KLAX — Los Angeles Intl
33.9381, -118.3889 · 38 m· standard offset UTC-8 h · truth product CLILAX
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 | 1.48+0.73 · n=30 | 1.57+1.02 · n=29 | 1.72+1.18 · n=28 | 1.70+1.26 · n=27 | 1.62+0.98 · n=26 | 2.05+0.55 · n=25 | 2.15+0.13 · n=24 | 2.02+0.02 · n=23 | 1.87-0.57 · n=22 | — | |
| Aurora (GFS init)aurora_gfs | 5.90-5.90 · n=2 | 5.95-5.95 · n=1 | — | — | — | — | — | — | — | — | |
| Aurora (IFS init)aurora_ifs | 4.63-4.63 · n=3 | 5.90-5.90 · n=2 | 6.29-6.29 · n=1 | — | — | — | — | — | — | — | |
| FourCastNet v2 (GFS init)fourcastnet_gfs | 3.32-3.32 · n=2 | 2.75-2.75 · n=1 | — | — | — | — | — | — | — | — | |
| FourCastNet v2 (IFS init)fourcastnet_ifs | 2.73-2.73 · n=3 | 3.08-3.08 · n=2 | 3.13-3.13 · n=1 | — | — | — | — | — | — | — | |
| NCEP GFSgfs | 2.09-0.81 · n=30 | 2.06-0.58 · n=29 | 2.25-0.52 · n=28 | 2.11-0.43 · n=27 | 2.18-0.18 · n=26 | 1.56-0.54 · n=25 | 1.86-0.81 · n=24 | 1.98-1.17 · n=23 | 2.99-1.16 · n=22 | — | |
| GraphCast (GFS init)graphcast_gfs | 5.57-5.57 · n=2 | 5.25-5.25 · n=1 | — | — | — | — | — | — | — | — | |
| GraphCast (IFS init)graphcast_ifs | 3.21-3.21 · n=34 | 3.39-3.39 · n=33 | 3.48-3.48 · n=32 | 3.42-3.37 · n=31 | 3.56-3.53 · n=31 | 3.69-3.57 · n=31 | 3.86-3.64 · n=30 | 4.11-3.93 · n=29 | 4.78-4.76 · n=28 | — | |
| ECMWF IFS HRESifs_hres | 2.35-2.26 · n=25 | 2.44-2.20 · n=22 | 2.32-2.12 · n=23 | 2.21-1.80 · n=22 | 1.97-1.31 · n=20 | 2.43-1.48 · n=18 | 2.43-1.80 · n=19 | 3.06-1.72 · n=18 | 3.34-2.55 · n=17 | — | |
| Pangu-Weather (GFS init)pangu_gfs | 2.47-2.47 · n=2 | 2.39-2.39 · n=1 | — | — | — | — | — | — | — | — | |
| Pangu-Weather (IFS init)pangu_ifs | 2.13-1.73 · n=3 | 3.27-3.27 · n=2 | 4.04-4.04 · n=1 | — | — | — | — | — | — | — | |
| Persistence (baseline)persistence | — | 2.91+0.00 · n=365 | 4.21-0.01 · n=365 | 4.70-0.01 · n=365 | 4.94-0.04 · n=365 | 5.04-0.07 · n=365 | 5.21-0.09 · n=365 | 5.35-0.11 · n=365 | 5.51-0.10 · n=365 | 5.56-0.09 · n=365 |
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
| Model | d0 | d1 | d2 | d3 | d4 | d5 | d6 | d7 | d8 | d9 | lead 1–9 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| ECMWF AIFS Singleaifs_single | 0.50-0.01 · n=30 | 0.60-0.01 · n=29 | 0.62+0.01 · n=28 | 0.68+0.07 · n=27 | 0.65+0.08 · n=26 | 0.58+0.04 · n=25 | 0.79-0.01 · n=24 | 0.93-0.18 · n=23 | 1.19-0.35 · n=22 | — | |
| Aurora (GFS init)aurora_gfs | 1.90-1.90 · n=2 | 2.74-2.74 · n=1 | — | — | — | — | — | — | — | — | |
| Aurora (IFS init)aurora_ifs | 0.95-0.95 · n=3 | 1.49-1.49 · n=2 | 2.78-2.78 · n=1 | — | — | — | — | — | — | — | |
| FourCastNet v2 (GFS init)fourcastnet_gfs | 2.12+2.12 · n=2 | 1.88+1.88 · n=1 | — | — | — | — | — | — | — | — | |
| FourCastNet v2 (IFS init)fourcastnet_ifs | 2.26+2.26 · n=3 | 2.05+2.05 · n=2 | 1.38+1.38 · n=1 | — | — | — | — | — | — | — | |
| NCEP GFSgfs | 2.94+2.84 · n=30 | 3.48+3.34 · n=29 | 3.67+3.58 · n=28 | 3.82+3.71 · n=27 | 3.61+3.54 · n=26 | 3.57+3.57 · n=25 | 3.42+3.42 · n=24 | 3.42+3.18 · n=23 | 3.32+2.87 · n=22 | — | |
| GraphCast (GFS init)graphcast_gfs | 1.21-1.21 · n=2 | 2.09-2.09 · n=1 | — | — | — | — | — | — | — | — | |
| GraphCast (IFS init)graphcast_ifs | 0.90+0.16 · n=34 | 1.16-0.15 · n=33 | 1.27-0.32 · n=32 | 1.42-0.04 · n=31 | 1.54+0.20 · n=31 | 1.95+0.60 · n=31 | 2.42+1.10 · n=30 | 3.13+1.56 · n=29 | 3.60+1.61 · n=28 | — | |
| ECMWF IFS HRESifs_hres | 0.64+0.45 · n=25 | 0.85+0.58 · n=22 | 0.97+0.52 · n=23 | 1.07+0.72 · n=22 | 1.36+1.26 · n=20 | 1.52+1.38 · n=18 | 1.49+1.34 · n=19 | 1.73+1.10 · n=18 | 2.18+0.63 · n=17 | — | |
| Pangu-Weather (GFS init)pangu_gfs | 1.25+0.02 · n=2 | 2.07-2.07 · n=1 | — | — | — | — | — | — | — | — | |
| Pangu-Weather (IFS init)pangu_ifs | 1.22+0.64 · n=3 | 1.34-1.34 · n=2 | 3.15-3.15 · n=1 | — | — | — | — | — | — | — | |
| Persistence (baseline)persistence | — | 1.86-0.01 · n=365 | 2.49-0.02 · n=365 | 2.64-0.04 · n=365 | 2.72-0.06 · n=365 | 2.77-0.08 · n=365 | 2.95-0.09 · n=365 | 3.09-0.09 · n=365 | 3.15-0.09 · n=365 | 3.12-0.09 · n=365 |
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, 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