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 5

KATL · aifs_single · lead 5

Target day = initialization date + 5 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
tmax00Zbilinear30d25 1 QC4.77 [3.73, 5.72]1.73-4.77 [-5.72, -3.73]5.26 [4.02, 6.20]0% [0%, 0%]12%24%-0.47+0.462026-08-06 → 2026-08-30
tmax00Zbilinear90d25 1 QC4.77 [3.62, 5.81]1.73-4.77 [-5.81, -3.62]5.26 [3.88, 6.27]0% [0%, 0%]12%24%-0.47+0.462026-08-06 → 2026-08-30
tmax00Zbilinear365d25 1 QC4.77 [3.50, 5.80]1.73-4.77 [-5.80, -3.50]5.26 [3.76, 6.22]0% [0%, 0%]12%24%-0.47+0.462026-08-06 → 2026-08-30
tmax00Zbilinearall25 1 QC4.77 [3.59, 5.81]1.73-4.77 [-5.81, -3.59]5.26 [3.85, 6.22]0% [0%, 0%]12%24%-0.47+0.462026-08-06 → 2026-08-30
tmax00Znearest30d25 1 QC4.91 [3.85, 5.89]1.79-4.91 [-5.89, -3.85]5.41 [4.09, 6.38]0% [0%, 0%]8%24%-0.52+0.442026-08-06 → 2026-08-30
tmax00Znearest90d25 1 QC4.91 [3.74, 5.99]1.79-4.91 [-5.99, -3.74]5.41 [3.96, 6.45]0% [0%, 0%]8%24%-0.52+0.442026-08-06 → 2026-08-30
tmax00Znearest365d25 1 QC4.91 [3.63, 5.98]1.79-4.91 [-5.98, -3.63]5.41 [3.86, 6.41]0% [0%, 0%]8%24%-0.52+0.442026-08-06 → 2026-08-30
tmax00Znearestall25 1 QC4.91 [3.72, 5.96]1.79-4.91 [-5.96, -3.72]5.41 [3.89, 6.41]0% [0%, 0%]8%24%-0.52+0.442026-08-06 → 2026-08-30
tmax12Zbilinear30d24 1 QC4.40 [3.65, 5.20]1.29-4.40 [-5.20, -3.65]4.70 [3.85, 5.51]0% [0%, 0%]4%17%-0.37+0.602026-08-06 → 2026-08-30
tmax12Zbilinear90d24 1 QC4.40 [3.57, 5.27]1.29-4.40 [-5.27, -3.57]4.70 [3.74, 5.60]0% [0%, 0%]4%17%-0.37+0.602026-08-06 → 2026-08-30
tmax12Zbilinear365d24 1 QC4.40 [3.46, 5.27]1.29-4.40 [-5.27, -3.46]4.70 [3.62, 5.61]0% [0%, 0%]4%17%-0.37+0.602026-08-06 → 2026-08-30
tmax12Zbilinearall24 1 QC4.40 [3.49, 5.26]1.29-4.40 [-5.26, -3.49]4.70 [3.66, 5.59]0% [0%, 0%]4%17%-0.37+0.602026-08-06 → 2026-08-30
tmax12Znearest30d24 1 QC4.52 [3.76, 5.33]1.32-4.52 [-5.33, -3.76]4.81 [3.95, 5.60]0% [0%, 0%]4%12%-0.41+0.592026-08-06 → 2026-08-30
tmax12Znearest90d24 1 QC4.52 [3.68, 5.37]1.32-4.52 [-5.37, -3.68]4.81 [3.85, 5.67]0% [0%, 0%]4%12%-0.41+0.592026-08-06 → 2026-08-30
tmax12Znearest365d24 1 QC4.52 [3.57, 5.37]1.32-4.52 [-5.37, -3.57]4.81 [3.71, 5.68]0% [0%, 0%]4%12%-0.41+0.592026-08-06 → 2026-08-30
tmax12Znearestall24 1 QC4.52 [3.62, 5.40]1.32-4.52 [-5.40, -3.62]4.81 [3.77, 5.67]0% [0%, 0%]4%12%-0.41+0.592026-08-06 → 2026-08-30
tmin00Zbilinear30d25 1 QC1.94 [1.33, 2.43]1.96-0.14 [-1.11, 0.71]2.49 [1.70, 3.00]32% [13%, 48%]68%88%+0.18+0.172026-08-06 → 2026-08-30
tmin00Zbilinear90d25 1 QC1.94 [1.11, 2.40]1.96-0.14 [-1.20, 0.78]2.49 [1.30, 2.99]32% [12%, 54%]68%88%+0.18+0.172026-08-06 → 2026-08-30
tmin00Zbilinear365d25 1 QC1.94 [1.04, 2.41]1.96-0.14 [-1.33, 0.79]2.49 [1.25, 3.00]32% [11%, 56%]68%88%+0.18+0.172026-08-06 → 2026-08-30
tmin00Zbilinearall25 1 QC1.94 [1.05, 2.47]1.96-0.14 [-1.40, 0.76]2.49 [1.28, 3.06]32% [10%, 52%]68%88%+0.18+0.172026-08-06 → 2026-08-30
tmin00Znearest30d25 1 QC1.93 [1.32, 2.41]1.95-0.23 [-1.19, 0.63]2.50 [1.67, 3.01]28% [12%, 43%]64%84%+0.18+0.182026-08-06 → 2026-08-30
tmin00Znearest90d25 1 QC1.93 [1.11, 2.39]1.95-0.23 [-1.29, 0.70]2.50 [1.31, 3.03]28% [12%, 45%]64%84%+0.18+0.182026-08-06 → 2026-08-30
tmin00Znearest365d25 1 QC1.93 [1.04, 2.38]1.95-0.23 [-1.45, 0.70]2.50 [1.26, 3.05]28% [11%, 50%]64%84%+0.18+0.182026-08-06 → 2026-08-30
tmin00Znearestall25 1 QC1.93 [1.06, 2.45]1.95-0.23 [-1.48, 0.67]2.50 [1.29, 3.12]28% [10%, 44%]64%84%+0.18+0.182026-08-06 → 2026-08-30
tmin12Zbilinear30d24 1 QC1.96 [1.35, 2.38]1.97-0.11 [-1.21, 0.89]2.39 [1.68, 2.81]33% [21%, 47%]58%79%+0.16+0.162026-08-06 → 2026-08-30
tmin12Zbilinear90d24 1 QC1.96 [1.13, 2.37]1.97-0.11 [-1.30, 1.05]2.39 [1.30, 2.82]33% [21%, 50%]58%79%+0.16+0.162026-08-06 → 2026-08-30
tmin12Zbilinear365d24 1 QC1.96 [1.12, 2.35]1.97-0.11 [-1.48, 1.06]2.39 [1.33, 2.81]33% [21%, 52%]58%79%+0.16+0.162026-08-06 → 2026-08-30
tmin12Zbilinearall24 1 QC1.96 [1.16, 2.42]1.97-0.11 [-1.53, 1.04]2.39 [1.33, 2.87]33% [19%, 50%]58%79%+0.16+0.162026-08-06 → 2026-08-30
tmin12Znearest30d24 1 QC1.95 [1.30, 2.37]1.96-0.18 [-1.26, 0.82]2.39 [1.65, 2.83]29% [20%, 41%]58%79%+0.17+0.162026-08-06 → 2026-08-30
tmin12Znearest90d24 1 QC1.95 [1.17, 2.37]1.96-0.18 [-1.37, 0.98]2.39 [1.31, 2.83]29% [18%, 42%]58%79%+0.17+0.162026-08-06 → 2026-08-30
tmin12Znearest365d24 1 QC1.95 [1.17, 2.36]1.96-0.18 [-1.56, 1.00]2.39 [1.34, 2.83]29% [19%, 43%]58%79%+0.17+0.162026-08-06 → 2026-08-30
tmin12Znearestall24 1 QC1.95 [1.15, 2.43]1.96-0.18 [-1.61, 0.97]2.39 [1.32, 2.90]29% [17%, 43%]58%79%+0.17+0.162026-08-06 → 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 5, 00Z bilinear tmax+20+100-10-202026-08-06: -5.3 °F2026-08-07: -1.88 °F2026-08-08: -5.19 °F2026-08-09: -6.07 °F2026-08-10: -8.58 °F2026-08-11: -7.44 °F2026-08-12: -6.09 °F2026-08-13: -5.93 °F2026-08-14: -3.44 °F2026-08-15: -2.64 °F2026-08-16: -5.42 °F2026-08-17: -2.44 °F2026-08-18: -1.45 °F2026-08-19: -4.22 °F2026-08-20: -4.66 °F2026-08-21: -2.62 °F2026-08-22: -1.9 °F2026-08-23: -4.57 °F2026-08-24: -4.24 °F2026-08-25: -5.88 °F2026-08-26: -3.17 °F2026-08-27: -11.01 °F2026-08-28: -7.21 °F2026-08-29: -3.37 °F2026-08-30: -4.47 °F2026-08-062026-08-30°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 (25 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-4.47
2026-08-29-3.37
2026-08-28-7.21
2026-08-27-11.01
2026-08-26-3.17
2026-08-25-5.88
2026-08-24-4.24
2026-08-23-4.57
2026-08-22-1.90
2026-08-21-2.62
2026-08-20-4.66
2026-08-19-4.22
2026-08-18-1.45
2026-08-17-2.44
2026-08-16-5.42
2026-08-15-2.64
2026-08-14-3.44
2026-08-13-5.93
2026-08-12-6.09
2026-08-11-7.44
2026-08-10-8.58
2026-08-09-6.07
2026-08-08-5.19
2026-08-07-1.88
2026-08-06-5.30

Error distribution

Distribution of the signed daily error in °F for ECMWF AIFS Single at KATL, lead day 5-20 to -18 °F: 0 days-18 to -16 °F: 0 days-16 to -14 °F: 0 days-14 to -12 °F: 0 days-12 to -10 °F: 1 day-10 to -8 °F: 1 day-8 to -6 °F: 4 days-6 to -4 °F: 10 days-4 to -2 °F: 6 days-2 to 0 °F: 3 days0 to 2 °F: 0 days2 to 4 °F: 0 days4 to 6 °F: 0 days6 to 8 °F: 0 days8 to 10 °F: 0 days10 to 12 °F: 0 days12 to 14 °F: 0 days14 to 16 °F: 0 days16 to 18 °F: 0 days18 to 20 °F: 0 daysdashed: P50 |e| 4.57 · P90 |e| 7.34 °F-200+20 °Fn = 25 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
-20.00-18.000
-18.00-16.000
-16.00-14.000
-14.00-12.000
-12.00-10.001
-10.00-8.001
-8.00-6.004
-6.00-4.0010
-4.00-2.006
-2.00+0.003
+0.00+2.000
+2.00+4.000
+4.00+6.000
+6.00+8.000
+8.00+10.000
+10.00+12.000
+12.00+14.000
+14.00+16.000
+16.00+18.000
+18.00+20.000

Month by month

00Z bilinear daily maximum, newest first.

Monthn MAE °FBias °F
2026-08254.77 -4.77

Availability

ModelScored period DaysCoverage
ECMWF AIFS Single2026-08-06 → 2026-08-30 25
ECMWF AIFS Single2026-08-06 → 2026-08-30 25
ECMWF AIFS Single2026-08-06 → 2026-08-30 24
ECMWF AIFS Single2026-08-06 → 2026-08-30 24

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 25 +0.75 [-1.06, 3.08] no
GraphCast (IFS init) 25 -0.27 [-1.70, 0.75] no
ECMWF IFS HRES 18 +1.03 [0.01, 2.50] yes
Persistence (baseline) 25 +1.53 [0.59, 2.50] yes

Cite this page

ShortCastCheck, KATL aifs_single lead 5, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KATL/model/aifs_single/lead/5/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KATL (Atlanta Hartsfield), model aifs_single, lead day 5. 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/5/

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