Philadelphia Intl · ECMWF AIFS Single · lead day 4
KPHL · aifs_single · lead 4
Target day = initialization date + 4 days. This page is a permanent link: the numbers change as history accumulates, the address and the methodology version do not.
Scores use the latest model version segment, aifs-single-gpid5, starting 2026-08-01 — days before that ran a different version of the model and are excluded rather than silently pooled. Of the scored days, 1 carry a QC flag on the observation.
JSON for this page CSV of the daily errors Cite this page
Every number for this combination
All four windows × both initializations × both interpolations × both variables. Errors are computed in °C and shown in °F; CI is a 95 % moving-block bootstrap interval. MAE debiased and skill, debiased remove the constant offset of the window first, so a station that the model always reads a degree too warm is not scored as if it had no skill — compare the two skill columns to see how much of the error is a fixed offset. n QC next to n counts days whose observation carries a QC flag.
| Variable | Init | Method | Window | n | MAE °F | MAE debiased | Bias °F | RMSE °F | ±1 °F | ±2 °F | ±3 °F | Skill | Skill, debiased | Period |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| tmax | 00Z | bilinear | 30d | 26 1 QC | 2.90 [2.33, 3.59] | 1.72 | -2.72 [-3.54, -2.06] | 3.58 [2.74, 4.52] | 23% [9%, 35%] | 35% | 65% | +0.19 | +0.50 | 2026-08-05 → 2026-08-30 |
| tmax | 00Z | bilinear | 90d | 26 1 QC | 2.90 [2.39, 3.60] | 1.72 | -2.72 [-3.51, -1.96] | 3.58 [2.70, 4.52] | 23% [4%, 34%] | 35% | 65% | +0.19 | +0.50 | 2026-08-05 → 2026-08-30 |
| tmax | 00Z | bilinear | 365d | 26 1 QC | 2.90 [2.32, 3.61] | 1.72 | -2.72 [-3.54, -1.89] | 3.58 [2.66, 4.54] | 23% [0%, 36%] | 35% | 65% | +0.19 | +0.50 | 2026-08-05 → 2026-08-30 |
| tmax | 00Z | bilinear | all | 26 1 QC | 2.90 [2.38, 3.63] | 1.72 | -2.72 [-3.60, -1.94] | 3.58 [2.68, 4.54] | 23% [0%, 36%] | 35% | 65% | +0.19 | +0.50 | 2026-08-05 → 2026-08-30 |
| tmax | 00Z | nearest | 30d | 26 1 QC | 2.49 [2.00, 3.16] | 1.74 | -2.10 [-2.83, -1.47] | 3.13 [2.34, 4.00] | 23% [10%, 35%] | 42% | 73% | +0.30 | +0.50 | 2026-08-05 → 2026-08-30 |
| tmax | 00Z | nearest | 90d | 26 1 QC | 2.49 [2.01, 3.16] | 1.74 | -2.10 [-2.85, -1.38] | 3.13 [2.29, 3.95] | 23% [6%, 33%] | 42% | 73% | +0.30 | +0.50 | 2026-08-05 → 2026-08-30 |
| tmax | 00Z | nearest | 365d | 26 1 QC | 2.49 [1.95, 3.16] | 1.74 | -2.10 [-2.85, -1.29] | 3.13 [2.27, 4.03] | 23% [6%, 36%] | 42% | 73% | +0.30 | +0.50 | 2026-08-05 → 2026-08-30 |
| tmax | 00Z | nearest | all | 26 1 QC | 2.49 [1.97, 3.19] | 1.74 | -2.10 [-2.89, -1.35] | 3.13 [2.27, 4.02] | 23% [0%, 36%] | 42% | 73% | +0.30 | +0.50 | 2026-08-05 → 2026-08-30 |
| tmax | 12Z | bilinear | 30d | 26 1 QC | 2.47 [2.01, 2.96] | 1.53 | -2.24 [-2.79, -1.73] | 2.98 [2.40, 3.54] | 27% [15%, 37%] | 38% | 65% | +0.31 | +0.56 | 2026-08-05 → 2026-08-30 |
| tmax | 12Z | bilinear | 90d | 26 1 QC | 2.47 [1.91, 2.99] | 1.53 | -2.24 [-2.77, -1.75] | 2.98 [2.32, 3.54] | 27% [14%, 38%] | 38% | 65% | +0.31 | +0.56 | 2026-08-05 → 2026-08-30 |
| tmax | 12Z | bilinear | 365d | 26 1 QC | 2.47 [1.88, 3.01] | 1.53 | -2.24 [-2.84, -1.68] | 2.98 [2.28, 3.58] | 27% [14%, 40%] | 38% | 65% | +0.31 | +0.56 | 2026-08-05 → 2026-08-30 |
| tmax | 12Z | bilinear | all | 26 1 QC | 2.47 [1.88, 3.02] | 1.53 | -2.24 [-2.85, -1.69] | 2.98 [2.28, 3.62] | 27% [12%, 39%] | 38% | 65% | +0.31 | +0.56 | 2026-08-05 → 2026-08-30 |
| tmax | 12Z | nearest | 30d | 26 1 QC | 2.12 [1.69, 2.54] | 1.57 | -1.60 [-2.10, -1.10] | 2.54 [2.01, 3.02] | 23% [10%, 36%] | 46% | 81% | +0.41 | +0.55 | 2026-08-05 → 2026-08-30 |
| tmax | 12Z | nearest | 90d | 26 1 QC | 2.12 [1.60, 2.55] | 1.57 | -1.60 [-2.10, -1.10] | 2.54 [1.91, 3.03] | 23% [9%, 38%] | 46% | 81% | +0.41 | +0.55 | 2026-08-05 → 2026-08-30 |
| tmax | 12Z | nearest | 365d | 26 1 QC | 2.12 [1.58, 2.59] | 1.57 | -1.60 [-2.19, -1.05] | 2.54 [1.87, 3.08] | 23% [9%, 39%] | 46% | 81% | +0.41 | +0.55 | 2026-08-05 → 2026-08-30 |
| tmax | 12Z | nearest | all | 26 1 QC | 2.12 [1.56, 2.59] | 1.57 | -1.60 [-2.14, -1.07] | 2.54 [1.88, 3.07] | 23% [7%, 38%] | 46% | 81% | +0.41 | +0.55 | 2026-08-05 → 2026-08-30 |
| tmin | 00Z | bilinear | 30d | 26 1 QC | 2.70 [1.74, 3.58] | 2.70 | +0.05 [-0.87, 1.00] | 3.22 [2.22, 3.95] | 23% [4%, 44%] | 38% | 58% | +0.05 | +0.07 | 2026-08-05 → 2026-08-30 |
| tmin | 00Z | bilinear | 90d | 26 1 QC | 2.70 [1.64, 3.68] | 2.70 | +0.05 [-1.09, 1.22] | 3.22 [2.07, 4.04] | 23% [0%, 44%] | 38% | 58% | +0.05 | +0.07 | 2026-08-05 → 2026-08-30 |
| tmin | 00Z | bilinear | 365d | 26 1 QC | 2.70 [1.58, 3.76] | 2.70 | +0.05 [-1.02, 1.31] | 3.22 [2.07, 4.10] | 23% [0%, 44%] | 38% | 58% | +0.05 | +0.07 | 2026-08-05 → 2026-08-30 |
| tmin | 00Z | bilinear | all | 26 1 QC | 2.70 [1.60, 3.70] | 2.70 | +0.05 [-1.13, 1.23] | 3.22 [2.03, 4.07] | 23% [0%, 44%] | 38% | 58% | +0.05 | +0.07 | 2026-08-05 → 2026-08-30 |
| tmin | 00Z | nearest | 30d | 26 1 QC | 2.64 [1.74, 3.52] | 2.69 | +0.59 [-0.29, 1.55] | 3.24 [2.19, 4.05] | 23% [7%, 44%] | 50% | 62% | +0.07 | +0.08 | 2026-08-05 → 2026-08-30 |
| tmin | 00Z | nearest | 90d | 26 1 QC | 2.64 [1.57, 3.60] | 2.69 | +0.59 [-0.49, 1.73] | 3.24 [2.01, 4.12] | 23% [5%, 47%] | 50% | 62% | +0.07 | +0.08 | 2026-08-05 → 2026-08-30 |
| tmin | 00Z | nearest | 365d | 26 1 QC | 2.64 [1.59, 3.68] | 2.69 | +0.59 [-0.42, 1.81] | 3.24 [1.99, 4.21] | 23% [0%, 44%] | 50% | 62% | +0.07 | +0.08 | 2026-08-05 → 2026-08-30 |
| tmin | 00Z | nearest | all | 26 1 QC | 2.64 [1.56, 3.67] | 2.69 | +0.59 [-0.51, 1.71] | 3.24 [1.93, 4.12] | 23% [0%, 49%] | 50% | 62% | +0.07 | +0.08 | 2026-08-05 → 2026-08-30 |
| tmin | 12Z | bilinear | 30d | 26 1 QC | 2.39 [1.68, 3.20] | 2.39 | -0.14 [-0.88, 0.63] | 2.85 [2.01, 3.59] | 27% [13%, 41%] | 42% | 65% | +0.16 | +0.18 | 2026-08-05 → 2026-08-30 |
| tmin | 12Z | bilinear | 90d | 26 1 QC | 2.39 [1.66, 3.30] | 2.39 | -0.14 [-0.99, 0.75] | 2.85 [1.98, 3.66] | 27% [13%, 43%] | 42% | 65% | +0.16 | +0.18 | 2026-08-05 → 2026-08-30 |
| tmin | 12Z | bilinear | 365d | 26 1 QC | 2.39 [1.64, 3.44] | 2.39 | -0.14 [-0.98, 0.84] | 2.85 [1.98, 3.79] | 27% [10%, 43%] | 42% | 65% | +0.16 | +0.18 | 2026-08-05 → 2026-08-30 |
| tmin | 12Z | bilinear | all | 26 1 QC | 2.39 [1.66, 3.34] | 2.39 | -0.14 [-1.08, 0.77] | 2.85 [1.98, 3.69] | 27% [11%, 42%] | 42% | 65% | +0.16 | +0.18 | 2026-08-05 → 2026-08-30 |
| tmin | 12Z | nearest | 30d | 26 1 QC | 2.37 [1.71, 3.16] | 2.37 | +0.37 [-0.34, 1.12] | 2.83 [1.98, 3.64] | 23% [9%, 36%] | 50% | 65% | +0.17 | +0.19 | 2026-08-05 → 2026-08-30 |
| tmin | 12Z | nearest | 90d | 26 1 QC | 2.37 [1.72, 3.24] | 2.37 | +0.37 [-0.45, 1.24] | 2.83 [1.96, 3.69] | 23% [9%, 37%] | 50% | 65% | +0.17 | +0.19 | 2026-08-05 → 2026-08-30 |
| tmin | 12Z | nearest | 365d | 26 1 QC | 2.37 [1.72, 3.40] | 2.37 | +0.37 [-0.41, 1.36] | 2.83 [1.97, 3.82] | 23% [6%, 38%] | 50% | 65% | +0.17 | +0.19 | 2026-08-05 → 2026-08-30 |
| tmin | 12Z | nearest | all | 26 1 QC | 2.37 [1.74, 3.26] | 2.37 | +0.37 [-0.48, 1.26] | 2.83 [1.99, 3.68] | 23% [0%, 37%] | 50% | 65% | +0.17 | +0.19 | 2026-08-05 → 2026-08-30 |
+ 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 error, last 90 days
The same series as a table (26 days, newest first) · download CSV
| Climatological day | Error °F |
|---|---|
| 2026-08-30 | -2.92 |
| 2026-08-29 | +1.95 |
| 2026-08-28 | -2.75 |
| 2026-08-27 | -2.84 |
| 2026-08-26 | -3.10 |
| 2026-08-25 | -0.83 |
| 2026-08-24 | -4.78 |
| 2026-08-23 | -1.78 |
| 2026-08-22 | -0.70 |
| 2026-08-21 | -5.16 |
| 2026-08-20 | -0.45 |
| 2026-08-19 | -4.09 |
| 2026-08-18 | -3.05 |
| 2026-08-17 | +0.05 |
| 2026-08-16 | -2.57 |
| 2026-08-15 | -9.01 |
| 2026-08-14 | -5.97 |
| 2026-08-13 | -2.40 |
| 2026-08-12 | -6.59 |
| 2026-08-11 | -0.20 |
| 2026-08-10 | +0.31 |
| 2026-08-09 | -1.58 |
| 2026-08-08 | -2.06 |
| 2026-08-07 | -4.58 |
| 2026-08-06 | -2.74 |
| 2026-08-05 | -2.88 |
Error distribution
Bin counts as a table
| From °F | To °F | Days |
|---|---|---|
| -10.00 | -9.00 | 1 |
| -9.00 | -8.00 | 0 |
| -8.00 | -7.00 | 0 |
| -7.00 | -6.00 | 1 |
| -6.00 | -5.00 | 2 |
| -5.00 | -4.00 | 3 |
| -4.00 | -3.00 | 2 |
| -3.00 | -2.00 | 8 |
| -2.00 | -1.00 | 2 |
| -1.00 | +0.00 | 4 |
| +0.00 | +1.00 | 2 |
| +1.00 | +2.00 | 1 |
| +2.00 | +3.00 | 0 |
| +3.00 | +4.00 | 0 |
| +4.00 | +5.00 | 0 |
| +5.00 | +6.00 | 0 |
| +6.00 | +7.00 | 0 |
| +7.00 | +8.00 | 0 |
| +8.00 | +9.00 | 0 |
| +9.00 | +10.00 | 0 |
Month by month
00Z bilinear daily maximum, newest first.
| Month | n | MAE °F | Bias °F |
|---|---|---|---|
| 2026-08 | 26 | 2.90 | -2.72 |
Availability
| Model | Scored period | Days | Coverage |
|---|---|---|---|
| ECMWF AIFS Single | 2026-08-05 → 2026-08-30 | 26 | |
| ECMWF AIFS Single | 2026-08-05 → 2026-08-30 | 26 | |
| ECMWF AIFS Single | 2026-08-05 → 2026-08-30 | 26 | |
| ECMWF AIFS Single | 2026-08-05 → 2026-08-30 | 26 |
Compared with other models
Paired bootstrap on the days both models cover (90d, 00Z, bilinear, daily maximum). Negative means ECMWF AIFS Single has the lower MAE. "Distinguishable" means the 95 % interval excludes zero.
| Other model | Common days | MAE difference °F | Distinguishable |
|---|---|---|---|
| NCEP GFS | 26 | -0.75 [-1.77, 0.82] | no |
| GraphCast (IFS init) | 25 | -1.60 [-2.06, -0.97] | yes |
| ECMWF IFS HRES | 20 | -0.73 [-1.43, 1.09] | no |
| Persistence (baseline) | 26 | -0.68 [-1.76, 0.51] | no |
Cite this page
ShortCastCheck, KPHL aifs_single lead 4, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KPHL/model/aifs_single/lead/4/
LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KPHL (Philadelphia Intl), model aifs_single, lead day 4. Methodology version 0.2, schema version 0.1, data through 2026-08-30. Accessed 2026-08-31. https://castcheck.zifanzhang.com/station/KPHL/model/aifs_single/lead/4/
Accessed2026-08-31 (data through 2026-08-30; page built 2026-08-31T03:52:06+00:00)