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 8

KMSY · graphcast_ifs · lead 8

Target day = initialization date + 8 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
tmax00Zbilinear30d22 1 QC5.19 [4.55, 5.99]1.43-5.19 [-5.99, -4.55]5.50 [4.83, 6.26]0% [0%, 0%]0%9%-0.61+0.552026-08-09 → 2026-08-30
tmax00Zbilinear90d22 1 QC5.19 [4.49, 6.18]1.43-5.19 [-6.18, -4.49]5.50 [4.82, 6.40]0% [0%, 0%]0%9%-0.61+0.552026-08-09 → 2026-08-30
tmax00Zbilinear365d28 1 QC5.02 [4.24, 5.85]1.48-5.02 [-5.85, -4.24]5.36 [4.59, 6.11]0% [0%, 0%]4%11%-0.07+0.692026-01-09 → 2026-08-30
tmax00Zbilinearall28 1 QC5.02 [4.21, 5.75]1.48-5.02 [-5.75, -4.21]5.36 [4.55, 6.02]0% [0%, 0%]4%11%-0.07+0.692026-01-09 → 2026-08-30
tmax00Znearest30d22 1 QC5.10 [4.45, 5.94]1.44-5.10 [-5.94, -4.45]5.42 [4.73, 6.21]0% [0%, 0%]0%9%-0.58+0.542026-08-09 → 2026-08-30
tmax00Znearest90d22 1 QC5.10 [4.39, 6.11]1.44-5.10 [-6.11, -4.39]5.42 [4.73, 6.34]0% [0%, 0%]0%9%-0.58+0.542026-08-09 → 2026-08-30
tmax00Znearest365d28 1 QC4.94 [4.15, 5.79]1.49-4.94 [-5.79, -4.15]5.29 [4.49, 6.04]0% [0%, 0%]4%11%-0.05+0.692026-01-09 → 2026-08-30
tmax00Znearestall28 1 QC4.94 [4.12, 5.68]1.49-4.94 [-5.68, -4.12]5.29 [4.46, 5.96]0% [0%, 0%]4%11%-0.05+0.692026-01-09 → 2026-08-30
tmax12Zbilinear30d22 1 QC5.63 [4.65, 6.80]1.66-5.63 [-6.80, -4.65]6.02 [5.08, 7.06]0% [0%, 0%]9%14%-0.75+0.472026-08-09 → 2026-08-30
tmax12Zbilinear90d22 1 QC5.63 [4.59, 7.03]1.66-5.63 [-7.03, -4.59]6.02 [5.05, 7.32]0% [0%, 0%]9%14%-0.75+0.472026-08-09 → 2026-08-30
tmax12Zbilinear365d27 1 QC5.60 [4.64, 6.61]1.65-5.60 [-6.61, -4.64]5.99 [5.15, 6.91]0% [0%, 0%]11%15%-0.29+0.632026-01-09 → 2026-08-30
tmax12Zbilinearall27 1 QC5.60 [4.66, 6.52]1.65-5.60 [-6.52, -4.66]5.99 [5.13, 6.90]0% [0%, 0%]11%15%-0.29+0.632026-01-09 → 2026-08-30
tmax12Znearest30d22 1 QC5.56 [4.57, 6.74]1.68-5.56 [-6.74, -4.57]5.95 [5.01, 7.01]0% [0%, 0%]9%14%-0.72+0.472026-08-09 → 2026-08-30
tmax12Znearest90d22 1 QC5.56 [4.50, 6.99]1.68-5.56 [-6.99, -4.50]5.95 [4.98, 7.28]0% [0%, 0%]9%14%-0.72+0.472026-08-09 → 2026-08-30
tmax12Znearest365d27 1 QC5.54 [4.56, 6.55]1.67-5.54 [-6.55, -4.56]5.94 [5.10, 6.86]0% [0%, 0%]11%15%-0.28+0.622026-01-09 → 2026-08-30
tmax12Znearestall27 1 QC5.54 [4.58, 6.49]1.67-5.54 [-6.49, -4.58]5.94 [5.07, 6.85]0% [0%, 0%]11%15%-0.28+0.622026-01-09 → 2026-08-30
tmin00Zbilinear30d22 1 QC2.82 [2.12, 3.64]1.81+2.49 [1.35, 3.31]3.40 [2.58, 4.20]14% [5%, 22%]41%59%-0.05+0.322026-08-09 → 2026-08-30
tmin00Zbilinear90d22 1 QC2.82 [2.10, 3.66]1.81+2.49 [1.21, 3.38]3.40 [2.50, 4.26]14% [0%, 24%]41%59%-0.05+0.322026-08-09 → 2026-08-30
tmin00Zbilinear365d28 1 QC2.69 [2.07, 3.46]2.02+1.91 [0.11, 3.05]3.26 [2.54, 4.00]18% [7%, 30%]46%61%+0.49+0.622026-01-09 → 2026-08-30
tmin00Zbilinearall28 1 QC2.69 [2.09, 3.48]2.02+1.91 [-0.04, 3.09]3.26 [2.54, 4.02]18% [8%, 32%]46%61%+0.49+0.622026-01-09 → 2026-08-30
tmin00Znearest30d22 1 QC2.74 [2.02, 3.58]1.81+2.40 [1.25, 3.22]3.33 [2.51, 4.13]18% [6%, 29%]41%59%-0.02+0.322026-08-09 → 2026-08-30
tmin00Znearest90d22 1 QC2.74 [2.01, 3.60]1.81+2.40 [1.11, 3.29]3.33 [2.42, 4.19]18% [0%, 30%]41%59%-0.02+0.322026-08-09 → 2026-08-30
tmin00Znearest365d28 1 QC2.62 [2.02, 3.39]2.02+1.80 [-0.02, 2.95]3.19 [2.46, 3.94]21% [9%, 33%]46%61%+0.50+0.622026-01-09 → 2026-08-30
tmin00Znearestall28 1 QC2.62 [2.04, 3.40]2.02+1.80 [-0.17, 2.99]3.19 [2.48, 3.97]21% [10%, 33%]46%61%+0.50+0.622026-01-09 → 2026-08-30
tmin12Zbilinear30d22 1 QC2.83 [2.11, 3.63]1.82+2.49 [1.31, 3.39]3.36 [2.54, 4.13]14% [5%, 22%]36%55%-0.05+0.322026-08-09 → 2026-08-30
tmin12Zbilinear90d22 1 QC2.83 [2.08, 3.67]1.82+2.49 [1.03, 3.42]3.36 [2.49, 4.14]14% [0%, 24%]36%55%-0.05+0.322026-08-09 → 2026-08-30
tmin12Zbilinear365d27 1 QC2.91 [2.31, 3.71]2.20+1.96 [0.01, 3.12]3.41 [2.70, 4.16]11% [0%, 20%]33%56%+0.43+0.572026-01-09 → 2026-08-30
tmin12Zbilinearall27 1 QC2.91 [2.27, 3.72]2.20+1.96 [-0.17, 3.22]3.41 [2.69, 4.16]11% [0%, 19%]33%56%+0.43+0.572026-01-09 → 2026-08-30
tmin12Znearest30d22 1 QC2.75 [2.04, 3.56]1.82+2.39 [1.21, 3.30]3.29 [2.46, 4.06]14% [5%, 22%]41%55%-0.03+0.322026-08-09 → 2026-08-30
tmin12Znearest90d22 1 QC2.75 [2.02, 3.60]1.82+2.39 [0.93, 3.33]3.29 [2.42, 4.07]14% [0%, 24%]41%55%-0.03+0.322026-08-09 → 2026-08-30
tmin12Znearest365d27 1 QC2.85 [2.24, 3.64]2.20+1.85 [-0.11, 3.02]3.34 [2.64, 4.07]11% [0%, 20%]37%56%+0.44+0.572026-01-09 → 2026-08-30
tmin12Znearestall27 1 QC2.85 [2.20, 3.65]2.20+1.85 [-0.25, 3.12]3.34 [2.64, 4.10]11% [0%, 19%]37%56%+0.44+0.572026-01-09 → 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 8, 00Z bilinear tmax+10+50-5-102026-08-09: -5.13 °F2026-08-10: -5.7 °F2026-08-11: -8.9 °F2026-08-12: -4.99 °F2026-08-13: -7.6 °F2026-08-14: -4.69 °F2026-08-15: -5.61 °F2026-08-16: -6.21 °F2026-08-17: -4.04 °F2026-08-18: -4.61 °F2026-08-19: -4.45 °F2026-08-20: -3.31 °F2026-08-21: -6.5 °F2026-08-22: -5.2 °F2026-08-23: -6.38 °F2026-08-24: -3.25 °F2026-08-25: -2.24 °F2026-08-26: -3.3 °F2026-08-27: -2.99 °F2026-08-28: -9.49 °F2026-08-29: -6.09 °F2026-08-30: -3.5 °F2026-08-092026-08-30°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 (22 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-3.50
2026-08-29-6.09
2026-08-28-9.49
2026-08-27-2.99
2026-08-26-3.30
2026-08-25-2.24
2026-08-24-3.25
2026-08-23-6.38
2026-08-22-5.20
2026-08-21-6.50
2026-08-20-3.31
2026-08-19-4.45
2026-08-18-4.61
2026-08-17-4.04
2026-08-16-6.21
2026-08-15-5.61
2026-08-14-4.69
2026-08-13-7.60
2026-08-12-4.99
2026-08-11-8.90
2026-08-10-5.70
2026-08-09-5.13

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KMSY, lead day 8-10 to -9 °F: 1 day-9 to -8 °F: 1 day-8 to -7 °F: 2 days-7 to -6 °F: 4 days-6 to -5 °F: 5 days-5 to -4 °F: 6 days-4 to -3 °F: 6 days-3 to -2 °F: 2 days-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| 4.84 · P90 |e| 7.55 °F-100+10 °Fn = 28 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
-10.00-9.001
-9.00-8.001
-8.00-7.002
-7.00-6.004
-6.00-5.005
-5.00-4.006
-4.00-3.006
-3.00-2.002
-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
2026-08225.19 -5.19
2026-0164.41 -4.41

Availability

ModelScored period DaysCoverage
GraphCast (IFS init)2026-01-09 → 2026-08-30 28
GraphCast (IFS init)2026-01-09 → 2026-08-30 28
GraphCast (IFS init)2026-01-09 → 2026-08-30 27
GraphCast (IFS init)2026-01-09 → 2026-08-30 27

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 22 +0.11 [-1.05, 1.41] no
NCEP GFS 22 +1.71 [0.46, 3.34] yes
ECMWF IFS HRES 17 +0.88 [0.04, 2.39] yes
Persistence (baseline) 22 +1.96 [0.41, 2.84] yes

Cite this page

ShortCastCheck, KMSY graphcast_ifs lead 8, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KMSY/model/graphcast_ifs/lead/8/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KMSY (New Orleans Intl), model graphcast_ifs, lead day 8. 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/8/

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