5.14 [4.28, 6.32]2.86-3.99 [-5.79, -1.65]5.76 [4.73, 6.95]7% [0%, 17%]11%26%+0.04+0.512026-01-10 → 2026-08-30
tmax00Znearestall27 1 QC5.14 [4.36, 6.16]2.86-3.99 [-5.73, -1.59]5.76 [4.85, 6.89]7% [0%, 18%]11%26%+0.04+0.512026-01-10 → 2026-08-30
tmax12Zbilinear30d21 1 QC5.65 [4.55, 6.80]2.27-5.29 [-6.75, -3.59]6.11 [5.24, 7.06]5% [0%, 12%]10%10%-0.72+0.322026-08-10 → 2026-08-30
tmax12Zbilinear90d21 1 QC5.65 [4.38, 7.06]2.27-5.29 [-7.06, -3.31]6.11 [5.12, 7.39]5% [0%, 14%]10%10%-0.72+0.322026-08-10 → 2026-08-30
tmax12Zbilinear365d26 1 QC5.37 [4.17, 6.48]2.37-5.07 [-6.48, -3.47]5.93 [4.95, 6.84]8% [0%, 19%]15%15%-0.19+0.502026-01-10 → 2026-08-30
tmax12Zbilinearall26 1 QC5.37 [3.95, 6.45]2.37-5.07 [-6.45, -3.28]5.93 [4.99, 6.84]8% [0%, 20%]15%15%-0.19+0.502026-01-10 → 2026-08-30
tmax12Znearest30d21 1 QC5.58 [4.50, 6.74]2.28-5.20 [-6.68, -3.50]6.05 [5.19, 7.00]5% [0%, 12%]10%10%-0.70+0.312026-08-10 → 2026-08-30
tmax12Znearest90d21 1 QC5.58 [4.34, 7.00]2.28-5.20 [-7.00, -3.22]6.05 [5.06, 7.34]5% [0%, 14%]10%10%-0.70+0.312026-08-10 → 2026-08-30
tmax12Znearest365d26 1 QC5.31 [4.13, 6.42]2.39-4.99 [-6.42, -3.39]5.87 [4.93, 6.77]8% [0%, 19%]15%15%-0.18+0.492026-01-10 → 2026-08-30
tmax12Znearestall26 1 QC5.31 [3.89, 6.37]2.39-4.99 [-6.37, -3.20]5.87 [4.95, 6.77]8% [0%, 20%]15%15%-0.18+0.492026-01-10 → 2026-08-30
tmin00Zbilinear30d21 1 QC2.92 [2.26, 3.73]1.82+2.38 [1.00, 3.10]3.45 [2.74, 4.23]24% [12%, 37%]29%62%-0.06+0.342026-08-10 → 2026-08-30
tmin00Zbilinear90d21 1 QC2.92 [2.21, 3.78]1.82+2.38 [0.74, 3.14]3.45 [2.59, 4.31]24% [11%, 36%]29%62%-0.06+0.342026-08-10 → 2026-08-30
tmin00Zbilinear365d27 1 QC3.48 [2.52, 5.01]2.30+2.97 [1.70, 4.44]4.40 [2.98, 6.20]19% [3%, 32%]26%56%+0.34+0.572026-01-10 → 2026-08-30
tmin00Zbilinearall27 1 QC3.48 [2.54, 5.01]2.30+2.97 [1.78, 4.49]4.40 [3.04, 6.38]19% [0%, 32%]26%56%+0.34+0.572026-01-10 → 2026-08-30
tmin00Znearest30d21 1 QC2.85 [2.18, 3.69]1.83+2.28 [0.90, 3.00]3.39 [2.67, 4.18]24% [12%, 37%]29%62%-0.03+0.342026-08-10 → 2026-08-30
tmin00Znearest90d21 1 QC2.85 [2.12, 3.73]1.83+2.28 [0.63, 3.04]3.39 [2.52, 4.27]24% [11%, 36%]29%62%-0.03+0.342026-08-10 → 2026-08-30
tmin00Znearest365d27 1 QC3.40 [2.44, 4.93]2.29+2.86 [1.61, 4.32]4.33 [2.91, 6.10]19% [3%, 32%]26%56%+0.35+0.572026-01-10 → 2026-08-30
tmin00Znearestall27 1 QC3.40 [2.46, 4.93]2.29+2.86 [1.68, 4.36]4.33 [3.00, 6.27]19% [0%, 32%]26%56%+0.35+0.572026-01-10 → 2026-08-30
tmin12Zbilinear30d21 1 QC2.93 [1.95, 4.04]2.11+2.36 [0.85, 3.43]3.59 [2.39, 4.63]10% [0%, 20%]48%62%-0.06+0.242026-08-10 → 2026-08-30
tmin12Zbilinear90d21 1 QC2.93 [1.94, 4.09]2.11+2.36 [0.56, 3.46]3.59 [2.29, 4.70]10% [0%, 22%]48%62%-0.06+0.242026-08-10 → 2026-08-30
tmin12Zbilinear365d26 1 QC2.83 [1.98, 3.83]2.27+1.99 [0.23, 3.15]3.48 [2.37, 4.43]8% [0%, 17%]50%65%+0.39+0.512026-01-10 → 2026-08-30
tmin12Zbilinearall26 1 QC2.83 [2.02, 3.87]2.27+1.99 [0.21, 3.16]3.48 [2.46, 4.43]8% [0%, 17%]50%65%+0.39+0.512026-01-10 → 2026-08-30
tmin12Znearest30d21 1 QC2.87 [1.88, 4.00]2.11+2.26 [0.75, 3.34]3.53 [2.31, 4.57]14% [0%, 28%]48%62%-0.04+0.242026-08-10 → 2026-08-30
tmin12Znearest90d21 1 QC2.87 [1.87, 4.06]2.11+2.26 [0.45, 3.37]3.53 [2.23, 4.65]14% [0%, 29%]48%62%-0.04+0.242026-08-10 → 2026-08-30
tmin12Znearest365d26 1 QC2.78 [1.92, 3.74]2.27+1.88 [0.12, 3.05]3.42 [2.31, 4.35]12% [0%, 25%]50%65%+0.40+0.512026-01-10 → 2026-08-30
tmin12Znearestall26 1 QC2.78 [1.95, 3.83]2.27+1.88 [0.05, 3.06]3.42 [2.39, 4.37]12% [0%, 25%]50%65%+0.40+0.512026-01-10 → 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 9, 00Z bilinear tmax+10+50-5-102026-08-10: -8.64 °F2026-08-11: -5.82 °F2026-08-12: -6.4 °F2026-08-13: -7.7 °F2026-08-14: -5.71 °F2026-08-15: -5.89 °F2026-08-16: -6.44 °F2026-08-17: -4.11 °F2026-08-18: -3.03 °F2026-08-19: -2.36 °F2026-08-20: -3.67 °F2026-08-21: -4.34 °F2026-08-22: -5.39 °F2026-08-23: -7 °F2026-08-24: -4.17 °F2026-08-25: -1.05 °F2026-08-26: -4.75 °F2026-08-27: +4.06 °F2026-08-28: -6.13 °F2026-08-29: -9.07 °F2026-08-30: -2.45 °F2026-08-102026-08-30°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 (21 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-2.45
2026-08-29-9.07
2026-08-28-6.13
2026-08-27+4.06
2026-08-26-4.75
2026-08-25-1.05
2026-08-24-4.17
2026-08-23-7.00
2026-08-22-5.39
2026-08-21-4.34
2026-08-20-3.67
2026-08-19-2.36
2026-08-18-3.03
2026-08-17-4.11
2026-08-16-6.44
2026-08-15-5.89
2026-08-14-5.71
2026-08-13-7.70
2026-08-12-6.40
2026-08-11-5.82
2026-08-10-8.64

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KMSY, lead day 9-20 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: 0 days-10 to -8 °F: 3 days-8 to -6 °F: 6 days-6 to -4 °F: 8 days-4 to -2 °F: 6 days-2 to 0 °F: 2 days0 to 2 °F: 0 days2 to 4 °F: 0 days4 to 6 °F: 1 day6 to 8 °F: 0 days8 to 10 °F: 0 days10 to 12 °F: 1 day12 to 14 °F: 0 days14 to 16 °F: 0 days16 to 18 °F: 0 days18 to 20 °F: 0 daysdashed: P50 |e| 5.39 · P90 |e| 8.29 °F-200+20 °Fn = 27 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
-12.00-10.000
-10.00-8.003
-8.00-6.006
-6.00-4.008
-4.00-2.006
-2.00+0.002
+0.00+2.000
+2.00+4.000
+4.00+6.001
+6.00+8.000
+8.00+10.000
+10.00+12.001
+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
2026-08215.15 -4.76
2026-0165.40 -1.65

Availability

ModelScored period DaysCoverage
GraphCast (IFS init)2026-01-10 → 2026-08-30 27
GraphCast (IFS init)2026-01-10 → 2026-08-30 27
GraphCast (IFS init)2026-01-10 → 2026-08-30 26
GraphCast (IFS init)2026-01-10 → 2026-08-30 26

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 21 +0.32 [-0.75, 2.20] no
NCEP GFS 21 +0.68 [-0.85, 2.97] no
ECMWF IFS HRES 16 +0.22 [-0.28, 2.05] no
Persistence (baseline) 21 +1.87 [0.65, 3.22] yes

Cite this page

ShortCastCheck, KMSY graphcast_ifs lead 9, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KMSY/model/graphcast_ifs/lead/9/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KMSY (New Orleans Intl), model graphcast_ifs, lead day 9. 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/9/

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