KPHL — Philadelphia Intl
39.8733, -75.2268 · 2 m· standard offset UTC-5 h · truth product CLIPHL
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
| Model | d0 | d1 | d2 | d3 | d4 | d5 | d6 | d7 | d8 | d9 | lead 1–9 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| ECMWF AIFS Singleaifs_single | — | 2.19-2.09 · n=29 | 2.76-2.58 · n=28 | 2.67-2.30 · n=27 | 2.47-2.24 · n=26 | 2.83-2.72 · n=24 | 3.42-2.63 · n=24 | 2.97-2.61 · n=23 | 4.19-3.79 · n=22 | 4.94-4.35 · n=21 | |
| Aurora (GFS init)aurora_gfs | — | 5.33-5.33 · n=2 | 7.15-7.15 · n=1 | — | — | — | — | — | — | — | |
| Aurora (IFS init)aurora_ifs | — | 5.17-5.17 · n=2 | 5.26-5.26 · n=1 | — | — | — | — | — | — | — | |
| FourCastNet v2 (GFS init)fourcastnet_gfs | — | 2.31-2.31 · n=2 | 5.03-5.03 · n=1 | — | — | — | — | — | — | — | |
| FourCastNet v2 (IFS init)fourcastnet_ifs | — | 3.09-3.09 · n=2 | 4.05-4.05 · n=1 | — | — | — | — | — | — | — | |
| NCEP GFSgfs | — | 2.60-1.73 · n=29 | 2.85-2.58 · n=28 | 3.02-1.69 · n=27 | 3.53-2.68 · n=26 | 3.16-1.49 · n=25 | 4.47-2.51 · n=24 | 4.69-1.56 · n=23 | 4.64-1.07 · n=22 | 5.98-1.50 · n=21 | |
| GraphCast (GFS init)graphcast_gfs | — | 4.53-4.53 · n=2 | 6.53-6.53 · n=1 | — | — | — | — | — | — | — | |
| GraphCast (IFS init)graphcast_ifs | — | 4.92-4.92 · n=27 | 4.93-4.93 · n=26 | 4.95-4.95 · n=25 | 4.34-4.25 · n=25 | 4.82-4.75 · n=25 | 4.57-4.44 · n=24 | 4.46-4.23 · n=23 | 5.75-5.20 · n=22 | 6.45-5.37 · n=21 | |
| ECMWF IFS HRESifs_hres | — | 3.66-3.54 · n=24 | 4.12-3.78 · n=22 | 4.04-3.42 · n=22 | 3.32-2.86 · n=21 | 3.83-2.76 · n=20 | 3.60-2.21 · n=19 | 4.53-3.81 · n=17 | 4.36-3.33 · n=17 | 6.44-4.35 · n=15 | |
| Pangu-Weather (GFS init)pangu_gfs | — | 1.13-1.13 · n=2 | 3.43-3.43 · n=1 | — | — | — | — | — | — | — | |
| Pangu-Weather (IFS init)pangu_ifs | — | 1.58-1.58 · n=2 | 2.88-2.88 · n=1 | — | — | — | — | — | — | — | |
| Persistence (baseline)persistence | — | 4.01-0.08 · n=90 | 5.10-0.12 · n=90 | 5.92-0.30 · n=90 | 6.02-0.33 · n=90 | 6.69-0.40 · n=90 | 6.44-0.38 · n=90 | 6.26-0.39 · n=90 | 6.76-0.49 · n=90 | 7.12-0.68 · n=90 |
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
| Model | d0 | d1 | d2 | d3 | d4 | d5 | d6 | d7 | d8 | d9 | lead 1–9 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| ECMWF AIFS Singleaifs_single | — | 1.48+0.21 · n=29 | 1.73+0.38 · n=28 | 2.06+0.33 · n=27 | 2.39-0.14 · n=26 | 2.67-0.21 · n=24 | 2.83-0.24 · n=24 | 2.46+0.07 · n=23 | 2.20+0.31 · n=22 | 3.20-0.20 · n=21 | |
| Aurora (GFS init)aurora_gfs | — | 0.79+0.79 · n=2 | 2.04+2.04 · n=1 | — | — | — | — | — | — | — | |
| Aurora (IFS init)aurora_ifs | — | 1.54-1.54 · n=2 | 0.56-0.56 · n=1 | — | — | — | — | — | — | — | |
| FourCastNet v2 (GFS init)fourcastnet_gfs | — | 3.64+3.64 · n=2 | 6.01+6.01 · n=1 | — | — | — | — | — | — | — | |
| FourCastNet v2 (IFS init)fourcastnet_ifs | — | 2.14+2.14 · n=2 | 4.78+4.78 · n=1 | — | — | — | — | — | — | — | |
| NCEP GFSgfs | — | 1.82+0.03 · n=29 | 2.05+0.35 · n=28 | 1.75+0.51 · n=27 | 2.48+0.20 · n=26 | 2.65-0.16 · n=25 | 3.06+0.14 · n=24 | 3.53+0.36 · n=23 | 3.93+0.16 · n=22 | 4.27+0.06 · n=21 | |
| GraphCast (GFS init)graphcast_gfs | — | 1.38+1.38 · n=2 | 3.25+3.25 · n=1 | — | — | — | — | — | — | — | |
| GraphCast (IFS init)graphcast_ifs | — | 1.89-0.86 · n=27 | 2.02-0.70 · n=26 | 2.02-0.65 · n=25 | 2.45-0.59 · n=25 | 2.59-0.54 · n=25 | 3.05-0.34 · n=24 | 2.42-0.17 · n=23 | 2.76-0.04 · n=22 | 4.07-1.43 · n=21 | |
| ECMWF IFS HRESifs_hres | — | 1.88-0.23 · n=24 | 1.98-0.02 · n=22 | 2.52-0.22 · n=22 | 3.48-0.32 · n=21 | 3.03-0.47 · n=20 | 3.26-0.38 · n=19 | 2.88+0.41 · n=17 | 2.77+1.28 · n=17 | 2.68-0.30 · n=15 | |
| Pangu-Weather (GFS init)pangu_gfs | — | 1.91+1.91 · n=2 | 2.63+2.63 · n=1 | — | — | — | — | — | — | — | |
| Pangu-Weather (IFS init)pangu_ifs | — | 1.56+0.55 · n=2 | 2.46+2.46 · n=1 | — | — | — | — | — | — | — | |
| Persistence (baseline)persistence | — | 3.22-0.09 · n=90 | 4.52-0.23 · n=90 | 4.82-0.42 · n=90 | 4.74-0.54 · n=90 | 4.81-0.59 · n=90 | 5.07-0.56 · n=90 | 5.01-0.57 · n=90 | 5.12-0.66 · n=90 | 5.60-0.84 · n=90 |
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 slices, model availability and the observed-truth table live on the canonical page: they do not depend on the window, initialization or interpolation selected here.
All scores as JSON scores_latest.csv daily_errors.csv.gz data & licences