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 2

KMSY · graphcast_ifs · lead 2

Target day = initialization date + 2 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
tmax00Zbilinear30d26 1 QC4.93 [4.49, 5.29]1.02-4.93 [-5.29, -4.49]5.10 [4.63, 5.47]0% [0%, 0%]0%8%-1.51+0.482026-08-03 → 2026-08-30
tmax00Zbilinear90d26 1 QC4.93 [4.43, 5.37]1.02-4.93 [-5.37, -4.43]5.10 [4.54, 5.54]0% [0%, 0%]0%8%-1.51+0.482026-08-03 → 2026-08-30
tmax00Zbilinear365d32 1 QC5.13 [4.58, 5.69]1.39-5.13 [-5.69, -4.58]5.44 [4.73, 6.13]3% [0%, 12%]3%9%-0.37+0.642026-01-03 → 2026-08-30
tmax00Zbilinearall32 1 QC5.13 [4.59, 5.74]1.39-5.13 [-5.74, -4.59]5.44 [4.77, 6.16]3% [0%, 11%]3%9%-0.37+0.642026-01-03 → 2026-08-30
tmax00Znearest30d26 1 QC4.86 [4.41, 5.23]1.02-4.86 [-5.23, -4.41]5.03 [4.55, 5.41]0% [0%, 0%]0%8%-1.48+0.482026-08-03 → 2026-08-30
tmax00Znearest90d26 1 QC4.86 [4.35, 5.31]1.02-4.86 [-5.31, -4.35]5.03 [4.47, 5.48]0% [0%, 0%]0%8%-1.48+0.482026-08-03 → 2026-08-30
tmax00Znearest365d32 1 QC5.05 [4.51, 5.60]1.39-5.05 [-5.60, -4.51]5.36 [4.67, 6.04]3% [0%, 12%]3%9%-0.35+0.642026-01-03 → 2026-08-30
tmax00Znearestall32 1 QC5.05 [4.52, 5.64]1.39-5.05 [-5.64, -4.52]5.36 [4.69, 6.07]3% [0%, 11%]3%9%-0.35+0.642026-01-03 → 2026-08-30
tmax12Zbilinear30d26 1 QC5.45 [5.04, 5.86]1.06-5.45 [-5.86, -5.04]5.60 [5.17, 6.00]0% [0%, 0%]0%0%-1.78+0.462026-08-03 → 2026-08-30
tmax12Zbilinear90d26 1 QC5.45 [4.92, 5.97]1.06-5.45 [-5.97, -4.92]5.60 [5.04, 6.10]0% [0%, 0%]0%0%-1.78+0.462026-08-03 → 2026-08-30
tmax12Zbilinear365d31 1 QC5.61 [5.10, 6.18]1.29-5.61 [-6.18, -5.10]5.84 [5.27, 6.49]0% [0%, 0%]3%3%-0.49+0.672026-01-03 → 2026-08-30
tmax12Zbilinearall31 1 QC5.61 [5.11, 6.25]1.29-5.61 [-6.25, -5.11]5.84 [5.25, 6.59]0% [0%, 0%]3%3%-0.49+0.672026-01-03 → 2026-08-30
tmax12Znearest30d26 1 QC5.38 [4.97, 5.78]1.07-5.38 [-5.78, -4.97]5.53 [5.09, 5.93]0% [0%, 0%]0%0%-1.74+0.462026-08-03 → 2026-08-30
tmax12Znearest90d26 1 QC5.38 [4.84, 5.91]1.07-5.38 [-5.91, -4.84]5.53 [4.96, 6.05]0% [0%, 0%]0%0%-1.74+0.462026-08-03 → 2026-08-30
tmax12Znearest365d31 1 QC5.53 [5.02, 6.11]1.29-5.53 [-6.11, -5.02]5.76 [5.19, 6.40]0% [0%, 0%]3%3%-0.47+0.672026-01-03 → 2026-08-30
tmax12Znearestall31 1 QC5.53 [5.03, 6.16]1.29-5.53 [-6.16, -5.03]5.76 [5.17, 6.49]0% [0%, 0%]3%3%-0.47+0.672026-01-03 → 2026-08-30
tmin00Zbilinear30d26 1 QC3.09 [2.51, 3.87]1.30+2.78 [1.99, 3.44]3.36 [2.62, 4.15]4% [0%, 11%]12%62%-0.49+0.372026-08-03 → 2026-08-30
tmin00Zbilinear90d26 1 QC3.09 [2.40, 3.93]1.30+2.78 [1.82, 3.38]3.36 [2.45, 4.25]4% [0%, 11%]12%62%-0.49+0.372026-08-03 → 2026-08-30
tmin00Zbilinear365d32 1 QC3.12 [2.53, 3.96]1.51+2.72 [1.83, 3.43]3.49 [2.65, 4.40]3% [0%, 10%]16%62%+0.05+0.552026-01-03 → 2026-08-30
tmin00Zbilinearall32 1 QC3.12 [2.50, 3.94]1.51+2.72 [1.91, 3.36]3.49 [2.62, 4.36]3% [0%, 10%]16%62%+0.05+0.552026-01-03 → 2026-08-30
tmin00Znearest30d26 1 QC3.01 [2.41, 3.80]1.31+2.68 [1.87, 3.33]3.27 [2.52, 4.07]4% [0%, 11%]19%62%-0.45+0.372026-08-03 → 2026-08-30
tmin00Znearest90d26 1 QC3.01 [2.29, 3.88]1.31+2.68 [1.70, 3.27]3.27 [2.34, 4.17]4% [0%, 11%]19%62%-0.45+0.372026-08-03 → 2026-08-30
tmin00Znearest365d32 1 QC3.05 [2.43, 3.92]1.52+2.62 [1.74, 3.33]3.42 [2.56, 4.33]3% [0%, 10%]22%62%+0.07+0.552026-01-03 → 2026-08-30
tmin00Znearestall32 1 QC3.05 [2.40, 3.90]1.52+2.62 [1.82, 3.27]3.42 [2.51, 4.30]3% [0%, 10%]22%62%+0.07+0.552026-01-03 → 2026-08-30
tmin12Zbilinear30d26 1 QC2.83 [2.22, 3.69]1.41+2.48 [1.58, 3.19]3.15 [2.39, 4.02]4% [0%, 11%]38%62%-0.36+0.322026-08-03 → 2026-08-30
tmin12Zbilinear90d26 1 QC2.83 [2.09, 3.89]1.41+2.48 [1.42, 3.11]3.15 [2.26, 4.17]4% [0%, 11%]38%62%-0.36+0.322026-08-03 → 2026-08-30
tmin12Zbilinear365d31 1 QC3.01 [2.28, 4.14]1.77+2.39 [1.36, 3.12]3.42 [2.46, 4.51]3% [0%, 10%]35%58%+0.08+0.482026-01-03 → 2026-08-30
tmin12Zbilinearall31 1 QC3.01 [2.22, 4.08]1.77+2.39 [1.39, 3.08]3.42 [2.40, 4.45]3% [0%, 10%]35%58%+0.08+0.482026-01-03 → 2026-08-30
tmin12Znearest30d26 1 QC2.74 [2.12, 3.63]1.41+2.37 [1.47, 3.09]3.08 [2.29, 3.94]4% [0%, 11%]42%62%-0.32+0.322026-08-03 → 2026-08-30
tmin12Znearest90d26 1 QC2.74 [1.98, 3.85]1.41+2.37 [1.30, 3.00]3.08 [2.16, 4.13]4% [0%, 11%]42%62%-0.32+0.322026-08-03 → 2026-08-30
tmin12Znearest365d31 1 QC2.95 [2.17, 4.13]1.77+2.29 [1.24, 3.01]3.36 [2.39, 4.49]3% [0%, 10%]39%58%+0.10+0.482026-01-03 → 2026-08-30
tmin12Znearestall31 1 QC2.95 [2.14, 4.05]1.77+2.29 [1.30, 2.98]3.36 [2.31, 4.42]3% [0%, 10%]39%58%+0.10+0.482026-01-03 → 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 2, 00Z bilinear tmax+10+50-5-102026-08-03: -4.88 °F2026-08-04: -6.69 °F2026-08-05: -6.2 °F2026-08-06: -5.99 °F2026-08-07: -3.26 °F2026-08-08: -4.56 °F2026-08-09: -2.59 °F2026-08-10: -7.57 °F2026-08-11: -4.92 °F2026-08-12: -7.29 °F2026-08-13: -6.31 °F2026-08-14: -3.79 °F2026-08-15: -5.04 °F2026-08-16: -4.85 °F2026-08-17: -2.34 °F2026-08-18: -3.77 °F2026-08-19: -4.45 °F2026-08-20: -5.3 °F2026-08-21: -6.65 °F2026-08-22: -5.3 °F2026-08-23: -4.73 °F2026-08-24: -4.68 °F2026-08-25: -5.2 °F2026-08-26: -4.48 °F2026-08-27: -3.59 °F2026-08-30: -3.82 °F2026-08-032026-08-30°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 (28 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-3.82
2026-08-29—
2026-08-28—
2026-08-27-3.59
2026-08-26-4.48
2026-08-25-5.20
2026-08-24-4.68
2026-08-23-4.73
2026-08-22-5.30
2026-08-21-6.65
2026-08-20-5.30
2026-08-19-4.45
2026-08-18-3.77
2026-08-17-2.34
2026-08-16-4.85
2026-08-15-5.04
2026-08-14-3.79
2026-08-13-6.31
2026-08-12-7.29
2026-08-11-4.92
2026-08-10-7.57
2026-08-09-2.59
2026-08-08-4.56
2026-08-07-3.26
2026-08-06-5.99
2026-08-05-6.20
2026-08-04-6.69
2026-08-03-4.88

Error distribution

Distribution of the signed daily error in °F for GraphCast (IFS init) at KMSY, lead day 2-10 to -9 °F: 0 days-9 to -8 °F: 3 days-8 to -7 °F: 2 days-7 to -6 °F: 5 days-6 to -5 °F: 5 days-5 to -4 °F: 9 days-4 to -3 °F: 5 days-3 to -2 °F: 2 days-2 to -1 °F: 0 days-1 to 0 °F: 1 day0 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| 4.9 · P90 |e| 7.54 °F-100+10 °Fn = 32 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
-10.00-9.000
-9.00-8.003
-8.00-7.002
-7.00-6.005
-6.00-5.005
-5.00-4.009
-4.00-3.005
-3.00-2.002
-2.00-1.000
-1.00+0.001
+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
2026-08264.93 -4.93
2026-0165.99 -5.99

Availability

ModelScored period DaysCoverage
GraphCast (IFS init)2026-01-03 → 2026-08-30 32
GraphCast (IFS init)2026-01-03 → 2026-08-30 32
GraphCast (IFS init)2026-01-03 → 2026-08-30 31
GraphCast (IFS init)2026-01-03 → 2026-08-30 31

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 26 +0.71 [0.19, 1.21] yes
Aurora (IFS init) 1 -0.10 [-0.10, -0.10] yes
FourCastNet v2 (IFS init) 1 +1.69 [1.69, 1.69] yes
NCEP GFS 26 +0.54 [-0.67, 1.60] no
ECMWF IFS HRES 20 +0.42 [-0.74, 1.68] no
Pangu-Weather (IFS init) 1 +1.05 [1.05, 1.05] yes
Persistence (baseline) 26 +2.97 [1.27, 3.96] yes

Cite this page

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

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

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