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 7

KATL · aifs_single · lead 7

Target day = initialization date + 7 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
tmax00Zbilinear30d23 1 QC4.88 [3.59, 6.25]1.93-4.80 [-6.25, -3.42]5.38 [4.31, 6.48]13% [0%, 29%]17%22%-0.26+0.492026-08-08 → 2026-08-30
tmax00Zbilinear90d23 1 QC4.88 [3.55, 6.62]1.93-4.80 [-6.62, -3.40]5.38 [4.25, 6.78]13% [0%, 29%]17%22%-0.26+0.492026-08-08 → 2026-08-30
tmax00Zbilinear365d23 1 QC4.88 [3.31, 6.56]1.93-4.80 [-6.56, -3.13]5.38 [3.99, 6.65]13% [0%, 30%]17%22%-0.26+0.492026-08-08 → 2026-08-30
tmax00Zbilinearall23 1 QC4.88 [3.38, 6.48]1.93-4.80 [-6.48, -3.21]5.38 [4.08, 6.62]13% [0%, 30%]17%22%-0.26+0.492026-08-08 → 2026-08-30
tmax00Znearest30d23 1 QC4.93 [3.64, 6.31]1.89-4.89 [-6.31, -3.56]5.44 [4.39, 6.51]13% [0%, 29%]13%22%-0.27+0.502026-08-08 → 2026-08-30
tmax00Znearest90d23 1 QC4.93 [3.61, 6.62]1.89-4.89 [-6.62, -3.54]5.44 [4.33, 6.73]13% [0%, 29%]13%22%-0.27+0.502026-08-08 → 2026-08-30
tmax00Znearest365d23 1 QC4.93 [3.37, 6.58]1.89-4.89 [-6.58, -3.28]5.44 [4.09, 6.70]13% [0%, 30%]13%22%-0.27+0.502026-08-08 → 2026-08-30
tmax00Znearestall23 1 QC4.93 [3.44, 6.52]1.89-4.89 [-6.52, -3.35]5.44 [4.17, 6.65]13% [0%, 30%]13%22%-0.27+0.502026-08-08 → 2026-08-30
tmax12Zbilinear30d23 1 QC5.22 [4.42, 6.01]2.00-4.97 [-5.99, -3.81]5.64 [4.73, 6.33]0% [0%, 0%]0%17%-0.35+0.472026-08-08 → 2026-08-30
tmax12Zbilinear90d23 1 QC5.22 [4.33, 6.09]2.00-4.97 [-6.09, -3.77]5.64 [4.60, 6.43]0% [0%, 0%]0%17%-0.35+0.472026-08-08 → 2026-08-30
tmax12Zbilinear365d23 1 QC5.22 [4.29, 6.17]2.00-4.97 [-6.17, -3.68]5.64 [4.63, 6.42]0% [0%, 0%]0%17%-0.35+0.472026-08-08 → 2026-08-30
tmax12Zbilinearall23 1 QC5.22 [4.21, 6.20]2.00-4.97 [-6.20, -3.63]5.64 [4.50, 6.46]0% [0%, 0%]0%17%-0.35+0.472026-08-08 → 2026-08-30
tmax12Znearest30d23 1 QC5.30 [4.48, 6.11]1.99-5.07 [-6.10, -3.94]5.72 [4.79, 6.43]0% [0%, 0%]0%17%-0.37+0.472026-08-08 → 2026-08-30
tmax12Znearest90d23 1 QC5.30 [4.39, 6.19]1.99-5.07 [-6.19, -3.87]5.72 [4.63, 6.55]0% [0%, 0%]0%17%-0.37+0.472026-08-08 → 2026-08-30
tmax12Znearest365d23 1 QC5.30 [4.35, 6.32]1.99-5.07 [-6.32, -3.79]5.72 [4.67, 6.53]0% [0%, 0%]0%17%-0.37+0.472026-08-08 → 2026-08-30
tmax12Znearestall23 1 QC5.30 [4.28, 6.33]1.99-5.07 [-6.33, -3.71]5.72 [4.58, 6.59]0% [0%, 0%]0%17%-0.37+0.472026-08-08 → 2026-08-30
tmin00Zbilinear30d23 1 QC1.93 [1.20, 2.48]1.93-0.04 [-1.04, 0.90]2.49 [1.73, 2.92]35% [12%, 60%]65%78%+0.22+0.222026-08-08 → 2026-08-30
tmin00Zbilinear90d23 1 QC1.93 [0.85, 2.45]1.93-0.04 [-1.08, 0.84]2.49 [0.87, 2.86]35% [12%, 64%]65%78%+0.22+0.222026-08-08 → 2026-08-30
tmin00Zbilinear365d23 1 QC1.93 [0.84, 2.54]1.93-0.04 [-1.23, 0.92]2.49 [0.86, 2.92]35% [10%, 67%]65%78%+0.22+0.222026-08-08 → 2026-08-30
tmin00Zbilinearall23 1 QC1.93 [0.84, 2.52]1.93-0.04 [-1.24, 0.86]2.49 [0.86, 2.92]35% [9%, 67%]65%78%+0.22+0.222026-08-08 → 2026-08-30
tmin00Znearest30d23 1 QC1.94 [1.20, 2.50]1.93-0.11 [-1.13, 0.84]2.51 [1.72, 2.94]39% [12%, 68%]65%78%+0.22+0.222026-08-08 → 2026-08-30
tmin00Znearest90d23 1 QC1.94 [0.86, 2.46]1.93-0.11 [-1.18, 0.78]2.51 [0.92, 2.89]39% [12%, 72%]65%78%+0.22+0.222026-08-08 → 2026-08-30
tmin00Znearest365d23 1 QC1.94 [0.86, 2.55]1.93-0.11 [-1.34, 0.89]2.51 [0.90, 2.92]39% [10%, 75%]65%78%+0.22+0.222026-08-08 → 2026-08-30
tmin00Znearestall23 1 QC1.94 [0.85, 2.53]1.93-0.11 [-1.33, 0.82]2.51 [0.89, 2.94]39% [9%, 75%]65%78%+0.22+0.222026-08-08 → 2026-08-30
tmin12Zbilinear30d23 1 QC1.84 [1.18, 2.44]1.84+0.00 [-0.52, 0.58]2.20 [1.40, 2.78]22% [7%, 46%]70%83%+0.26+0.262026-08-08 → 2026-08-30
tmin12Zbilinear90d23 1 QC1.84 [1.08, 2.46]1.84+0.00 [-0.58, 0.51]2.20 [1.31, 2.78]22% [7%, 50%]70%83%+0.26+0.262026-08-08 → 2026-08-30
tmin12Zbilinear365d23 1 QC1.84 [1.08, 2.52]1.84+0.00 [-0.57, 0.53]2.20 [1.30, 2.83]22% [5%, 50%]70%83%+0.26+0.262026-08-08 → 2026-08-30
tmin12Zbilinearall23 1 QC1.84 [1.04, 2.50]1.84+0.00 [-0.62, 0.50]2.20 [1.27, 2.81]22% [5%, 50%]70%83%+0.26+0.262026-08-08 → 2026-08-30
tmin12Znearest30d23 1 QC1.83 [1.17, 2.44]1.83-0.09 [-0.62, 0.50]2.19 [1.42, 2.77]22% [7%, 46%]70%83%+0.26+0.262026-08-08 → 2026-08-30
tmin12Znearest90d23 1 QC1.83 [1.05, 2.45]1.83-0.09 [-0.68, 0.43]2.19 [1.33, 2.77]22% [7%, 50%]70%83%+0.26+0.262026-08-08 → 2026-08-30
tmin12Znearest365d23 1 QC1.83 [1.06, 2.50]1.83-0.09 [-0.67, 0.47]2.19 [1.32, 2.82]22% [5%, 50%]70%83%+0.26+0.262026-08-08 → 2026-08-30
tmin12Znearestall23 1 QC1.83 [1.04, 2.50]1.83-0.09 [-0.73, 0.42]2.19 [1.31, 2.80]22% [5%, 50%]70%83%+0.26+0.262026-08-08 → 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 7, 00Z bilinear tmax+10+50-5-102026-08-08: -6.79 °F2026-08-09: -7.71 °F2026-08-10: -7.73 °F2026-08-11: -6.48 °F2026-08-12: -6.15 °F2026-08-13: -6.15 °F2026-08-14: -5.07 °F2026-08-15: -4.54 °F2026-08-16: -3.49 °F2026-08-17: -4.89 °F2026-08-18: +0.6 °F2026-08-19: -0.25 °F2026-08-20: -4.27 °F2026-08-21: -2.84 °F2026-08-22: -7.32 °F2026-08-23: +0.36 °F2026-08-24: -4.66 °F2026-08-25: -6.36 °F2026-08-26: -5.18 °F2026-08-27: -6.05 °F2026-08-28: -6.42 °F2026-08-29: -7.01 °F2026-08-30: -1.97 °F2026-08-082026-08-30°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 (23 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-1.97
2026-08-29-7.01
2026-08-28-6.42
2026-08-27-6.05
2026-08-26-5.18
2026-08-25-6.36
2026-08-24-4.66
2026-08-23+0.36
2026-08-22-7.32
2026-08-21-2.84
2026-08-20-4.27
2026-08-19-0.25
2026-08-18+0.60
2026-08-17-4.89
2026-08-16-3.49
2026-08-15-4.54
2026-08-14-5.07
2026-08-13-6.15
2026-08-12-6.15
2026-08-11-6.48
2026-08-10-7.73
2026-08-09-7.71
2026-08-08-6.79

Error distribution

Distribution of the signed daily error in °F for ECMWF AIFS Single at KATL, lead day 7-10 to -9 °F: 0 days-9 to -8 °F: 0 days-8 to -7 °F: 4 days-7 to -6 °F: 7 days-6 to -5 °F: 2 days-5 to -4 °F: 4 days-4 to -3 °F: 1 day-3 to -2 °F: 1 day-2 to -1 °F: 1 day-1 to 0 °F: 1 day0 to 1 °F: 2 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| 5.18 · P90 |e| 7.26 °F-100+10 °Fn = 23 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
-8.00-7.004
-7.00-6.007
-6.00-5.002
-5.00-4.004
-4.00-3.001
-3.00-2.001
-2.00-1.001
-1.00+0.001
+0.00+1.002
+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
2026-08234.88 -4.80

Availability

ModelScored period DaysCoverage
ECMWF AIFS Single2026-08-08 → 2026-08-30 23
ECMWF AIFS Single2026-08-08 → 2026-08-30 23
ECMWF AIFS Single2026-08-08 → 2026-08-30 23
ECMWF AIFS Single2026-08-08 → 2026-08-30 23

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 23 +1.90 [-0.09, 4.51] no
GraphCast (IFS init) 23 -0.53 [-1.89, 0.43] no
ECMWF IFS HRES 18 +0.86 [0.08, 3.47] yes
Persistence (baseline) 23 +1.01 [0.25, 1.99] yes

Cite this page

ShortCastCheck, KATL aifs_single lead 7, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KATL/model/aifs_single/lead/7/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KATL (Atlanta Hartsfield), model aifs_single, lead day 7. 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/7/

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