Raw model output on the native 0.25° grid — no MOS, no bias correction, no post-processing. Scores understate operational forecast quality. Read the fairness statement →

CastCheck methodology v0.2 · data through 2026-08-30

Atlanta Hartsfield · ECMWF AIFS Single · lead day 4

KATL · 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.

VariableInitMethod Windown MAE °F MAE debiased Bias °F RMSE °F ±1 °F±2 °F±3 °F Skill Skill, debiased Period
tmax00Zbilinear30d26 1 QC4.21 [3.49, 4.88]1.42-4.21 [-4.88, -3.49]4.57 [3.89, 5.13]8% [0%, 15%]15%19%-0.52+0.482026-08-05 → 2026-08-30
tmax00Zbilinear90d26 1 QC4.21 [3.51, 5.00]1.42-4.21 [-5.00, -3.51]4.57 [3.86, 5.24]8% [0%, 14%]15%19%-0.52+0.482026-08-05 → 2026-08-30
tmax00Zbilinear365d26 1 QC4.21 [3.40, 4.96]1.42-4.21 [-4.96, -3.40]4.57 [3.76, 5.21]8% [0%, 15%]15%19%-0.52+0.482026-08-05 → 2026-08-30
tmax00Zbilinearall26 1 QC4.21 [3.41, 4.94]1.42-4.21 [-4.94, -3.41]4.57 [3.76, 5.18]8% [0%, 15%]15%19%-0.52+0.482026-08-05 → 2026-08-30
tmax00Znearest30d26 1 QC4.34 [3.60, 5.01]1.43-4.34 [-5.01, -3.60]4.69 [3.98, 5.27]4% [0%, 11%]12%19%-0.57+0.482026-08-05 → 2026-08-30
tmax00Znearest90d26 1 QC4.34 [3.63, 5.14]1.43-4.34 [-5.14, -3.63]4.69 [3.95, 5.38]4% [0%, 11%]12%19%-0.57+0.482026-08-05 → 2026-08-30
tmax00Znearest365d26 1 QC4.34 [3.53, 5.11]1.43-4.34 [-5.11, -3.53]4.69 [3.85, 5.36]4% [0%, 12%]12%19%-0.57+0.482026-08-05 → 2026-08-30
tmax00Znearestall26 1 QC4.34 [3.52, 5.08]1.43-4.34 [-5.08, -3.52]4.69 [3.84, 5.33]4% [0%, 12%]12%19%-0.57+0.482026-08-05 → 2026-08-30
tmax12Zbilinear30d26 1 QC4.49 [3.81, 5.03]1.42-4.49 [-5.03, -3.81]4.82 [4.18, 5.35]8% [0%, 15%]8%23%-0.62+0.482026-08-05 → 2026-08-30
tmax12Zbilinear90d26 1 QC4.49 [3.86, 5.13]1.42-4.49 [-5.13, -3.86]4.82 [4.19, 5.47]8% [0%, 14%]8%23%-0.62+0.482026-08-05 → 2026-08-30
tmax12Zbilinear365d26 1 QC4.49 [3.78, 5.07]1.42-4.49 [-5.07, -3.78]4.82 [4.10, 5.47]8% [0%, 15%]8%23%-0.62+0.482026-08-05 → 2026-08-30
tmax12Zbilinearall26 1 QC4.49 [3.78, 5.08]1.42-4.49 [-5.08, -3.78]4.82 [4.10, 5.45]8% [0%, 15%]8%23%-0.62+0.482026-08-05 → 2026-08-30
tmax12Znearest30d26 1 QC4.61 [3.91, 5.17]1.48-4.61 [-5.17, -3.91]4.95 [4.26, 5.47]8% [0%, 15%]8%19%-0.67+0.462026-08-05 → 2026-08-30
tmax12Znearest90d26 1 QC4.61 [3.96, 5.23]1.48-4.61 [-5.23, -3.96]4.95 [4.27, 5.58]8% [0%, 14%]8%19%-0.67+0.462026-08-05 → 2026-08-30
tmax12Znearest365d26 1 QC4.61 [3.89, 5.20]1.48-4.61 [-5.20, -3.89]4.95 [4.21, 5.58]8% [0%, 15%]8%19%-0.67+0.462026-08-05 → 2026-08-30
tmax12Znearestall26 1 QC4.61 [3.89, 5.20]1.48-4.61 [-5.20, -3.89]4.95 [4.18, 5.58]8% [0%, 15%]8%19%-0.67+0.462026-08-05 → 2026-08-30
tmin00Zbilinear30d26 1 QC1.79 [1.15, 2.28]1.77-0.25 [-1.39, 0.68]2.31 [1.48, 2.86]42% [27%, 64%]58%81%+0.17+0.192026-08-05 → 2026-08-30
tmin00Zbilinear90d26 1 QC1.79 [0.99, 2.29]1.77-0.25 [-1.55, 0.75]2.31 [1.19, 2.88]42% [27%, 69%]58%81%+0.17+0.192026-08-05 → 2026-08-30
tmin00Zbilinear365d26 1 QC1.79 [0.99, 2.33]1.77-0.25 [-1.72, 0.76]2.31 [1.21, 2.92]42% [24%, 67%]58%81%+0.17+0.192026-08-05 → 2026-08-30
tmin00Zbilinearall26 1 QC1.79 [0.94, 2.34]1.77-0.25 [-1.71, 0.76]2.31 [1.11, 2.96]42% [25%, 71%]58%81%+0.17+0.192026-08-05 → 2026-08-30
tmin00Znearest30d26 1 QC1.81 [1.15, 2.32]1.77-0.33 [-1.49, 0.60]2.34 [1.45, 2.93]38% [23%, 58%]65%81%+0.16+0.182026-08-05 → 2026-08-30
tmin00Znearest90d26 1 QC1.81 [1.02, 2.33]1.77-0.33 [-1.64, 0.67]2.34 [1.20, 2.93]38% [24%, 62%]65%81%+0.16+0.182026-08-05 → 2026-08-30
tmin00Znearest365d26 1 QC1.81 [1.01, 2.38]1.77-0.33 [-1.84, 0.69]2.34 [1.22, 2.99]38% [24%, 64%]65%81%+0.16+0.182026-08-05 → 2026-08-30
tmin00Znearestall26 1 QC1.81 [0.96, 2.40]1.77-0.33 [-1.82, 0.68]2.34 [1.09, 3.02]38% [24%, 67%]65%81%+0.16+0.182026-08-05 → 2026-08-30
tmin12Zbilinear30d26 1 QC1.90 [1.21, 2.43]1.85-0.35 [-1.53, 0.60]2.37 [1.53, 2.95]38% [19%, 62%]58%81%+0.12+0.152026-08-05 → 2026-08-30
tmin12Zbilinear90d26 1 QC1.90 [1.03, 2.44]1.85-0.35 [-1.64, 0.72]2.37 [1.26, 2.94]38% [20%, 67%]58%81%+0.12+0.152026-08-05 → 2026-08-30
tmin12Zbilinear365d26 1 QC1.90 [1.03, 2.52]1.85-0.35 [-1.86, 0.74]2.37 [1.28, 2.99]38% [17%, 67%]58%81%+0.12+0.152026-08-05 → 2026-08-30
tmin12Zbilinearall26 1 QC1.90 [0.91, 2.50]1.85-0.35 [-1.84, 0.73]2.37 [1.14, 3.02]38% [17%, 67%]58%81%+0.12+0.152026-08-05 → 2026-08-30
tmin12Znearest30d26 1 QC1.92 [1.19, 2.48]1.85-0.43 [-1.60, 0.53]2.38 [1.56, 2.98]35% [15%, 60%]58%81%+0.11+0.152026-08-05 → 2026-08-30
tmin12Znearest90d26 1 QC1.92 [1.01, 2.49]1.85-0.43 [-1.74, 0.64]2.38 [1.27, 2.98]35% [15%, 67%]58%81%+0.11+0.152026-08-05 → 2026-08-30
tmin12Znearest365d26 1 QC1.92 [1.04, 2.56]1.85-0.43 [-1.94, 0.66]2.38 [1.30, 3.04]35% [14%, 67%]58%81%+0.11+0.152026-08-05 → 2026-08-30
tmin12Znearestall26 1 QC1.92 [0.91, 2.54]1.85-0.43 [-1.93, 0.67]2.38 [1.16, 3.05]35% [14%, 67%]58%81%+0.11+0.152026-08-05 → 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

Daily forecast minus observed error in °F for ECMWF AIFS Single at KATL, lead day 4, 00Z bilinear tmax+10+50-5-102026-08-05: -6.86 °F2026-08-06: -3.83 °F2026-08-07: -2.81 °F2026-08-08: -5.85 °F2026-08-09: -4.55 °F2026-08-10: -6.52 °F2026-08-11: -5.19 °F2026-08-12: -5.12 °F2026-08-13: -5.17 °F2026-08-14: -3.04 °F2026-08-15: -3.98 °F2026-08-16: -1.71 °F2026-08-17: -3.01 °F2026-08-18: -0.17 °F2026-08-19: -5.01 °F2026-08-20: -4.37 °F2026-08-21: -4.76 °F2026-08-22: -3.39 °F2026-08-23: -2 °F2026-08-24: -4.9 °F2026-08-25: -4.69 °F2026-08-26: -0.9 °F2026-08-27: -7.55 °F2026-08-28: -6.51 °F2026-08-29: -4.56 °F2026-08-30: -3.01 °F2026-08-052026-08-30°F, forecast − observed
Forecast − observed, °F, 00Z bilinear daily maximum. The dashed line is zero; the thick line is a centred 7-day mean, drawn only where the whole window is present. Gaps are days with no score, never interpolation. Hover a point for its date and value.
The same series as a table (26 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-3.01
2026-08-29-4.56
2026-08-28-6.51
2026-08-27-7.55
2026-08-26-0.90
2026-08-25-4.69
2026-08-24-4.90
2026-08-23-2.00
2026-08-22-3.39
2026-08-21-4.76
2026-08-20-4.37
2026-08-19-5.01
2026-08-18-0.17
2026-08-17-3.01
2026-08-16-1.71
2026-08-15-3.98
2026-08-14-3.04
2026-08-13-5.17
2026-08-12-5.12
2026-08-11-5.19
2026-08-10-6.52
2026-08-09-4.55
2026-08-08-5.85
2026-08-07-2.81
2026-08-06-3.83
2026-08-05-6.86

Error distribution

Distribution of the signed daily error in °F for ECMWF AIFS Single at KATL, lead day 4-10 to -9 °F: 0 days-9 to -8 °F: 0 days-8 to -7 °F: 1 day-7 to -6 °F: 3 days-6 to -5 °F: 5 days-5 to -4 °F: 6 days-4 to -3 °F: 6 days-3 to -2 °F: 1 day-2 to -1 °F: 2 days-1 to 0 °F: 2 days0 to 1 °F: 0 days1 to 2 °F: 0 days2 to 3 °F: 0 days3 to 4 °F: 0 days4 to 5 °F: 0 days5 to 6 °F: 0 days6 to 7 °F: 0 days7 to 8 °F: 0 days8 to 9 °F: 0 days9 to 10 °F: 0 daysdashed: P50 |e| 4.55 · P90 |e| 6.52 °F-100+10 °Fn = 26 days
All scored days for 00Z bilinear daily maximum, 20 equal bins. The dashed marks are the 50th and 90th percentiles of the absolute error, mirrored on both sides. Hover a bar for its bin and count.
Bin counts as a table
From °FTo °FDays
-10.00-9.000
-9.00-8.000
-8.00-7.001
-7.00-6.003
-6.00-5.005
-5.00-4.006
-4.00-3.006
-3.00-2.001
-2.00-1.002
-1.00+0.002
+0.00+1.000
+1.00+2.000
+2.00+3.000
+3.00+4.000
+4.00+5.000
+5.00+6.000
+6.00+7.000
+7.00+8.000
+8.00+9.000
+9.00+10.000

Month by month

00Z bilinear daily maximum, newest first.

Monthn MAE °FBias °F
2026-08264.21 -4.21

Availability

ModelScored period DaysCoverage
ECMWF AIFS Single2026-08-05 → 2026-08-30 26
ECMWF AIFS Single2026-08-05 → 2026-08-30 26
ECMWF AIFS Single2026-08-05 → 2026-08-30 26
ECMWF AIFS Single2026-08-05 → 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 modelCommon days MAE difference °FDistinguishable
NCEP GFS 26 +0.95 [-0.53, 2.76] no
GraphCast (IFS init) 25 -0.88 [-1.99, 0.29] no
ECMWF IFS HRES 20 +0.10 [-1.21, 2.09] no
Persistence (baseline) 26 +1.44 [0.99, 2.05] yes

Cite this page

ShortCastCheck, KATL aifs_single lead 4, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KATL/model/aifs_single/lead/4/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KATL (Atlanta Hartsfield), 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/KATL/model/aifs_single/lead/4/

Accessed2026-08-31 (data through 2026-08-30; page built 2026-08-31T03:52:06+00:00)

JSON CSV all scores methodology v0.2 licence