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

FourCastNet v2 (IFS init) (fourcastnet_ifs)

source aiwp · product FOUR · initial conditions from IFS · steps every 6 h to 240 h · initializations 0, 12 UTC.

Scores use the latest model version segment, FOUR_v200, starting 2026-08-28. Earlier days ran a different version of the model and are excluded rather than silently pooled into the same average.

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 by station

the last 30 days, 00Z, bilinear. MAE with the bias and n underneath; every cell links to its permanent page. The sparkline shows this station across lead days 1–9 on a scale shared within this table.
Stationd0d1d2d3d4d5d6d7d8d9lead 1–9
KATL 4.43-4.43 · n=3 2.78-2.78 · n=2 4.64-4.64 · n=1 KATL MAE by lead day 1 to 9, tmax
KAUS 6.26-6.26 · n=3 4.75-4.75 · n=2 4.13-4.13 · n=1 KAUS MAE by lead day 1 to 9, tmax
KBOS 4.31-3.73 · n=2 4.78-2.31 · n=2 6.09-6.09 · n=1 KBOS MAE by lead day 1 to 9, tmax
KDCA 5.71-5.71 · n=3 2.44-2.44 · n=2 2.89-2.89 · n=1 KDCA MAE by lead day 1 to 9, tmax
KDEN 5.50-5.50 · n=3 5.56-5.56 · n=2 4.08-4.08 · n=1 KDEN MAE by lead day 1 to 9, tmax
KDFW 5.31-5.31 · n=3 5.73-5.73 · n=2 4.82-4.82 · n=1 KDFW MAE by lead day 1 to 9, tmax
KEWR 4.75-4.75 · n=3 1.85-1.85 · n=2 2.09-2.09 · n=1 KEWR MAE by lead day 1 to 9, tmax
KIAH 4.48-4.48 · n=3 3.71-3.71 · n=2 3.08-3.08 · n=1 KIAH MAE by lead day 1 to 9, tmax
KLAS 5.93-5.93 · n=3 6.07-6.07 · n=2 5.92-5.92 · n=1 KLAS MAE by lead day 1 to 9, tmax
KLAX 2.73-2.73 · n=3 3.08-3.08 · n=2 3.13-3.13 · n=1 KLAX MAE by lead day 1 to 9, tmax
KMIA 5.08-5.08 · n=3 4.98-4.98 · n=2 5.26-5.26 · n=1 KMIA MAE by lead day 1 to 9, tmax
KMSP 5.88-5.88 · n=3 6.41-6.41 · n=2 5.88-5.88 · n=1 KMSP MAE by lead day 1 to 9, tmax
KMSY 3.85-3.85 · n=3 3.18-3.18 · n=2 2.13-2.13 · n=1 KMSY MAE by lead day 1 to 9, tmax
KNYC 2.89-1.75 · n=3 2.01+1.18 · n=2 0.52+0.52 · n=1 KNYC MAE by lead day 1 to 9, tmax
KOKC 6.62-6.62 · n=3 7.13-7.13 · n=2 7.02-7.02 · n=1 KOKC MAE by lead day 1 to 9, tmax
KORD 3.36-3.36 · n=3 2.45-2.45 · n=2 0.02-0.02 · n=1 KORD MAE by lead day 1 to 9, tmax
KPHL 5.11-5.11 · n=3 2.71-2.54 · n=2 4.59-4.59 · n=1 KPHL MAE by lead day 1 to 9, tmax
KPHX 7.94-7.94 · n=3 10.33-10.33 · n=2 11.70-11.70 · n=1 KPHX MAE by lead day 1 to 9, tmax
KSAN 2.69-2.69 · n=3 2.56-2.56 · n=2 0.54-0.54 · n=1 KSAN MAE by lead day 1 to 9, tmax
KSAT 4.22-4.22 · n=3 2.73-2.73 · n=2 1.67-1.67 · n=1 KSAT MAE by lead day 1 to 9, tmax
KSEA 2.16-2.06 · n=3 1.70-1.70 · n=2 1.53+1.53 · n=1 KSEA MAE by lead day 1 to 9, tmax
KSFO 3.34-1.87 · n=3 2.45-2.45 · n=2 1.61-1.61 · n=1 KSFO MAE by lead day 1 to 9, tmax
KTTN 2.72-1.90 · n=3 2.66+0.67 · n=2 1.07-1.07 · n=1 KTTN MAE by lead day 1 to 9, tmax

Up to 2 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 by station

the last 30 days, 00Z, bilinear. MAE with the bias and n underneath; every cell links to its permanent page. The sparkline shows this station across lead days 1–9 on a scale shared within this table.
Stationd0d1d2d3d4d5d6d7d8d9lead 1–9
KATL 3.33-3.33 · n=3 0.89-0.89 · n=2 0.21+0.21 · n=1 KATL MAE by lead day 1 to 9, tmin
KAUS 2.00+0.50 · n=3 4.46+4.46 · n=2 4.42+4.42 · n=1 KAUS MAE by lead day 1 to 9, tmin
KBOS 2.63-2.63 · n=2 2.51-0.37 · n=2 1.43-1.43 · n=1 KBOS MAE by lead day 1 to 9, tmin
KDCA 3.84-3.84 · n=3 0.51-0.04 · n=2 0.76+0.76 · n=1 KDCA MAE by lead day 1 to 9, tmin
KDEN 2.09+1.75 · n=3 1.89+1.89 · n=2 1.38+1.38 · n=1 KDEN MAE by lead day 1 to 9, tmin
KDFW 1.10-0.81 · n=3 0.95-0.95 · n=2 1.39-1.39 · n=1 KDFW MAE by lead day 1 to 9, tmin
KEWR 0.91+0.80 · n=3 3.02+3.02 · n=2 4.08+4.08 · n=1 KEWR MAE by lead day 1 to 9, tmin
KIAH 2.50+1.86 · n=3 2.26+2.26 · n=2 2.49+2.49 · n=1 KIAH MAE by lead day 1 to 9, tmin
KLAS 4.94-4.94 · n=3 6.12-6.12 · n=2 7.64-7.64 · n=1 KLAS MAE by lead day 1 to 9, tmin
KLAX 2.26+2.26 · n=3 2.05+2.05 · n=2 1.38+1.38 · n=1 KLAX MAE by lead day 1 to 9, tmin
KMIA 2.31+2.26 · n=3 3.41+3.41 · n=2 0.73+0.73 · n=1 KMIA MAE by lead day 1 to 9, tmin
KMSP 2.15-2.15 · n=3 1.97-1.97 · n=2 1.40-1.40 · n=1 KMSP MAE by lead day 1 to 9, tmin
KMSY 1.49-0.47 · n=3 1.82-0.50 · n=2 2.27-2.27 · n=1 KMSY MAE by lead day 1 to 9, tmin
KNYC 1.98+0.15 · n=3 1.84+1.11 · n=2 0.99+0.99 · n=1 KNYC MAE by lead day 1 to 9, tmin
KOKC 2.74+1.92 · n=3 2.93+2.93 · n=2 0.82+0.82 · n=1 KOKC MAE by lead day 1 to 9, tmin
KORD 1.66+0.14 · n=3 2.27+2.27 · n=2 2.44+2.44 · n=1 KORD MAE by lead day 1 to 9, tmin
KPHL 1.20-0.92 · n=3 3.30+3.30 · n=2 5.37+5.37 · n=1 KPHL MAE by lead day 1 to 9, tmin
KPHX 4.99-4.99 · n=3 4.13-4.13 · n=2 6.16-6.16 · n=1 KPHX MAE by lead day 1 to 9, tmin
KSAN 1.21+0.09 · n=3 1.16+0.30 · n=2 0.82-0.82 · n=1 KSAN MAE by lead day 1 to 9, tmin
KSAT 0.95-0.51 · n=3 1.76+0.21 · n=2 1.22-1.22 · n=1 KSAT MAE by lead day 1 to 9, tmin
KSEA 2.19+2.19 · n=3 1.86+1.86 · n=2 0.48-0.48 · n=1 KSEA MAE by lead day 1 to 9, tmin
KSFO 2.71-2.24 · n=3 1.23-1.23 · n=2 0.40-0.40 · n=1 KSFO MAE by lead day 1 to 9, tmin
KTTN 3.75+3.75 · n=3 8.43+8.43 · n=2 10.97+10.97 · n=1 KTTN MAE by lead day 1 to 9, tmin

Up to 2 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 slices live on the canonical page: they do not depend on the window, initialization or interpolation selected here.

Source and licence

Where it comes from

aiwp · FOUR · IFS initial conditions

Steps every 6 h to 240 h; sampled at 00/06/12/18 UTC only.

Licence

NOAA/CIRA AIWP, U.S. Government work, public domain. Cite Radford et al. (2025), BAMS, doi:10.1175/BAMS-D-24-0057.1.

Post-processing

None. Raw grid values, bilinear (headline) or nearest-node interpolation, no MOS, no bias correction, no downscaling.

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