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

KMSY — New Orleans Intl

29.9928, -90.2508 · 1 m· standard offset UTC-6 h · truth product CLIMSY

These pages are always bilinear interpolation, the headline method. The nearest-node variant, and every other window/initialization/interpolation/variable combination, is published on each permanent link below — follow any number.

Daily maximum temperature — MAE °F

the last 90 days, 00Z, bilinear. MAE with the bias and n underneath; every cell links to its permanent page. The sparkline shows the same model across lead days 1–9 on a scale shared within this table.
Modeld0d1d2d3d4d5d6d7d8d9lead 1–9
ECMWF AIFS Singleaifs_single 4.01-3.84 · n=30 4.31-4.09 · n=29 4.33-4.33 · n=28 4.62-4.62 · n=27 4.71-4.71 · n=26 4.51-4.51 · n=25 4.99-4.99 · n=24 5.03-5.03 · n=23 5.08-4.95 · n=22 4.83-4.38 · n=21 ECMWF AIFS Single MAE by lead day 1 to 9, tmax
Aurora (GFS init)aurora_gfs 7.03-7.03 · n=2 7.22-7.22 · n=1 Aurora (GFS init) MAE by lead day 1 to 9, tmax
Aurora (IFS init)aurora_ifs 6.66-6.66 · n=3 6.90-6.90 · n=2 3.91-3.91 · n=1 Aurora (IFS init) MAE by lead day 1 to 9, tmax
FourCastNet v2 (GFS init)fourcastnet_gfs 4.07-4.07 · n=2 2.88-2.88 · n=1 FourCastNet v2 (GFS init) MAE by lead day 1 to 9, tmax
FourCastNet v2 (IFS init)fourcastnet_ifs 3.85-3.85 · n=3 3.18-3.18 · n=2 2.13-2.13 · n=1 FourCastNet v2 (IFS init) MAE by lead day 1 to 9, tmax
NCEP GFSgfs 5.06-4.80 · n=30 4.69-4.41 · n=29 4.66-4.44 · n=28 3.78-3.78 · n=27 4.12-4.12 · n=26 3.38-2.97 · n=25 4.53-4.46 · n=24 4.14-3.62 · n=23 3.48-3.27 · n=22 4.48-4.41 · n=21 NCEP GFS MAE by lead day 1 to 9, tmax
GraphCast (GFS init)graphcast_gfs 5.57-5.57 · n=2 5.32-5.32 · n=1 GraphCast (GFS init) MAE by lead day 1 to 9, tmax
GraphCast (IFS init)graphcast_ifs 4.83-4.76 · n=28 5.07-4.99 · n=27 4.93-4.93 · n=26 5.22-5.22 · n=25 5.65-5.65 · n=25 5.25-5.25 · n=25 5.60-5.60 · n=24 5.38-5.38 · n=23 5.19-5.19 · n=22 5.15-4.76 · n=21 GraphCast (IFS init) MAE by lead day 1 to 9, tmax
ECMWF IFS HRESifs_hres 4.30-4.30 · n=24 4.05-3.45 · n=23 4.47-4.47 · n=22 4.80-4.80 · n=22 4.99-4.99 · n=20 5.16-5.16 · n=18 4.64-4.64 · n=19 4.15-4.10 · n=18 3.96-3.96 · n=17 4.57-3.94 · n=16 ECMWF IFS HRES MAE by lead day 1 to 9, tmax
Pangu-Weather (GFS init)pangu_gfs 4.73-4.73 · n=2 5.45-5.45 · n=1 Pangu-Weather (GFS init) MAE by lead day 1 to 9, tmax
Pangu-Weather (IFS init)pangu_ifs 4.27-4.27 · n=3 4.24-4.24 · n=2 2.77-2.77 · n=1 Pangu-Weather (IFS init) MAE by lead day 1 to 9, tmax
Persistence (baseline)persistence 1.96-0.04 · n=90 2.39-0.08 · n=90 2.61-0.12 · n=90 2.81-0.12 · n=90 2.89-0.20 · n=90 3.08-0.28 · n=90 3.17-0.39 · n=90 3.21-0.61 · n=90 3.22-0.80 · n=90 Persistence (baseline) MAE by lead day 1 to 9, tmax

Up to 1 of the scored days in this table carry a QC flag on the observation (a CLI value that disagreed with the hourly observations, or a fallback source). They are kept in the scores and counted here rather than dropped — see methodology.

+ 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 minimum temperature — MAE °F

the last 90 days, 00Z, bilinear. MAE with the bias and n underneath; every cell links to its permanent page. The sparkline shows the same model across lead days 1–9 on a scale shared within this table.
Modeld0d1d2d3d4d5d6d7d8d9lead 1–9
ECMWF AIFS Singleaifs_single 2.77+2.61 · n=30 3.07+2.89 · n=29 3.26+2.94 · n=28 3.30+3.04 · n=27 3.40+3.13 · n=26 3.49+3.31 · n=25 3.50+3.33 · n=24 3.53+3.38 · n=23 3.56+3.05 · n=22 3.56+3.25 · n=21 ECMWF AIFS Single MAE by lead day 1 to 9, tmin
Aurora (GFS init)aurora_gfs 2.67-0.05 · n=2 3.19-3.19 · n=1 Aurora (GFS init) MAE by lead day 1 to 9, tmin
Aurora (IFS init)aurora_ifs 1.78+0.02 · n=3 2.40-0.74 · n=2 3.66-3.66 · n=1 Aurora (IFS init) MAE by lead day 1 to 9, tmin
FourCastNet v2 (GFS init)fourcastnet_gfs 2.24-1.15 · n=2 2.27-2.27 · n=1 FourCastNet v2 (GFS init) MAE by lead day 1 to 9, tmin
FourCastNet v2 (IFS init)fourcastnet_ifs 1.49-0.47 · n=3 1.82-0.50 · n=2 2.27-2.27 · n=1 FourCastNet v2 (IFS init) MAE by lead day 1 to 9, tmin
NCEP GFSgfs 1.68+1.34 · n=30 1.80+1.40 · n=29 1.58+1.17 · n=28 1.70+1.00 · n=27 2.07+1.29 · n=26 2.17+1.45 · n=25 2.27+0.99 · n=24 1.96+0.96 · n=23 2.14+0.94 · n=22 2.11+0.86 · n=21 NCEP GFS MAE by lead day 1 to 9, tmin
GraphCast (GFS init)graphcast_gfs 2.51-0.22 · n=2 2.65-2.65 · n=1 GraphCast (GFS init) MAE by lead day 1 to 9, tmin
GraphCast (IFS init)graphcast_ifs 3.11+2.98 · n=28 3.06+2.82 · n=27 3.09+2.78 · n=26 3.01+2.93 · n=25 2.93+2.77 · n=25 2.94+2.60 · n=25 2.88+2.59 · n=24 2.87+2.42 · n=23 2.82+2.49 · n=22 2.92+2.38 · n=21 GraphCast (IFS init) MAE by lead day 1 to 9, tmin
ECMWF IFS HRESifs_hres 3.49+3.38 · n=24 3.45+3.33 · n=23 3.44+3.29 · n=22 3.46+3.30 · n=22 3.26+2.98 · n=20 3.06+2.71 · n=18 3.35+2.91 · n=19 3.42+2.88 · n=18 3.56+2.97 · n=17 3.66+3.06 · n=16 ECMWF IFS HRES MAE by lead day 1 to 9, tmin
Pangu-Weather (GFS init)pangu_gfs 2.12-0.17 · n=2 2.75-2.75 · n=1 Pangu-Weather (GFS init) MAE by lead day 1 to 9, tmin
Pangu-Weather (IFS init)pangu_ifs 1.63-0.14 · n=3 1.93-1.00 · n=2 3.66-3.66 · n=1 Pangu-Weather (IFS init) MAE by lead day 1 to 9, tmin
Persistence (baseline)persistence 1.44-0.07 · n=90 1.97-0.08 · n=90 2.11-0.11 · n=90 2.04-0.11 · n=90 1.99-0.12 · n=90 2.12-0.12 · n=90 2.06-0.21 · n=90 2.20-0.31 · n=90 2.30-0.37 · n=90 Persistence (baseline) MAE by lead day 1 to 9, tmin

Up to 1 of the scored days in this table carry a QC flag on the observation (a CLI value that disagreed with the hourly observations, or a fallback source). They are kept in the scores and counted here rather than dropped — see methodology.

Month by month

MAE °F at lead day 1, 00Z, bilinear, daily maximum — the seasonal slice behind the window averages. A model that is excellent in one season and poor in another shows up here and nowhere else.

Monthaifs_singleaurora_gfsaurora_ifsfourcastnet_gfsfourcastnet_ifsgfsgraphcast_gfsgraphcast_ifsifs_hrespangu_gfspangu_ifs
2026-08 4.31-4.09 · n=297.22-7.22 · n=16.90-6.90 · n=22.88-2.88 · n=13.18-3.18 · n=24.69-4.41 · n=295.32-5.32 · n=15.07-4.99 · n=274.05-3.45 · n=235.45-5.45 · n=14.24-4.24 · n=2
2026-01 6.27-6.27 · n=6

Model availability at this station

ModelPeriod Scored daysCoverage
ECMWF AIFS Single 2026-08-02 → 2026-08-3029
Aurora (GFS init) 2026-08-30 → 2026-08-301
Aurora (IFS init) 2026-08-29 → 2026-08-302
FourCastNet v2 (GFS init) 2026-08-30 → 2026-08-301
FourCastNet v2 (IFS init) 2026-08-29 → 2026-08-302
NCEP GFS 2026-08-02 → 2026-08-3029
GraphCast (GFS init) 2026-08-30 → 2026-08-301
GraphCast (IFS init) 2026-01-02 → 2026-08-3033
ECMWF IFS HRES 2026-08-02 → 2026-08-3023
Pangu-Weather (GFS init) 2026-08-30 → 2026-08-301
Pangu-Weather (IFS init) 2026-08-29 → 2026-08-302
Persistence (baseline) 2024-01-02 → 2026-08-30972

Observed truth — last 30 days

Climatological dayTmax °F Tmin °FSourceFlag
2026-08-309082OBSobs_fallback
2026-08-299477CLI
2026-08-289376CLI
2026-08-278773CLI
2026-08-269575CLI
2026-08-259475CLI
2026-08-249576CLI
2026-08-239780CLI
2026-08-229674CLI
2026-08-219776CLI
2026-08-209677CLI
2026-08-199679CLI
2026-08-189679CLI
2026-08-179579CLI
2026-08-169679CLI
2026-08-159677CLI
2026-08-149575CLI
2026-08-139679CLI
2026-08-129378CLI
2026-08-119477CLI
2026-08-109377CLI
2026-08-099075CLI
2026-08-089177CLI
2026-08-079176CLI
2026-08-069277CLI
2026-08-059577CLI
2026-08-049475CLI
2026-08-039375CLI
2026-08-028476CLI
2026-08-019678CLI

All scores as JSON scores_latest.csv daily_errors.csv.gz data & licences