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 · GraphCast (GFS init) · lead day 1

KATL · graphcast_gfs · lead 1

Target day = initialization date + 1 day. 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, GRAP_v100, starting 2026-08-28 — 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
tmax00Zbilinear30d1 1 QC6.18 [6.18, 6.18]0.00-6.18 [-6.18, -6.18]6.18 [6.18, 6.18]0% [0%, 0%]0%0%-5.18—2026-08-30 → 2026-08-30
tmax00Zbilinear90d1 1 QC6.18 [6.18, 6.18]0.00-6.18 [-6.18, -6.18]6.18 [6.18, 6.18]0% [0%, 0%]0%0%-5.18—2026-08-30 → 2026-08-30
tmax00Zbilinear365d1 1 QC6.18 [6.18, 6.18]0.00-6.18 [-6.18, -6.18]6.18 [6.18, 6.18]0% [0%, 0%]0%0%-5.18—2026-08-30 → 2026-08-30
tmax00Zbilinearall1 1 QC6.18 [6.18, 6.18]0.00-6.18 [-6.18, -6.18]6.18 [6.18, 6.18]0% [0%, 0%]0%0%-5.18—2026-08-30 → 2026-08-30
tmax00Znearest30d1 1 QC6.06 [6.06, 6.06]0.00-6.06 [-6.06, -6.06]6.06 [6.06, 6.06]0% [0%, 0%]0%0%-5.06—2026-08-30 → 2026-08-30
tmax00Znearest90d1 1 QC6.06 [6.06, 6.06]0.00-6.06 [-6.06, -6.06]6.06 [6.06, 6.06]0% [0%, 0%]0%0%-5.06—2026-08-30 → 2026-08-30
tmax00Znearest365d1 1 QC6.06 [6.06, 6.06]0.00-6.06 [-6.06, -6.06]6.06 [6.06, 6.06]0% [0%, 0%]0%0%-5.06—2026-08-30 → 2026-08-30
tmax00Znearestall1 1 QC6.06 [6.06, 6.06]0.00-6.06 [-6.06, -6.06]6.06 [6.06, 6.06]0% [0%, 0%]0%0%-5.06—2026-08-30 → 2026-08-30
tmax12Zbilinear30d2 1 QC4.97 [4.61, 5.33]0.36-4.97 [-5.33, -4.61]4.98 [4.61, 5.33]0% [0%, 0%]0%0%-0.99+0.862026-08-29 → 2026-08-30
tmax12Zbilinear90d2 1 QC4.97 [4.61, 5.33]0.36-4.97 [-5.33, -4.61]4.98 [4.61, 5.33]0% [0%, 0%]0%0%-0.99+0.862026-08-29 → 2026-08-30
tmax12Zbilinear365d2 1 QC4.97 [4.61, 5.33]0.36-4.97 [-5.33, -4.61]4.98 [4.61, 5.33]0% [0%, 0%]0%0%-0.99+0.862026-08-29 → 2026-08-30
tmax12Zbilinearall2 1 QC4.97 [4.61, 5.33]0.36-4.97 [-5.33, -4.61]4.98 [4.61, 5.33]0% [0%, 0%]0%0%-0.99+0.862026-08-29 → 2026-08-30
tmax12Znearest30d2 1 QC4.83 [4.48, 5.18]0.35-4.83 [-5.18, -4.48]4.84 [4.48, 5.18]0% [0%, 0%]0%0%-0.93+0.862026-08-29 → 2026-08-30
tmax12Znearest90d2 1 QC4.83 [4.48, 5.18]0.35-4.83 [-5.18, -4.48]4.84 [4.48, 5.18]0% [0%, 0%]0%0%-0.93+0.862026-08-29 → 2026-08-30
tmax12Znearest365d2 1 QC4.83 [4.48, 5.18]0.35-4.83 [-5.18, -4.48]4.84 [4.48, 5.18]0% [0%, 0%]0%0%-0.93+0.862026-08-29 → 2026-08-30
tmax12Znearestall2 1 QC4.83 [4.48, 5.18]0.35-4.83 [-5.18, -4.48]4.84 [4.48, 5.18]0% [0%, 0%]0%0%-0.93+0.862026-08-29 → 2026-08-30
tmin00Zbilinear30d1 1 QC0.62 [0.62, 0.62]0.00-0.62 [-0.62, -0.62]0.62 [0.62, 0.62]100% [100%, 100%]100%100%+0.38—2026-08-30 → 2026-08-30
tmin00Zbilinear90d1 1 QC0.62 [0.62, 0.62]0.00-0.62 [-0.62, -0.62]0.62 [0.62, 0.62]100% [100%, 100%]100%100%+0.38—2026-08-30 → 2026-08-30
tmin00Zbilinear365d1 1 QC0.62 [0.62, 0.62]0.00-0.62 [-0.62, -0.62]0.62 [0.62, 0.62]100% [100%, 100%]100%100%+0.38—2026-08-30 → 2026-08-30
tmin00Zbilinearall1 1 QC0.62 [0.62, 0.62]0.00-0.62 [-0.62, -0.62]0.62 [0.62, 0.62]100% [100%, 100%]100%100%+0.38—2026-08-30 → 2026-08-30
tmin00Znearest30d1 1 QC0.58 [0.58, 0.58]0.00-0.58 [-0.58, -0.58]0.58 [0.58, 0.58]100% [100%, 100%]100%100%+0.42—2026-08-30 → 2026-08-30
tmin00Znearest90d1 1 QC0.58 [0.58, 0.58]0.00-0.58 [-0.58, -0.58]0.58 [0.58, 0.58]100% [100%, 100%]100%100%+0.42—2026-08-30 → 2026-08-30
tmin00Znearest365d1 1 QC0.58 [0.58, 0.58]0.00-0.58 [-0.58, -0.58]0.58 [0.58, 0.58]100% [100%, 100%]100%100%+0.42—2026-08-30 → 2026-08-30
tmin00Znearestall1 1 QC0.58 [0.58, 0.58]0.00-0.58 [-0.58, -0.58]0.58 [0.58, 0.58]100% [100%, 100%]100%100%+0.42—2026-08-30 → 2026-08-30
tmin12Zbilinear30d2 1 QC0.97 [0.55, 1.38]0.41-0.97 [-1.38, -0.55]1.05 [0.55, 1.38]50% [0%, 100%]100%100%+0.03+0.592026-08-29 → 2026-08-30
tmin12Zbilinear90d2 1 QC0.97 [0.55, 1.38]0.41-0.97 [-1.38, -0.55]1.05 [0.55, 1.38]50% [0%, 100%]100%100%+0.03+0.592026-08-29 → 2026-08-30
tmin12Zbilinear365d2 1 QC0.97 [0.55, 1.38]0.41-0.97 [-1.38, -0.55]1.05 [0.55, 1.38]50% [0%, 100%]100%100%+0.03+0.592026-08-29 → 2026-08-30
tmin12Zbilinearall2 1 QC0.97 [0.55, 1.38]0.41-0.97 [-1.38, -0.55]1.05 [0.55, 1.38]50% [0%, 100%]100%100%+0.03+0.592026-08-29 → 2026-08-30
tmin12Znearest30d2 1 QC0.87 [0.44, 1.29]0.43-0.87 [-1.29, -0.44]0.97 [0.44, 1.29]50% [0%, 100%]100%100%+0.13+0.572026-08-29 → 2026-08-30
tmin12Znearest90d2 1 QC0.87 [0.44, 1.29]0.43-0.87 [-1.29, -0.44]0.97 [0.44, 1.29]50% [0%, 100%]100%100%+0.13+0.572026-08-29 → 2026-08-30
tmin12Znearest365d2 1 QC0.87 [0.44, 1.29]0.43-0.87 [-1.29, -0.44]0.97 [0.44, 1.29]50% [0%, 100%]100%100%+0.13+0.572026-08-29 → 2026-08-30
tmin12Znearestall2 1 QC0.87 [0.44, 1.29]0.43-0.87 [-1.29, -0.44]0.97 [0.44, 1.29]50% [0%, 100%]100%100%+0.13+0.572026-08-29 → 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 GraphCast (GFS init) at KATL, lead day 1, 00Z bilinear tmax+10+50-5-102026-08-30: -6.18 °F2026-08-30°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 (1 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-6.18

Error distribution

Distribution of the signed daily error in °F for GraphCast (GFS init) at KATL, lead day 1-10 to -9 °F: 0 days-9 to -8 °F: 0 days-8 to -7 °F: 0 days-7 to -6 °F: 1 day-6 to -5 °F: 0 days-5 to -4 °F: 0 days-4 to -3 °F: 0 days-3 to -2 °F: 0 days-2 to -1 °F: 0 days-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| 6.18 · P90 |e| 6.18 °F-100+10 °Fn = 1 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
-8.00-7.000
-7.00-6.001
-6.00-5.000
-5.00-4.000
-4.00-3.000
-3.00-2.000
-2.00-1.000
-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
2026-0816.18 -6.18

Availability

ModelScored period DaysCoverage
GraphCast (GFS init)2026-08-30 → 2026-08-30 1
GraphCast (GFS init)2026-08-30 → 2026-08-30 1
GraphCast (GFS init)2026-08-29 → 2026-08-30 2
GraphCast (GFS init)2026-08-29 → 2026-08-30 2

Compared with other models

Paired bootstrap on the days both models cover (90d, 00Z, bilinear, daily maximum). Negative means GraphCast (GFS init) has the lower MAE. "Distinguishable" means the 95 % interval excludes zero.

Other modelCommon days MAE difference °FDistinguishable
ECMWF AIFS Single 1 +2.35 [2.35, 2.35] yes
Aurora (GFS init) 1 -0.92 [-0.92, -0.92] yes
Aurora (IFS init) 1 -0.00 [-0.00, -0.00] yes
FourCastNet v2 (GFS init) 1 +2.75 [2.75, 2.75] yes
FourCastNet v2 (IFS init) 1 +3.57 [3.57, 3.57] yes
NCEP GFS 1 +2.52 [2.52, 2.52] yes
GraphCast (IFS init) 1 +0.62 [0.62, 0.62] yes
ECMWF IFS HRES 1 +3.69 [3.69, 3.69] yes
Pangu-Weather (GFS init) 1 +2.20 [2.20, 2.20] yes
Pangu-Weather (IFS init) 1 +3.20 [3.20, 3.20] yes
Persistence (baseline) 1 +5.18 [5.18, 5.18] yes

Cite this page

ShortCastCheck, KATL graphcast_gfs lead 1, methodology v0.2, accessed 2026-08-31, https://castcheck.zifanzhang.com/station/KATL/model/graphcast_gfs/lead/1/

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KATL (Atlanta Hartsfield), model graphcast_gfs, lead day 1. Methodology version 0.2, schema version 0.1, data through 2026-08-30. Accessed 2026-08-31. https://castcheck.zifanzhang.com/station/KATL/model/graphcast_gfs/lead/1/

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