Miami Intl · GraphCast (IFS init) · lead day 9
KMIA · graphcast_ifs · lead 9
Target day = initialization date + 9 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, GRAP_v100, starting 2026-01-01 — days before that ran a different version of the model and are excluded rather than silently pooled. Of the scored days, 3 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 | 21 2 QC | 5.01 [4.29, 5.84] | 1.84 | -5.01 [-5.84, -4.29] | 5.44 [4.48, 6.28] | 0% [0%, 0%] | 0% | 24% | -0.70 | +0.39 | 2026-08-10 → 2026-08-30 |
| tmax | 00Z | bilinear | 90d | 21 2 QC | 5.01 [4.11, 5.88] | 1.84 | -5.01 [-5.88, -4.11] | 5.44 [4.34, 6.30] | 0% [0%, 0%] | 0% | 24% | -0.70 | +0.39 | 2026-08-10 → 2026-08-30 |
| tmax | 00Z | bilinear | 365d | 27 3 QC | 5.45 [4.43, 6.72] | 2.47 | -5.12 [-5.98, -4.13] | 6.02 [4.66, 7.39] | 0% [0%, 0%] | 0% | 19% | -0.39 | +0.39 | 2026-01-10 → 2026-08-30 |
| tmax | 00Z | bilinear | all | 27 3 QC | 5.45 [4.52, 6.69] | 2.47 | -5.12 [-5.93, -4.22] | 6.02 [4.82, 7.38] | 0% [0%, 0%] | 0% | 19% | -0.39 | +0.39 | 2026-01-10 → 2026-08-30 |
| tmax | 00Z | nearest | 30d | 21 2 QC | 5.44 [4.90, 6.07] | 1.70 | -5.44 [-6.07, -4.90] | 5.79 [5.08, 6.46] | 0% [0%, 0%] | 0% | 10% | -0.84 | +0.43 | 2026-08-10 → 2026-08-30 |
| tmax | 00Z | nearest | 90d | 21 2 QC | 5.44 [4.80, 6.10] | 1.70 | -5.44 [-6.10, -4.80] | 5.79 [4.96, 6.48] | 0% [0%, 0%] | 0% | 10% | -0.84 | +0.43 | 2026-08-10 → 2026-08-30 |
| tmax | 00Z | nearest | 365d | 27 3 QC | 5.81 [5.00, 6.85] | 2.31 | -5.50 [-6.17, -4.67] | 6.30 [5.23, 7.48] | 0% [0%, 0%] | 0% | 7% | -0.48 | +0.42 | 2026-01-10 → 2026-08-30 |
| tmax | 00Z | nearest | all | 27 3 QC | 5.81 [5.04, 6.86] | 2.31 | -5.50 [-6.20, -4.68] | 6.30 [5.31, 7.49] | 0% [0%, 0%] | 0% | 7% | -0.48 | +0.42 | 2026-01-10 → 2026-08-30 |
| tmax | 12Z | bilinear | 30d | 21 2 QC | 5.06 [4.18, 5.86] | 2.43 | -5.06 [-5.86, -4.18] | 5.88 [4.63, 6.97] | 0% [0%, 0%] | 5% | 29% | -0.71 | +0.19 | 2026-08-10 → 2026-08-30 |
| tmax | 12Z | bilinear | 90d | 21 2 QC | 5.06 [4.16, 5.82] | 2.43 | -5.06 [-5.82, -4.16] | 5.88 [4.40, 6.96] | 0% [0%, 0%] | 5% | 29% | -0.71 | +0.19 | 2026-08-10 → 2026-08-30 |
| tmax | 12Z | bilinear | 365d | 26 3 QC | 5.52 [4.38, 6.94] | 2.87 | -5.52 [-6.94, -4.38] | 6.58 [4.85, 8.33] | 0% [0%, 0%] | 4% | 27% | -0.48 | +0.26 | 2026-01-10 → 2026-08-30 |
| tmax | 12Z | bilinear | all | 26 3 QC | 5.52 [4.44, 6.99] | 2.87 | -5.52 [-6.99, -4.44] | 6.58 [4.85, 8.35] | 0% [0%, 0%] | 4% | 27% | -0.48 | +0.26 | 2026-01-10 → 2026-08-30 |
| tmax | 12Z | nearest | 30d | 21 2 QC | 5.46 [4.73, 6.22] | 2.22 | -5.46 [-6.22, -4.73] | 6.13 [5.05, 7.18] | 0% [0%, 0%] | 5% | 14% | -0.85 | +0.26 | 2026-08-10 → 2026-08-30 |
| tmax | 12Z | nearest | 90d | 21 2 QC | 5.46 [4.69, 6.11] | 2.22 | -5.46 [-6.11, -4.69] | 6.13 [4.90, 7.17] | 0% [0%, 0%] | 5% | 14% | -0.85 | +0.26 | 2026-08-10 → 2026-08-30 |
| tmax | 12Z | nearest | 365d | 26 3 QC | 5.88 [4.83, 7.20] | 2.67 | -5.88 [-7.20, -4.83] | 6.79 [5.15, 8.42] | 0% [0%, 0%] | 4% | 15% | -0.58 | +0.31 | 2026-01-10 → 2026-08-30 |
| tmax | 12Z | nearest | all | 26 3 QC | 5.88 [4.88, 7.22] | 2.67 | -5.88 [-7.22, -4.88] | 6.79 [5.21, 8.47] | 0% [0%, 0%] | 4% | 15% | -0.58 | +0.31 | 2026-01-10 → 2026-08-30 |
| tmin | 00Z | bilinear | 30d | 21 2 QC | 1.50 [1.15, 2.19] | 1.50 | -0.14 [-1.22, 0.54] | 1.81 [1.40, 2.50] | 43% [20%, 57%] | 76% | 90% | +0.58 | +0.58 | 2026-08-10 → 2026-08-30 |
| tmin | 00Z | bilinear | 90d | 21 2 QC | 1.50 [1.14, 2.34] | 1.50 | -0.14 [-1.61, 0.57] | 1.81 [1.38, 2.70] | 43% [10%, 57%] | 76% | 90% | +0.58 | +0.58 | 2026-08-10 → 2026-08-30 |
| tmin | 00Z | bilinear | 365d | 27 2 QC | 3.86 [1.26, 9.69] | 4.01 | -1.66 [-5.64, 0.59] | 6.63 [1.52, 11.97] | 33% [0%, 52%] | 59% | 70% | +0.36 | +0.33 | 2026-01-10 → 2026-08-30 |
| tmin | 00Z | bilinear | all | 27 2 QC | 3.86 [1.30, 10.16] | 4.01 | -1.66 [-6.13, 0.69] | 6.63 [1.59, 12.31] | 33% [0%, 52%] | 59% | 70% | +0.36 | +0.33 | 2026-01-10 → 2026-08-30 |
| tmin | 00Z | nearest | 30d | 21 2 QC | 1.59 [1.31, 2.10] | 1.54 | +0.37 [-0.75, 1.09] | 1.88 [1.59, 2.38] | 38% [23%, 46%] | 67% | 86% | +0.56 | +0.57 | 2026-08-10 → 2026-08-30 |
| tmin | 00Z | nearest | 90d | 21 2 QC | 1.59 [1.31, 2.20] | 1.54 | +0.37 [-1.11, 1.15] | 1.88 [1.60, 2.46] | 38% [20%, 46%] | 67% | 86% | +0.56 | +0.57 | 2026-08-10 → 2026-08-30 |
| tmin | 00Z | nearest | 365d | 27 2 QC | 3.84 [1.42, 9.37] | 4.04 | -1.20 [-5.23, 1.12] | 6.43 [1.70, 11.60] | 30% [5%, 43%] | 52% | 67% | +0.36 | +0.33 | 2026-01-10 → 2026-08-30 |
| tmin | 00Z | nearest | all | 27 2 QC | 3.84 [1.43, 9.84] | 4.04 | -1.20 [-5.79, 1.16] | 6.43 [1.73, 11.89] | 30% [0%, 43%] | 52% | 67% | +0.36 | +0.33 | 2026-01-10 → 2026-08-30 |
| tmin | 12Z | bilinear | 30d | 21 2 QC | 1.65 [1.26, 2.21] | 1.63 | -0.33 [-1.43, 0.39] | 2.06 [1.53, 2.59] | 33% [17%, 46%] | 71% | 86% | +0.54 | +0.55 | 2026-08-10 → 2026-08-30 |
| tmin | 12Z | bilinear | 90d | 21 2 QC | 1.65 [1.20, 2.29] | 1.63 | -0.33 [-1.66, 0.44] | 2.06 [1.48, 2.68] | 33% [10%, 46%] | 71% | 86% | +0.54 | +0.55 | 2026-08-10 → 2026-08-30 |
| tmin | 12Z | bilinear | 365d | 26 2 QC | 3.05 [1.41, 6.78] | 3.04 | -1.99 [-6.41, 0.17] | 5.42 [1.74, 9.86] | 27% [0%, 41%] | 58% | 73% | +0.46 | +0.46 | 2026-01-10 → 2026-08-30 |
| tmin | 12Z | bilinear | all | 26 2 QC | 3.05 [1.38, 7.41] | 3.04 | -1.99 [-7.30, 0.16] | 5.42 [1.71, 10.36] | 27% [0%, 42%] | 58% | 73% | +0.46 | +0.46 | 2026-01-10 → 2026-08-30 |
| tmin | 12Z | nearest | 30d | 21 2 QC | 1.71 [1.37, 2.11] | 1.69 | +0.14 [-0.94, 0.87] | 2.06 [1.60, 2.48] | 33% [11%, 48%] | 67% | 86% | +0.52 | +0.53 | 2026-08-10 → 2026-08-30 |
| tmin | 12Z | nearest | 90d | 21 2 QC | 1.71 [1.36, 2.18] | 1.69 | +0.14 [-1.16, 0.95] | 2.06 [1.55, 2.52] | 33% [0%, 50%] | 67% | 86% | +0.52 | +0.53 | 2026-08-10 → 2026-08-30 |
| tmin | 12Z | nearest | 365d | 26 2 QC | 3.03 [1.50, 6.52] | 3.09 | -1.54 [-5.96, 0.66] | 5.26 [1.76, 9.53] | 27% [0%, 44%] | 54% | 73% | +0.47 | +0.45 | 2026-01-10 → 2026-08-30 |
| tmin | 12Z | nearest | all | 26 2 QC | 3.03 [1.48, 7.02] | 3.09 | -1.54 [-6.91, 0.66] | 5.26 [1.73, 10.00] | 27% [0%, 44%] | 54% | 73% | +0.47 | +0.45 | 2026-01-10 → 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 (21 days, newest first) · download CSV
| Climatological day | Error °F |
|---|---|
| 2026-08-30 | -5.93 |
| 2026-08-29 | -2.03 |
| 2026-08-28 | -8.38 |
| 2026-08-27 | -8.40 |
| 2026-08-26 | -6.05 |
| 2026-08-25 | -3.47 |
| 2026-08-24 | -3.25 |
| 2026-08-23 | -6.08 |
| 2026-08-22 | -9.40 |
| 2026-08-21 | -2.86 |
| 2026-08-20 | -2.87 |
| 2026-08-19 | -6.89 |
| 2026-08-18 | -6.95 |
| 2026-08-17 | -2.93 |
| 2026-08-16 | -3.77 |
| 2026-08-15 | -2.26 |
| 2026-08-14 | -6.34 |
| 2026-08-13 | -4.98 |
| 2026-08-12 | -4.20 |
| 2026-08-11 | -4.22 |
| 2026-08-10 | -3.96 |
Error distribution
Bin counts as a table
| From °F | To °F | Days |
|---|---|---|
| -20.00 | -18.00 | 0 |
| -18.00 | -16.00 | 0 |
| -16.00 | -14.00 | 0 |
| -14.00 | -12.00 | 0 |
| -12.00 | -10.00 | 2 |
| -10.00 | -8.00 | 4 |
| -8.00 | -6.00 | 5 |
| -6.00 | -4.00 | 4 |
| -4.00 | -2.00 | 11 |
| -2.00 | +0.00 | 0 |
| +0.00 | +2.00 | 0 |
| +2.00 | +4.00 | 0 |
| +4.00 | +6.00 | 1 |
| +6.00 | +8.00 | 0 |
| +8.00 | +10.00 | 0 |
| +10.00 | +12.00 | 0 |
| +12.00 | +14.00 | 0 |
| +14.00 | +16.00 | 0 |
| +16.00 | +18.00 | 0 |
| +18.00 | +20.00 | 0 |
Month by month
00Z bilinear daily maximum, newest first.
| Month | n | MAE °F | Bias °F |
|---|---|---|---|
| 2026-08 | 21 | 5.01 | -5.01 |
| 2026-01 | 6 | 6.98 | -5.49 |
Availability
| Model | Scored period | Days | Coverage |
|---|---|---|---|
| GraphCast (IFS init) | 2026-01-10 → 2026-08-30 | 27 | |
| GraphCast (IFS init) | 2026-01-10 → 2026-08-30 | 27 | |
| GraphCast (IFS init) | 2026-01-10 → 2026-08-30 | 26 | |
| GraphCast (IFS init) | 2026-01-10 → 2026-08-30 | 26 |
Compared with other models
Paired bootstrap on the days both models cover (90d, 00Z, bilinear, daily maximum). Negative means GraphCast (IFS init) has the lower MAE. "Distinguishable" means the 95 % interval excludes zero.
| Other model | Common days | MAE difference °F | Distinguishable |
|---|---|---|---|
| ECMWF AIFS Single | 21 | +0.53 [-0.40, 1.42] | no |
| NCEP GFS | 21 | +2.36 [0.54, 4.45] | yes |
| ECMWF IFS HRES | 16 | +1.35 [-0.86, 2.31] | no |
| Persistence (baseline) | 21 | +2.06 [0.88, 3.21] | yes |
Cite this page
ShortCastCheck, KMIA graphcast_ifs lead 9, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KMIA/model/graphcast_ifs/lead/9/
LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KMIA (Miami Intl), model graphcast_ifs, lead day 9. Methodology version 0.2, schema version 0.1, data through 2026-08-30. Accessed 2026-08-31. https://castcheck.zifanzhang.com/station/KMIA/model/graphcast_ifs/lead/9/
Accessed2026-08-31 (data through 2026-08-30; page built 2026-08-31T03:52:06+00:00)