Miami Intl · GraphCast (IFS init) · lead day 8
KMIA · graphcast_ifs · lead 8
Target day = initialization date + 8 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 | 22 2 QC | 5.10 [4.02, 6.19] | 1.99 | -5.10 [-6.19, -4.02] | 5.65 [4.39, 6.61] | 5% [0%, 12%] | 5% | 14% | -0.81 | +0.30 | 2026-08-09 → 2026-08-30 |
| tmax | 00Z | bilinear | 90d | 22 2 QC | 5.10 [3.87, 6.29] | 1.99 | -5.10 [-6.29, -3.87] | 5.65 [4.06, 6.63] | 5% [0%, 12%] | 5% | 14% | -0.81 | +0.30 | 2026-08-09 → 2026-08-30 |
| tmax | 00Z | bilinear | 365d | 28 3 QC | 5.18 [3.99, 6.13] | 2.39 | -5.14 [-6.07, -3.96] | 5.96 [4.48, 7.05] | 7% [0%, 17%] | 7% | 21% | -0.41 | +0.36 | 2026-01-09 → 2026-08-30 |
| tmax | 00Z | bilinear | all | 28 3 QC | 5.18 [4.09, 6.18] | 2.39 | -5.14 [-6.13, -4.04] | 5.96 [4.69, 7.05] | 7% [0%, 18%] | 7% | 21% | -0.41 | +0.36 | 2026-01-09 → 2026-08-30 |
| tmax | 00Z | nearest | 30d | 22 2 QC | 5.50 [4.63, 6.40] | 1.85 | -5.50 [-6.40, -4.63] | 5.95 [4.90, 6.76] | 0% [0%, 0%] | 5% | 9% | -0.95 | +0.35 | 2026-08-09 → 2026-08-30 |
| tmax | 00Z | nearest | 90d | 22 2 QC | 5.50 [4.53, 6.46] | 1.85 | -5.50 [-6.46, -4.53] | 5.95 [4.65, 6.78] | 0% [0%, 0%] | 5% | 9% | -0.95 | +0.35 | 2026-08-09 → 2026-08-30 |
| tmax | 00Z | nearest | 365d | 28 3 QC | 5.52 [4.60, 6.30] | 2.24 | -5.50 [-6.30, -4.58] | 6.20 [4.90, 7.14] | 4% [0%, 14%] | 7% | 14% | -0.50 | +0.40 | 2026-01-09 → 2026-08-30 |
| tmax | 00Z | nearest | all | 28 3 QC | 5.52 [4.64, 6.35] | 2.24 | -5.50 [-6.30, -4.61] | 6.20 [5.11, 7.16] | 4% [0%, 15%] | 7% | 14% | -0.50 | +0.40 | 2026-01-09 → 2026-08-30 |
| tmax | 12Z | bilinear | 30d | 22 2 QC | 4.92 [4.13, 5.79] | 1.98 | -4.92 [-5.79, -4.13] | 5.42 [4.46, 6.19] | 0% [0%, 0%] | 5% | 18% | -0.75 | +0.30 | 2026-08-09 → 2026-08-30 |
| tmax | 12Z | bilinear | 90d | 22 2 QC | 4.92 [3.96, 5.84] | 1.98 | -4.92 [-5.84, -3.96] | 5.42 [4.26, 6.20] | 0% [0%, 0%] | 5% | 18% | -0.75 | +0.30 | 2026-08-09 → 2026-08-30 |
| tmax | 12Z | bilinear | 365d | 27 3 QC | 4.95 [4.07, 5.81] | 2.35 | -4.84 [-5.57, -3.97] | 5.62 [4.59, 6.55] | 0% [0%, 0%] | 7% | 26% | -0.32 | +0.38 | 2026-01-09 → 2026-08-30 |
| tmax | 12Z | bilinear | all | 27 3 QC | 4.95 [4.16, 5.80] | 2.35 | -4.84 [-5.63, -3.98] | 5.62 [4.62, 6.54] | 0% [0%, 0%] | 7% | 26% | -0.32 | +0.38 | 2026-01-09 → 2026-08-30 |
| tmax | 12Z | nearest | 30d | 22 2 QC | 5.33 [4.65, 6.02] | 1.80 | -5.33 [-6.02, -4.65] | 5.74 [4.91, 6.41] | 0% [0%, 0%] | 0% | 9% | -0.89 | +0.36 | 2026-08-09 → 2026-08-30 |
| tmax | 12Z | nearest | 90d | 22 2 QC | 5.33 [4.55, 6.03] | 1.80 | -5.33 [-6.03, -4.55] | 5.74 [4.71, 6.37] | 0% [0%, 0%] | 0% | 9% | -0.89 | +0.36 | 2026-08-09 → 2026-08-30 |
| tmax | 12Z | nearest | 365d | 27 3 QC | 5.29 [4.52, 5.94] | 2.16 | -5.21 [-5.81, -4.42] | 5.86 [4.97, 6.62] | 0% [0%, 0%] | 4% | 15% | -0.42 | +0.43 | 2026-01-09 → 2026-08-30 |
| tmax | 12Z | nearest | all | 27 3 QC | 5.29 [4.54, 5.96] | 2.16 | -5.21 [-5.86, -4.43] | 5.86 [4.98, 6.59] | 0% [0%, 0%] | 4% | 15% | -0.42 | +0.43 | 2026-01-09 → 2026-08-30 |
| tmin | 00Z | bilinear | 30d | 22 2 QC | 1.63 [1.18, 2.22] | 1.61 | -0.38 [-1.40, 0.38] | 1.94 [1.46, 2.48] | 41% [10%, 67%] | 64% | 91% | +0.51 | +0.52 | 2026-08-09 → 2026-08-30 |
| tmin | 00Z | bilinear | 90d | 22 2 QC | 1.63 [1.16, 2.28] | 1.61 | -0.38 [-1.77, 0.41] | 1.94 [1.43, 2.59] | 41% [0%, 67%] | 64% | 91% | +0.51 | +0.52 | 2026-08-09 → 2026-08-30 |
| tmin | 00Z | bilinear | 365d | 28 2 QC | 2.61 [1.35, 4.83] | 2.44 | -1.63 [-4.46, 0.10] | 3.83 [1.66, 6.37] | 32% [0%, 58%] | 50% | 79% | +0.52 | +0.57 | 2026-01-09 → 2026-08-30 |
| tmin | 00Z | bilinear | all | 28 2 QC | 2.61 [1.34, 5.33] | 2.44 | -1.63 [-5.14, 0.17] | 3.83 [1.64, 6.61] | 32% [0%, 59%] | 50% | 79% | +0.52 | +0.57 | 2026-01-09 → 2026-08-30 |
| tmin | 00Z | nearest | 30d | 22 2 QC | 1.66 [1.30, 2.04] | 1.66 | +0.10 [-0.89, 0.87] | 1.92 [1.58, 2.27] | 27% [7%, 45%] | 64% | 91% | +0.50 | +0.51 | 2026-08-09 → 2026-08-30 |
| tmin | 00Z | nearest | 90d | 22 2 QC | 1.66 [1.29, 2.11] | 1.66 | +0.10 [-1.25, 0.95] | 1.92 [1.57, 2.34] | 27% [0%, 46%] | 64% | 91% | +0.50 | +0.51 | 2026-08-09 → 2026-08-30 |
| tmin | 00Z | nearest | 365d | 28 2 QC | 2.56 [1.43, 4.56] | 2.48 | -1.18 [-4.03, 0.55] | 3.66 [1.72, 6.01] | 21% [0%, 40%] | 50% | 79% | +0.52 | +0.56 | 2026-01-09 → 2026-08-30 |
| tmin | 00Z | nearest | all | 28 2 QC | 2.56 [1.45, 5.03] | 2.48 | -1.18 [-4.80, 0.65] | 3.66 [1.74, 6.24] | 21% [0%, 42%] | 50% | 79% | +0.52 | +0.56 | 2026-01-09 → 2026-08-30 |
| tmin | 12Z | bilinear | 30d | 22 2 QC | 1.64 [1.17, 2.12] | 1.62 | -0.49 [-1.33, 0.16] | 1.93 [1.47, 2.32] | 32% [7%, 59%] | 59% | 86% | +0.51 | +0.52 | 2026-08-09 → 2026-08-30 |
| tmin | 12Z | bilinear | 90d | 22 2 QC | 1.64 [1.14, 2.28] | 1.62 | -0.49 [-1.61, 0.21] | 1.93 [1.43, 2.37] | 32% [0%, 60%] | 59% | 86% | +0.51 | +0.52 | 2026-08-09 → 2026-08-30 |
| tmin | 12Z | bilinear | 365d | 27 2 QC | 2.11 [1.39, 3.29] | 1.98 | -1.18 [-2.94, -0.06] | 2.66 [1.71, 3.87] | 26% [0%, 50%] | 52% | 74% | +0.62 | +0.66 | 2026-01-09 → 2026-08-30 |
| tmin | 12Z | bilinear | all | 27 2 QC | 2.11 [1.32, 3.66] | 1.98 | -1.18 [-3.50, 0.01] | 2.66 [1.65, 4.18] | 26% [0%, 55%] | 52% | 74% | +0.62 | +0.66 | 2026-01-09 → 2026-08-30 |
| tmin | 12Z | nearest | 30d | 22 2 QC | 1.63 [1.28, 1.97] | 1.62 | +0.01 [-0.82, 0.67] | 1.84 [1.53, 2.11] | 23% [4%, 43%] | 68% | 91% | +0.51 | +0.52 | 2026-08-09 → 2026-08-30 |
| tmin | 12Z | nearest | 90d | 22 2 QC | 1.63 [1.24, 2.07] | 1.62 | +0.01 [-1.06, 0.73] | 1.84 [1.50, 2.17] | 23% [0%, 43%] | 68% | 91% | +0.51 | +0.52 | 2026-08-09 → 2026-08-30 |
| tmin | 12Z | nearest | 365d | 27 2 QC | 2.04 [1.41, 3.04] | 2.00 | -0.71 [-2.50, 0.44] | 2.50 [1.68, 3.60] | 19% [0%, 38%] | 59% | 81% | +0.63 | +0.66 | 2026-01-09 → 2026-08-30 |
| tmin | 12Z | nearest | all | 27 2 QC | 2.04 [1.39, 3.33] | 2.00 | -0.71 [-3.06, 0.52] | 2.50 [1.64, 3.90] | 19% [0%, 40%] | 59% | 81% | +0.63 | +0.66 | 2026-01-09 → 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 (22 days, newest first) · download CSV
| Climatological day | Error °F |
|---|---|
| 2026-08-30 | -6.20 |
| 2026-08-29 | -4.24 |
| 2026-08-28 | -7.06 |
| 2026-08-27 | -8.21 |
| 2026-08-26 | -8.35 |
| 2026-08-25 | -5.07 |
| 2026-08-24 | -2.15 |
| 2026-08-23 | -6.21 |
| 2026-08-22 | -9.76 |
| 2026-08-21 | -4.35 |
| 2026-08-20 | -3.82 |
| 2026-08-19 | -4.39 |
| 2026-08-18 | -10.68 |
| 2026-08-17 | -0.79 |
| 2026-08-16 | -3.15 |
| 2026-08-15 | -2.66 |
| 2026-08-14 | -6.20 |
| 2026-08-13 | -3.06 |
| 2026-08-12 | -3.53 |
| 2026-08-11 | -4.83 |
| 2026-08-10 | -4.00 |
| 2026-08-09 | -3.36 |
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 | 1 |
| -12.00 | -10.00 | 1 |
| -10.00 | -8.00 | 3 |
| -8.00 | -6.00 | 6 |
| -6.00 | -4.00 | 6 |
| -4.00 | -2.00 | 9 |
| -2.00 | +0.00 | 1 |
| +0.00 | +2.00 | 1 |
| +2.00 | +4.00 | 0 |
| +4.00 | +6.00 | 0 |
| +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 | 22 | 5.10 | -5.10 |
| 2026-01 | 6 | 5.50 | -5.29 |
Availability
| Model | Scored period | Days | Coverage |
|---|---|---|---|
| GraphCast (IFS init) | 2026-01-09 → 2026-08-30 | 28 | |
| GraphCast (IFS init) | 2026-01-09 → 2026-08-30 | 28 | |
| GraphCast (IFS init) | 2026-01-09 → 2026-08-30 | 27 | |
| GraphCast (IFS init) | 2026-01-09 → 2026-08-30 | 27 |
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 | 22 | +0.89 [-0.46, 2.36] | no |
| NCEP GFS | 22 | +2.54 [0.61, 4.80] | yes |
| ECMWF IFS HRES | 17 | +1.05 [-1.05, 2.00] | no |
| Persistence (baseline) | 22 | +2.28 [0.86, 3.56] | yes |
Cite this page
ShortCastCheck, KMIA graphcast_ifs lead 8, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KMIA/model/graphcast_ifs/lead/8/
LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KMIA (Miami Intl), model graphcast_ifs, lead day 8. 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/8/
Accessed2026-08-31 (data through 2026-08-30; page built 2026-08-31T03:52:06+00:00)