Philadelphia Intl · ECMWF AIFS Single · lead day 1
KPHL · aifs_single · lead 1
Target day = initialization date + 1 day. 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 | 29 1 QC | 2.41 [1.81, 3.36] | 1.46 | -2.28 [-3.33, -1.53] | 2.91 [2.25, 3.81] | 21% [7%, 33%] | 41% | 62% | +0.25 | +0.55 | 2026-08-02 → 2026-08-30 |
| tmax | 00Z | bilinear | 90d | 29 1 QC | 2.41 [1.80, 3.46] | 1.46 | -2.28 [-3.41, -1.49] | 2.91 [2.25, 3.95] | 21% [6%, 33%] | 41% | 62% | +0.25 | +0.55 | 2026-08-02 → 2026-08-30 |
| tmax | 00Z | bilinear | 365d | 29 1 QC | 2.41 [1.82, 3.46] | 1.46 | -2.28 [-3.42, -1.51] | 2.91 [2.25, 3.93] | 21% [6%, 33%] | 41% | 62% | +0.25 | +0.55 | 2026-08-02 → 2026-08-30 |
| tmax | 00Z | bilinear | all | 29 1 QC | 2.41 [1.82, 3.69] | 1.46 | -2.28 [-3.69, -1.46] | 2.91 [2.23, 4.09] | 21% [4%, 33%] | 41% | 62% | +0.25 | +0.55 | 2026-08-02 → 2026-08-30 |
| tmax | 00Z | nearest | 30d | 29 1 QC | 2.05 [1.53, 2.84] | 1.51 | -1.60 [-2.68, -0.76] | 2.46 [1.82, 3.27] | 24% [14%, 34%] | 59% | 76% | +0.36 | +0.53 | 2026-08-02 → 2026-08-30 |
| tmax | 00Z | nearest | 90d | 29 1 QC | 2.05 [1.55, 3.03] | 1.51 | -1.60 [-2.77, -0.71] | 2.46 [1.83, 3.44] | 24% [11%, 33%] | 59% | 76% | +0.36 | +0.53 | 2026-08-02 → 2026-08-30 |
| tmax | 00Z | nearest | 365d | 29 1 QC | 2.05 [1.52, 2.99] | 1.51 | -1.60 [-2.79, -0.71] | 2.46 [1.82, 3.42] | 24% [11%, 36%] | 59% | 76% | +0.36 | +0.53 | 2026-08-02 → 2026-08-30 |
| tmax | 00Z | nearest | all | 29 1 QC | 2.05 [1.52, 3.15] | 1.51 | -1.60 [-3.04, -0.67] | 2.46 [1.80, 3.53] | 24% [9%, 36%] | 59% | 76% | +0.36 | +0.53 | 2026-08-02 → 2026-08-30 |
| tmax | 12Z | bilinear | 30d | 29 1 QC | 2.19 [1.61, 3.00] | 1.28 | -2.09 [-2.96, -1.35] | 2.62 [1.95, 3.36] | 21% [10%, 33%] | 52% | 72% | +0.32 | +0.60 | 2026-08-02 → 2026-08-30 |
| tmax | 12Z | bilinear | 90d | 29 1 QC | 2.19 [1.59, 3.08] | 1.28 | -2.09 [-3.08, -1.33] | 2.62 [1.92, 3.48] | 21% [8%, 33%] | 52% | 72% | +0.32 | +0.60 | 2026-08-02 → 2026-08-30 |
| tmax | 12Z | bilinear | 365d | 29 1 QC | 2.19 [1.57, 3.07] | 1.28 | -2.09 [-3.07, -1.33] | 2.62 [1.93, 3.44] | 21% [7%, 33%] | 52% | 72% | +0.32 | +0.60 | 2026-08-02 → 2026-08-30 |
| tmax | 12Z | bilinear | all | 29 1 QC | 2.19 [1.55, 3.31] | 1.28 | -2.09 [-3.31, -1.26] | 2.62 [1.91, 3.67] | 21% [6%, 33%] | 52% | 72% | +0.32 | +0.60 | 2026-08-02 → 2026-08-30 |
| tmax | 12Z | nearest | 30d | 29 1 QC | 1.80 [1.31, 2.47] | 1.37 | -1.40 [-2.34, -0.55] | 2.20 [1.57, 2.84] | 34% [15%, 50%] | 66% | 79% | +0.44 | +0.57 | 2026-08-02 → 2026-08-30 |
| tmax | 12Z | nearest | 90d | 29 1 QC | 1.80 [1.32, 2.65] | 1.37 | -1.40 [-2.52, -0.51] | 2.20 [1.58, 2.97] | 34% [13%, 50%] | 66% | 79% | +0.44 | +0.57 | 2026-08-02 → 2026-08-30 |
| tmax | 12Z | nearest | 365d | 29 1 QC | 1.80 [1.29, 2.58] | 1.37 | -1.40 [-2.48, -0.49] | 2.20 [1.57, 2.95] | 34% [12%, 50%] | 66% | 79% | +0.44 | +0.57 | 2026-08-02 → 2026-08-30 |
| tmax | 12Z | nearest | all | 29 1 QC | 1.80 [1.28, 2.70] | 1.37 | -1.40 [-2.68, -0.42] | 2.20 [1.56, 3.12] | 34% [10%, 50%] | 66% | 79% | +0.44 | +0.57 | 2026-08-02 → 2026-08-30 |
| tmin | 00Z | bilinear | 30d | 29 1 QC | 1.60 [1.11, 2.13] | 1.60 | +0.01 [-0.44, 0.51] | 1.99 [1.46, 2.43] | 38% [21%, 55%] | 59% | 79% | +0.42 | +0.42 | 2026-08-02 → 2026-08-30 |
| tmin | 00Z | bilinear | 90d | 29 1 QC | 1.60 [1.01, 2.13] | 1.60 | +0.01 [-0.48, 0.52] | 1.99 [1.33, 2.42] | 38% [20%, 57%] | 59% | 79% | +0.42 | +0.42 | 2026-08-02 → 2026-08-30 |
| tmin | 00Z | bilinear | 365d | 29 1 QC | 1.60 [0.99, 2.17] | 1.60 | +0.01 [-0.51, 0.57] | 1.99 [1.23, 2.46] | 38% [19%, 57%] | 59% | 79% | +0.42 | +0.42 | 2026-08-02 → 2026-08-30 |
| tmin | 00Z | bilinear | all | 29 1 QC | 1.60 [1.02, 2.14] | 1.60 | +0.01 [-0.47, 0.48] | 1.99 [1.32, 2.44] | 38% [21%, 57%] | 59% | 79% | +0.42 | +0.42 | 2026-08-02 → 2026-08-30 |
| tmin | 00Z | nearest | 30d | 29 1 QC | 1.65 [1.12, 2.23] | 1.61 | +0.58 [0.18, 1.06] | 2.06 [1.48, 2.59] | 38% [20%, 59%] | 62% | 86% | +0.40 | +0.42 | 2026-08-02 → 2026-08-30 |
| tmin | 00Z | nearest | 90d | 29 1 QC | 1.65 [1.02, 2.24] | 1.61 | +0.58 [0.16, 1.05] | 2.06 [1.33, 2.58] | 38% [23%, 61%] | 62% | 86% | +0.40 | +0.42 | 2026-08-02 → 2026-08-30 |
| tmin | 00Z | nearest | 365d | 29 1 QC | 1.65 [1.00, 2.27] | 1.61 | +0.58 [0.13, 1.11] | 2.06 [1.24, 2.61] | 38% [21%, 64%] | 62% | 86% | +0.40 | +0.42 | 2026-08-02 → 2026-08-30 |
| tmin | 00Z | nearest | all | 29 1 QC | 1.65 [1.02, 2.21] | 1.61 | +0.58 [0.13, 1.03] | 2.06 [1.29, 2.57] | 38% [22%, 62%] | 62% | 86% | +0.40 | +0.42 | 2026-08-02 → 2026-08-30 |
| tmin | 12Z | bilinear | 30d | 29 1 QC | 1.48 [1.17, 1.85] | 1.50 | +0.21 [-0.27, 0.74] | 1.85 [1.51, 2.16] | 41% [23%, 59%] | 66% | 83% | +0.46 | +0.46 | 2026-08-02 → 2026-08-30 |
| tmin | 12Z | bilinear | 90d | 29 1 QC | 1.48 [1.17, 1.84] | 1.50 | +0.21 [-0.36, 0.79] | 1.85 [1.46, 2.14] | 41% [22%, 60%] | 66% | 83% | +0.46 | +0.46 | 2026-08-02 → 2026-08-30 |
| tmin | 12Z | bilinear | 365d | 29 1 QC | 1.48 [1.13, 1.86] | 1.50 | +0.21 [-0.41, 0.81] | 1.85 [1.42, 2.19] | 41% [21%, 62%] | 66% | 83% | +0.46 | +0.46 | 2026-08-02 → 2026-08-30 |
| tmin | 12Z | bilinear | all | 29 1 QC | 1.48 [1.15, 1.87] | 1.50 | +0.21 [-0.34, 0.71] | 1.85 [1.44, 2.19] | 41% [20%, 61%] | 66% | 83% | +0.46 | +0.46 | 2026-08-02 → 2026-08-30 |
| tmin | 12Z | nearest | 30d | 29 1 QC | 1.53 [1.20, 1.89] | 1.50 | +0.76 [0.32, 1.30] | 1.98 [1.55, 2.38] | 48% [37%, 60%] | 69% | 83% | +0.45 | +0.46 | 2026-08-02 → 2026-08-30 |
| tmin | 12Z | nearest | 90d | 29 1 QC | 1.53 [1.13, 1.87] | 1.50 | +0.76 [0.21, 1.32] | 1.98 [1.44, 2.38] | 48% [35%, 62%] | 69% | 83% | +0.45 | +0.46 | 2026-08-02 → 2026-08-30 |
| tmin | 12Z | nearest | 365d | 29 1 QC | 1.53 [1.08, 1.92] | 1.50 | +0.76 [0.20, 1.34] | 1.98 [1.40, 2.44] | 48% [36%, 62%] | 69% | 83% | +0.45 | +0.46 | 2026-08-02 → 2026-08-30 |
| tmin | 12Z | nearest | all | 29 1 QC | 1.53 [1.12, 1.91] | 1.50 | +0.76 [0.23, 1.24] | 1.98 [1.43, 2.39] | 48% [35%, 62%] | 69% | 83% | +0.45 | +0.46 | 2026-08-02 → 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 (29 days, newest first) · download CSV
| Climatological day | Error °F |
|---|---|
| 2026-08-30 | -4.25 |
| 2026-08-29 | -1.62 |
| 2026-08-28 | -3.05 |
| 2026-08-27 | -2.29 |
| 2026-08-26 | -2.04 |
| 2026-08-25 | -0.50 |
| 2026-08-24 | -1.94 |
| 2026-08-23 | -2.03 |
| 2026-08-22 | -1.44 |
| 2026-08-21 | -4.19 |
| 2026-08-20 | -3.78 |
| 2026-08-19 | -3.38 |
| 2026-08-18 | -0.02 |
| 2026-08-17 | -1.59 |
| 2026-08-16 | -0.12 |
| 2026-08-15 | -3.32 |
| 2026-08-14 | -2.16 |
| 2026-08-13 | -1.37 |
| 2026-08-12 | -4.24 |
| 2026-08-11 | +1.04 |
| 2026-08-10 | +0.85 |
| 2026-08-09 | -0.09 |
| 2026-08-08 | -0.02 |
| 2026-08-07 | -3.31 |
| 2026-08-06 | -2.37 |
| 2026-08-05 | -2.96 |
| 2026-08-04 | -4.92 |
| 2026-08-03 | -6.51 |
| 2026-08-02 | -4.53 |
Error distribution
Bin counts as a table
| From °F | To °F | Days |
|---|---|---|
| -10.00 | -9.00 | 0 |
| -9.00 | -8.00 | 0 |
| -8.00 | -7.00 | 0 |
| -7.00 | -6.00 | 1 |
| -6.00 | -5.00 | 0 |
| -5.00 | -4.00 | 5 |
| -4.00 | -3.00 | 5 |
| -3.00 | -2.00 | 6 |
| -2.00 | -1.00 | 5 |
| -1.00 | +0.00 | 5 |
| +0.00 | +1.00 | 1 |
| +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 | 29 | 2.41 | -2.28 |
Availability
| Model | Scored period | Days | Coverage |
|---|---|---|---|
| ECMWF AIFS Single | 2026-08-02 → 2026-08-30 | 29 | |
| ECMWF AIFS Single | 2026-08-02 → 2026-08-30 | 29 | |
| ECMWF AIFS Single | 2026-08-02 → 2026-08-30 | 29 | |
| ECMWF AIFS Single | 2026-08-02 → 2026-08-30 | 29 |
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 |
|---|---|---|---|
| Aurora (GFS init) | 1 | -2.26 [-2.26, -2.26] | yes |
| Aurora (IFS init) | 2 | -1.25 [-1.92, -0.59] | yes |
| FourCastNet v2 (GFS init) | 1 | -0.47 [-0.47, -0.47] | yes |
| FourCastNet v2 (IFS init) | 2 | +0.23 [-1.00, 1.45] | no |
| NCEP GFS | 29 | -0.47 [-1.44, 0.79] | no |
| GraphCast (GFS init) | 1 | -2.10 [-2.10, -2.10] | yes |
| GraphCast (IFS init) | 27 | -2.76 [-3.15, -2.42] | yes |
| ECMWF IFS HRES | 23 | -2.01 [-2.90, -0.66] | yes |
| Pangu-Weather (GFS init) | 1 | +1.72 [1.72, 1.72] | yes |
| Pangu-Weather (IFS init) | 2 | +1.27 [0.94, 1.61] | yes |
| Persistence (baseline) | 29 | -0.80 [-1.71, 0.57] | no |
Cite this page
ShortCastCheck, KPHL aifs_single lead 1, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KPHL/model/aifs_single/lead/1/
LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KPHL (Philadelphia Intl), model aifs_single, lead day 1. 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/1/
Accessed2026-08-31 (data through 2026-08-30; page built 2026-08-31T03:52:06+00:00)