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 0

KATL · aifs_single · lead 0

Target day = initialization date + 0 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
tmax00Zbilinear30d30 1 QC4.36 [3.81, 4.78]1.16-4.36 [-4.78, -3.81]4.59 [4.04, 5.00]0% [0%, 0%]3%20%——2026-08-01 → 2026-08-30
tmax00Zbilinear90d30 1 QC4.36 [3.86, 4.90]1.16-4.36 [-4.90, -3.86]4.59 [4.07, 5.11]0% [0%, 0%]3%20%——2026-08-01 → 2026-08-30
tmax00Zbilinear365d30 1 QC4.36 [3.78, 4.85]1.16-4.36 [-4.85, -3.78]4.59 [3.99, 5.10]0% [0%, 0%]3%20%——2026-08-01 → 2026-08-30
tmax00Zbilinearall30 1 QC4.36 [3.81, 4.89]1.16-4.36 [-4.89, -3.81]4.59 [4.01, 5.12]0% [0%, 0%]3%20%——2026-08-01 → 2026-08-30
tmax00Znearest30d30 1 QC4.47 [3.90, 4.90]1.18-4.47 [-4.90, -3.90]4.69 [4.13, 5.09]0% [0%, 0%]3%13%——2026-08-01 → 2026-08-30
tmax00Znearest90d30 1 QC4.47 [3.91, 5.00]1.18-4.47 [-5.00, -3.91]4.69 [4.16, 5.19]0% [0%, 0%]3%13%——2026-08-01 → 2026-08-30
tmax00Znearest365d30 1 QC4.47 [3.85, 4.97]1.18-4.47 [-4.97, -3.85]4.69 [4.07, 5.19]0% [0%, 0%]3%13%——2026-08-01 → 2026-08-30
tmax00Znearestall30 1 QC4.47 [3.89, 4.99]1.18-4.47 [-4.99, -3.89]4.69 [4.09, 5.20]0% [0%, 0%]3%13%——2026-08-01 → 2026-08-30
tmin00Zbilinear30d30 1 QC1.34 [0.97, 1.65]1.29-0.40 [-1.10, 0.12]1.73 [1.32, 2.06]43% [30%, 60%]80%93%——2026-08-01 → 2026-08-30
tmin00Zbilinear90d30 1 QC1.34 [0.94, 1.67]1.29-0.40 [-1.14, 0.14]1.73 [1.24, 2.04]43% [27%, 62%]80%93%——2026-08-01 → 2026-08-30
tmin00Zbilinear365d30 1 QC1.34 [0.92, 1.67]1.29-0.40 [-1.24, 0.15]1.73 [1.24, 2.06]43% [27%, 63%]80%93%——2026-08-01 → 2026-08-30
tmin00Zbilinearall30 1 QC1.34 [0.95, 1.67]1.29-0.40 [-1.28, 0.14]1.73 [1.26, 2.07]43% [27%, 64%]80%93%——2026-08-01 → 2026-08-30
tmin00Znearest30d30 1 QC1.38 [0.99, 1.71]1.31-0.48 [-1.23, 0.07]1.77 [1.33, 2.14]40% [27%, 60%]77%93%——2026-08-01 → 2026-08-30
tmin00Znearest90d30 1 QC1.38 [0.96, 1.72]1.31-0.48 [-1.25, 0.09]1.77 [1.26, 2.11]40% [22%, 61%]77%93%——2026-08-01 → 2026-08-30
tmin00Znearest365d30 1 QC1.38 [0.96, 1.73]1.31-0.48 [-1.36, 0.09]1.77 [1.25, 2.15]40% [22%, 62%]77%93%——2026-08-01 → 2026-08-30
tmin00Znearestall30 1 QC1.38 [0.98, 1.73]1.31-0.48 [-1.44, 0.09]1.77 [1.27, 2.18]40% [21%, 62%]77%93%——2026-08-01 → 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 0, 00Z bilinear tmax+10+50-5-102026-08-01: -3.94 °F2026-08-02: -7.85 °F2026-08-03: -3.85 °F2026-08-04: -4.38 °F2026-08-05: -5.71 °F2026-08-06: -5.91 °F2026-08-07: -3.74 °F2026-08-08: -4.01 °F2026-08-09: -3.81 °F2026-08-10: -5.82 °F2026-08-11: -3.64 °F2026-08-12: -4.61 °F2026-08-13: -4.17 °F2026-08-14: -2.74 °F2026-08-15: -3.83 °F2026-08-16: -3.23 °F2026-08-17: -2.53 °F2026-08-18: -1.27 °F2026-08-19: -4.94 °F2026-08-20: -6.1 °F2026-08-21: -5.81 °F2026-08-22: -6.56 °F2026-08-23: -2.6 °F2026-08-24: -2.86 °F2026-08-25: -4.47 °F2026-08-26: -3.42 °F2026-08-27: -6.01 °F2026-08-28: -6.01 °F2026-08-29: -4.27 °F2026-08-30: -2.8 °F2026-08-012026-08-30°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 (30 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-2.80
2026-08-29-4.27
2026-08-28-6.01
2026-08-27-6.01
2026-08-26-3.42
2026-08-25-4.47
2026-08-24-2.86
2026-08-23-2.60
2026-08-22-6.56
2026-08-21-5.81
2026-08-20-6.10
2026-08-19-4.94
2026-08-18-1.27
2026-08-17-2.53
2026-08-16-3.23
2026-08-15-3.83
2026-08-14-2.74
2026-08-13-4.17
2026-08-12-4.61
2026-08-11-3.64
2026-08-10-5.82
2026-08-09-3.81
2026-08-08-4.01
2026-08-07-3.74
2026-08-06-5.91
2026-08-05-5.71
2026-08-04-4.38
2026-08-03-3.85
2026-08-02-7.85
2026-08-01-3.94

Error distribution

Distribution of the signed daily error in °F for ECMWF AIFS Single at KATL, lead day 0-10 to -9 °F: 0 days-9 to -8 °F: 0 days-8 to -7 °F: 1 day-7 to -6 °F: 4 days-6 to -5 °F: 4 days-5 to -4 °F: 7 days-4 to -3 °F: 8 days-3 to -2 °F: 5 days-2 to -1 °F: 1 day-1 to 0 °F: 0 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| 4.09 · P90 |e| 6.02 °F-100+10 °Fn = 30 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
-7.00-6.004
-6.00-5.004
-5.00-4.007
-4.00-3.008
-3.00-2.005
-2.00-1.001
-1.00+0.000
+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
2026-08304.36 -4.36

Availability

ModelScored period DaysCoverage
ECMWF AIFS Single2026-08-01 → 2026-08-30 30
ECMWF AIFS Single2026-08-01 → 2026-08-30 30

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 (GFS init) 2 -3.05 [-3.68, -2.43] yes
Aurora (IFS init) 3 -2.33 [-3.11, -1.94] yes
FourCastNet v2 (GFS init) 2 -0.14 [-0.58, 0.31] no
FourCastNet v2 (IFS init) 3 -0.07 [-1.23, 0.51] no
NCEP GFS 30 +3.20 [2.74, 3.58] yes
GraphCast (GFS init) 2 -1.50 [-2.67, -0.34] yes
GraphCast (IFS init) 28 -1.56 [-2.30, -0.79] yes
ECMWF IFS HRES 24 +1.50 [0.97, 1.81] yes
Pangu-Weather (GFS init) 2 +1.04 [0.11, 1.97] yes
Pangu-Weather (IFS init) 3 +1.08 [0.45, 1.40] yes

Cite this page

ShortCastCheck, KATL aifs_single lead 0, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KATL/model/aifs_single/lead/0/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KATL (Atlanta Hartsfield), model aifs_single, lead day 0. 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/0/

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