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 2

KATL · aifs_single · lead 2

Target day = initialization date + 2 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
tmax00Zbilinear30d28 1 QC4.38 [3.76, 4.85]1.43-4.37 [-4.84, -3.74]4.74 [4.09, 5.19]4% [0%, 11%]7%14%-0.83+0.402026-08-03 → 2026-08-30
tmax00Zbilinear90d28 1 QC4.38 [3.76, 4.88]1.43-4.37 [-4.88, -3.74]4.74 [4.09, 5.24]4% [0%, 10%]7%14%-0.83+0.402026-08-03 → 2026-08-30
tmax00Zbilinear365d28 1 QC4.38 [3.64, 4.91]1.43-4.37 [-4.90, -3.62]4.74 [3.99, 5.25]4% [0%, 11%]7%14%-0.83+0.402026-08-03 → 2026-08-30
tmax00Zbilinearall28 1 QC4.38 [3.68, 4.92]1.43-4.37 [-4.92, -3.67]4.74 [4.01, 5.27]4% [0%, 11%]7%14%-0.83+0.402026-08-03 → 2026-08-30
tmax00Znearest30d28 1 QC4.52 [3.83, 5.04]1.48-4.52 [-5.04, -3.83]4.90 [4.23, 5.40]4% [0%, 11%]7%14%-0.89+0.382026-08-03 → 2026-08-30
tmax00Znearest90d28 1 QC4.52 [3.85, 5.06]1.48-4.52 [-5.06, -3.85]4.90 [4.21, 5.43]4% [0%, 10%]7%14%-0.89+0.382026-08-03 → 2026-08-30
tmax00Znearest365d28 1 QC4.52 [3.74, 5.06]1.48-4.52 [-5.06, -3.74]4.90 [4.10, 5.44]4% [0%, 11%]7%14%-0.89+0.382026-08-03 → 2026-08-30
tmax00Znearestall28 1 QC4.52 [3.77, 5.14]1.48-4.52 [-5.14, -3.77]4.90 [4.12, 5.48]4% [0%, 11%]7%14%-0.89+0.382026-08-03 → 2026-08-30
tmax12Zbilinear30d28 1 QC4.38 [3.89, 4.81]1.31-4.38 [-4.81, -3.89]4.68 [4.21, 5.04]4% [0%, 11%]4%14%-0.83+0.452026-08-03 → 2026-08-30
tmax12Zbilinear90d28 1 QC4.38 [3.90, 4.94]1.31-4.38 [-4.94, -3.90]4.68 [4.23, 5.14]4% [0%, 10%]4%14%-0.83+0.452026-08-03 → 2026-08-30
tmax12Zbilinear365d28 1 QC4.38 [3.84, 4.97]1.31-4.38 [-4.97, -3.84]4.68 [4.17, 5.16]4% [0%, 11%]4%14%-0.83+0.452026-08-03 → 2026-08-30
tmax12Zbilinearall28 1 QC4.38 [3.85, 4.93]1.31-4.38 [-4.93, -3.85]4.68 [4.16, 5.12]4% [0%, 11%]4%14%-0.83+0.452026-08-03 → 2026-08-30
tmax12Znearest30d28 1 QC4.48 [3.99, 4.89]1.29-4.48 [-4.89, -3.99]4.76 [4.28, 5.12]4% [0%, 11%]4%11%-0.87+0.462026-08-03 → 2026-08-30
tmax12Znearest90d28 1 QC4.48 [3.98, 5.01]1.29-4.48 [-5.01, -3.98]4.76 [4.29, 5.19]4% [0%, 10%]4%11%-0.87+0.462026-08-03 → 2026-08-30
tmax12Znearest365d28 1 QC4.48 [3.91, 5.02]1.29-4.48 [-5.02, -3.91]4.76 [4.23, 5.21]4% [0%, 11%]4%11%-0.87+0.462026-08-03 → 2026-08-30
tmax12Znearestall28 1 QC4.48 [3.92, 5.00]1.29-4.48 [-5.00, -3.92]4.76 [4.24, 5.17]4% [0%, 11%]4%11%-0.87+0.462026-08-03 → 2026-08-30
tmin00Zbilinear30d28 1 QC1.88 [1.11, 2.48]1.84-0.37 [-1.62, 0.55]2.41 [1.51, 3.04]39% [21%, 62%]61%82%+0.11+0.142026-08-03 → 2026-08-30
tmin00Zbilinear90d28 1 QC1.88 [0.96, 2.45]1.84-0.37 [-1.65, 0.66]2.41 [1.28, 3.02]39% [22%, 65%]61%82%+0.11+0.142026-08-03 → 2026-08-30
tmin00Zbilinear365d28 1 QC1.88 [0.98, 2.51]1.84-0.37 [-1.84, 0.69]2.41 [1.28, 3.06]39% [21%, 64%]61%82%+0.11+0.142026-08-03 → 2026-08-30
tmin00Zbilinearall28 1 QC1.88 [0.95, 2.61]1.84-0.37 [-1.93, 0.71]2.41 [1.25, 3.12]39% [19%, 65%]61%82%+0.11+0.142026-08-03 → 2026-08-30
tmin00Znearest30d28 1 QC1.90 [1.09, 2.52]1.85-0.46 [-1.74, 0.48]2.45 [1.49, 3.15]29% [10%, 52%]61%82%+0.10+0.132026-08-03 → 2026-08-30
tmin00Znearest90d28 1 QC1.90 [0.96, 2.50]1.85-0.46 [-1.78, 0.60]2.45 [1.31, 3.13]29% [10%, 56%]61%82%+0.10+0.132026-08-03 → 2026-08-30
tmin00Znearest365d28 1 QC1.90 [0.96, 2.57]1.85-0.46 [-1.99, 0.63]2.45 [1.30, 3.17]29% [9%, 57%]61%82%+0.10+0.132026-08-03 → 2026-08-30
tmin00Znearestall28 1 QC1.90 [0.95, 2.64]1.85-0.46 [-2.08, 0.65]2.45 [1.27, 3.24]29% [9%, 57%]61%82%+0.10+0.132026-08-03 → 2026-08-30
tmin12Zbilinear30d28 1 QC1.68 [1.02, 2.16]1.63-0.35 [-1.36, 0.40]2.18 [1.40, 2.68]43% [23%, 67%]64%86%+0.20+0.232026-08-03 → 2026-08-30
tmin12Zbilinear90d28 1 QC1.68 [0.90, 2.15]1.63-0.35 [-1.36, 0.47]2.18 [1.15, 2.66]43% [22%, 70%]64%86%+0.20+0.232026-08-03 → 2026-08-30
tmin12Zbilinear365d28 1 QC1.68 [0.90, 2.17]1.63-0.35 [-1.59, 0.51]2.18 [1.13, 2.70]43% [21%, 70%]64%86%+0.20+0.232026-08-03 → 2026-08-30
tmin12Zbilinearall28 1 QC1.68 [0.85, 2.17]1.63-0.35 [-1.71, 0.54]2.18 [1.12, 2.78]43% [22%, 69%]64%86%+0.20+0.232026-08-03 → 2026-08-30
tmin12Znearest30d28 1 QC1.70 [1.03, 2.20]1.64-0.44 [-1.48, 0.33]2.22 [1.39, 2.79]43% [23%, 67%]64%82%+0.19+0.232026-08-03 → 2026-08-30
tmin12Znearest90d28 1 QC1.70 [0.90, 2.20]1.64-0.44 [-1.49, 0.40]2.22 [1.17, 2.76]43% [22%, 70%]64%82%+0.19+0.232026-08-03 → 2026-08-30
tmin12Znearest365d28 1 QC1.70 [0.90, 2.22]1.64-0.44 [-1.72, 0.44]2.22 [1.12, 2.80]43% [21%, 70%]64%82%+0.19+0.232026-08-03 → 2026-08-30
tmin12Znearestall28 1 QC1.70 [0.86, 2.23]1.64-0.44 [-1.82, 0.48]2.22 [1.12, 2.88]43% [22%, 69%]64%82%+0.19+0.232026-08-03 → 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 2, 00Z bilinear tmax+10+50-5-102026-08-03: -3.69 °F2026-08-04: -3.17 °F2026-08-05: -7.36 °F2026-08-06: -3.04 °F2026-08-07: -3.37 °F2026-08-08: -5.16 °F2026-08-09: -4.76 °F2026-08-10: -7.31 °F2026-08-11: -3.44 °F2026-08-12: -3.53 °F2026-08-13: -4.52 °F2026-08-14: -2.99 °F2026-08-15: -3.17 °F2026-08-16: -2.53 °F2026-08-17: -3.07 °F2026-08-18: +0.14 °F2026-08-19: -5.43 °F2026-08-20: -8.75 °F2026-08-21: -5.95 °F2026-08-22: -4.75 °F2026-08-23: -4.67 °F2026-08-24: -3.19 °F2026-08-25: -4.96 °F2026-08-26: -1.84 °F2026-08-27: -7.39 °F2026-08-28: -5.13 °F2026-08-29: -4.33 °F2026-08-30: -5.05 °F2026-08-032026-08-30°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 (28 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-5.05
2026-08-29-4.33
2026-08-28-5.13
2026-08-27-7.39
2026-08-26-1.84
2026-08-25-4.96
2026-08-24-3.19
2026-08-23-4.67
2026-08-22-4.75
2026-08-21-5.95
2026-08-20-8.75
2026-08-19-5.43
2026-08-18+0.14
2026-08-17-3.07
2026-08-16-2.53
2026-08-15-3.17
2026-08-14-2.99
2026-08-13-4.52
2026-08-12-3.53
2026-08-11-3.44
2026-08-10-7.31
2026-08-09-4.76
2026-08-08-5.16
2026-08-07-3.37
2026-08-06-3.04
2026-08-05-7.36
2026-08-04-3.17
2026-08-03-3.69

Error distribution

Distribution of the signed daily error in °F for ECMWF AIFS Single at KATL, lead day 2-10 to -9 °F: 0 days-9 to -8 °F: 1 day-8 to -7 °F: 3 days-7 to -6 °F: 0 days-6 to -5 °F: 5 days-5 to -4 °F: 6 days-4 to -3 °F: 9 days-3 to -2 °F: 2 days-2 to -1 °F: 1 day-1 to 0 °F: 0 days0 to 1 °F: 1 day1 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| 4.42 · P90 |e| 7.33 °F-100+10 °Fn = 28 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
-9.00-8.001
-8.00-7.003
-7.00-6.000
-6.00-5.005
-5.00-4.006
-4.00-3.009
-3.00-2.002
-2.00-1.001
-1.00+0.000
+0.00+1.001
+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
2026-08284.38 -4.37

Availability

ModelScored period DaysCoverage
ECMWF AIFS Single2026-08-03 → 2026-08-30 28
ECMWF AIFS Single2026-08-03 → 2026-08-30 28
ECMWF AIFS Single2026-08-03 → 2026-08-30 28
ECMWF AIFS Single2026-08-03 → 2026-08-30 28

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
Aurora (IFS init) 1 -2.47 [-2.47, -2.47] yes
FourCastNet v2 (IFS init) 1 +0.41 [0.41, 0.41] yes
NCEP GFS 28 +1.25 [0.24, 2.16] yes
GraphCast (IFS init) 26 -1.45 [-2.18, -0.47] yes
ECMWF IFS HRES 22 +1.75 [0.64, 2.69] yes
Pangu-Weather (IFS init) 1 +0.34 [0.34, 0.34] yes
Persistence (baseline) 28 +1.99 [1.22, 2.67] yes

Cite this page

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

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

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