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

Pangu-Weather (GFS init) (pangu_gfs)

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

Scores use the latest model version segment, PANG_v100, 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 2.50-2.50 · n=2 3.98-3.98 · n=1 KATL MAE by lead day 1 to 9, tmax
KAUS 3.58-3.58 · n=2 4.44-4.44 · n=1 KAUS MAE by lead day 1 to 9, tmax
KBOS 2.65-1.20 · n=2 3.50-3.50 · n=1 KBOS MAE by lead day 1 to 9, tmax
KDCA 2.21-2.21 · n=2 2.52-2.52 · n=1 KDCA MAE by lead day 1 to 9, tmax
KDEN 4.14-4.14 · n=2 0.26+0.26 · n=1 KDEN MAE by lead day 1 to 9, tmax
KDFW 2.26-2.26 · n=2 1.77-1.77 · n=1 KDFW MAE by lead day 1 to 9, tmax
KEWR 1.28+0.51 · n=2 1.93+1.93 · n=1 KEWR MAE by lead day 1 to 9, tmax
KIAH 2.50-2.50 · n=2 2.14-2.14 · n=1 KIAH MAE by lead day 1 to 9, tmax
KLAS 5.16-5.16 · n=2 4.89-4.89 · n=1 KLAS MAE by lead day 1 to 9, tmax
KLAX 2.47-2.47 · n=2 2.39-2.39 · n=1 KLAX MAE by lead day 1 to 9, tmax
KMIA 5.83-5.83 · n=2 5.99-5.99 · n=1 KMIA MAE by lead day 1 to 9, tmax
KMSP 4.42-4.42 · n=2 0.54-0.54 · n=1 KMSP MAE by lead day 1 to 9, tmax
KMSY 4.73-4.73 · n=2 5.45-5.45 · n=1 KMSY MAE by lead day 1 to 9, tmax
KNYC 3.81+3.81 · n=2 4.44+4.44 · n=1 KNYC MAE by lead day 1 to 9, tmax
KOKC 3.55-3.55 · n=2 2.66-2.66 · n=1 KOKC MAE by lead day 1 to 9, tmax
KORD 2.36-2.36 · n=2 4.23-4.23 · n=1 KORD MAE by lead day 1 to 9, tmax
KPHL 2.09-2.09 · n=2 2.54-2.54 · n=1 KPHL MAE by lead day 1 to 9, tmax
KPHX 8.75-8.75 · n=2 7.42-7.42 · n=1 KPHX MAE by lead day 1 to 9, tmax
KSAN 5.38-5.38 · n=2 4.97-4.97 · n=1 KSAN MAE by lead day 1 to 9, tmax
KSAT 3.03-3.03 · n=2 3.17-3.17 · n=1 KSAT MAE by lead day 1 to 9, tmax
KSEA 3.78-3.78 · n=2 2.42-2.42 · n=1 KSEA MAE by lead day 1 to 9, tmax
KSFO 7.29-7.29 · n=2 6.64-6.64 · n=1 KSFO MAE by lead day 1 to 9, tmax
KTTN 2.25+2.25 · n=2 2.46+2.46 · 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 1.35-1.35 · n=2 0.45-0.45 · n=1 KATL MAE by lead day 1 to 9, tmin
KAUS 5.39+5.39 · n=2 4.55+4.55 · n=1 KAUS MAE by lead day 1 to 9, tmin
KBOS 3.35-2.72 · n=2 4.10-4.10 · n=1 KBOS MAE by lead day 1 to 9, tmin
KDCA 2.04-1.33 · n=2 1.92-1.92 · n=1 KDCA MAE by lead day 1 to 9, tmin
KDEN 1.32+1.32 · n=2 0.63+0.63 · n=1 KDEN MAE by lead day 1 to 9, tmin
KDFW 2.66+2.66 · n=2 1.08+1.08 · n=1 KDFW MAE by lead day 1 to 9, tmin
KEWR 1.83+1.83 · n=2 0.80+0.80 · n=1 KEWR MAE by lead day 1 to 9, tmin
KIAH 0.81+0.68 · n=2 1.36+1.36 · n=1 KIAH MAE by lead day 1 to 9, tmin
KLAS 7.76-7.76 · n=2 6.67-6.67 · n=1 KLAS MAE by lead day 1 to 9, tmin
KLAX 1.25+0.02 · n=2 2.07-2.07 · n=1 KLAX MAE by lead day 1 to 9, tmin
KMIA 3.53+3.53 · n=2 0.07-0.07 · n=1 KMIA MAE by lead day 1 to 9, tmin
KMSP 0.81-0.81 · n=2 1.26-1.26 · n=1 KMSP MAE by lead day 1 to 9, tmin
KMSY 2.12-0.17 · n=2 2.75-2.75 · n=1 KMSY MAE by lead day 1 to 9, tmin
KNYC 2.04+0.08 · n=2 1.98-1.98 · n=1 KNYC MAE by lead day 1 to 9, tmin
KOKC 6.89+6.89 · n=2 5.58+5.58 · n=1 KOKC MAE by lead day 1 to 9, tmin
KORD 1.79+1.79 · n=2 2.01+2.01 · n=1 KORD MAE by lead day 1 to 9, tmin
KPHL 1.71+0.37 · n=2 1.83+1.83 · n=1 KPHL MAE by lead day 1 to 9, tmin
KPHX 2.25-2.25 · n=2 1.48-1.48 · n=1 KPHX MAE by lead day 1 to 9, tmin
KSAN 1.39-1.11 · n=2 3.14-3.14 · n=1 KSAN MAE by lead day 1 to 9, tmin
KSAT 0.94-0.53 · n=2 2.72-2.72 · n=1 KSAT MAE by lead day 1 to 9, tmin
KSEA 2.20+2.20 · n=2 0.98+0.98 · n=1 KSEA MAE by lead day 1 to 9, tmin
KSFO 0.66+0.17 · n=2 0.55-0.55 · n=1 KSFO MAE by lead day 1 to 9, tmin
KTTN 5.53+5.53 · n=2 6.42+6.42 · 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 · PANG · GFS 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