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

Austin Bergstrom · FourCastNet v2 (IFS init) · lead day 0

KAUS · fourcastnet_ifs · 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, FOUR_v200, 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
tmax00Zbilinear30d3 1 QC6.26 [4.28, 7.32]1.32-6.26 [-7.32, -4.28]6.41 [4.28, 7.32]0% [0%, 0%]0%0%——2026-08-28 → 2026-08-30
tmax00Zbilinear90d3 1 QC6.26 [4.28, 7.32]1.32-6.26 [-7.32, -4.28]6.41 [4.28, 7.32]0% [0%, 0%]0%0%——2026-08-28 → 2026-08-30
tmax00Zbilinear365d3 1 QC6.26 [4.28, 7.32]1.32-6.26 [-7.32, -4.28]6.41 [4.28, 7.32]0% [0%, 0%]0%0%——2026-08-28 → 2026-08-30
tmax00Zbilinearall3 1 QC6.26 [4.28, 7.32]1.32-6.26 [-7.32, -4.28]6.41 [4.28, 7.32]0% [0%, 0%]0%0%——2026-08-28 → 2026-08-30
tmax00Znearest30d3 1 QC6.10 [4.17, 7.30]1.29-6.10 [-7.30, -4.17]6.26 [4.17, 7.30]0% [0%, 0%]0%0%——2026-08-28 → 2026-08-30
tmax00Znearest90d3 1 QC6.10 [4.17, 7.30]1.29-6.10 [-7.30, -4.17]6.26 [4.17, 7.30]0% [0%, 0%]0%0%——2026-08-28 → 2026-08-30
tmax00Znearest365d3 1 QC6.10 [4.17, 7.30]1.29-6.10 [-7.30, -4.17]6.26 [4.17, 7.30]0% [0%, 0%]0%0%——2026-08-28 → 2026-08-30
tmax00Znearestall3 1 QC6.10 [4.17, 7.30]1.29-6.10 [-7.30, -4.17]6.26 [4.17, 7.30]0% [0%, 0%]0%0%——2026-08-28 → 2026-08-30
tmin00Zbilinear30d3 1 QC2.00 [1.00, 3.76]2.17+0.50 [-1.13, 3.76]2.36 [1.00, 3.76]0% [0%, 0%]67%67%——2026-08-28 → 2026-08-30
tmin00Zbilinear90d3 1 QC2.00 [1.00, 3.76]2.17+0.50 [-1.13, 3.76]2.36 [1.00, 3.76]0% [0%, 0%]67%67%——2026-08-28 → 2026-08-30
tmin00Zbilinear365d3 1 QC2.00 [1.00, 3.76]2.17+0.50 [-1.13, 3.76]2.36 [1.00, 3.76]0% [0%, 0%]67%67%——2026-08-28 → 2026-08-30
tmin00Zbilinearall3 1 QC2.00 [1.00, 3.76]2.17+0.50 [-1.13, 3.76]2.36 [1.00, 3.76]0% [0%, 0%]67%67%——2026-08-28 → 2026-08-30
tmin00Znearest30d3 1 QC1.65 [0.71, 3.53]1.89+0.70 [-1.07, 3.53]2.14 [0.80, 3.53]33% [0%, 50%]67%67%——2026-08-28 → 2026-08-30
tmin00Znearest90d3 1 QC1.65 [0.71, 3.53]1.89+0.70 [-1.07, 3.53]2.14 [0.80, 3.53]33% [0%, 50%]67%67%——2026-08-28 → 2026-08-30
tmin00Znearest365d3 1 QC1.65 [0.71, 3.53]1.89+0.70 [-1.07, 3.53]2.14 [0.80, 3.53]33% [0%, 50%]67%67%——2026-08-28 → 2026-08-30
tmin00Znearestall3 1 QC1.65 [0.71, 3.53]1.89+0.70 [-1.07, 3.53]2.14 [0.80, 3.53]33% [0%, 50%]67%67%——2026-08-28 → 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 FourCastNet v2 (IFS init) at KAUS, lead day 0, 00Z bilinear tmax+10+50-5-102026-08-28: -7.32 °F2026-08-29: -7.17 °F2026-08-30: -4.28 °F2026-08-282026-08-30°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 (3 days, newest first) · download CSV
Climatological dayError °F
2026-08-30-4.28
2026-08-29-7.17
2026-08-28-7.32

Error distribution

Distribution of the signed daily error in °F for FourCastNet v2 (IFS init) at KAUS, lead day 0-10 to -9 °F: 0 days-9 to -8 °F: 0 days-8 to -7 °F: 2 days-7 to -6 °F: 0 days-6 to -5 °F: 0 days-5 to -4 °F: 1 day-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| 7.17 · P90 |e| 7.29 °F-100+10 °Fn = 3 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
-8.00-7.002
-7.00-6.000
-6.00-5.000
-5.00-4.001
-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
2026-0836.26 -6.26

Availability

ModelScored period DaysCoverage
FourCastNet v2 (IFS init)2026-08-28 → 2026-08-30 3
FourCastNet v2 (IFS init)2026-08-28 → 2026-08-30 3

Compared with other models

Paired bootstrap on the days both models cover (90d, 00Z, bilinear, daily maximum). Negative means FourCastNet v2 (IFS init) has the lower MAE. "Distinguishable" means the 95 % interval excludes zero.

Other modelCommon days MAE difference °FDistinguishable
ECMWF AIFS Single 3 +1.48 [0.34, 2.05] yes
Aurora (GFS init) 2 -1.68 [-2.45, -0.92] yes
Aurora (IFS init) 3 -2.34 [-2.75, -1.50] yes
FourCastNet v2 (GFS init) 2 +0.53 [-0.32, 1.37] no
NCEP GFS 3 +3.08 [1.98, 3.62] yes
GraphCast (GFS init) 2 -1.21 [-2.47, 0.06] no
GraphCast (IFS init) 3 -2.73 [-3.19, -1.79] yes
ECMWF IFS HRES 3 +1.01 [-0.19, 2.32] no
Pangu-Weather (GFS init) 2 +2.14 [0.31, 3.97] yes
Pangu-Weather (IFS init) 3 +1.14 [-0.43, 2.24] no

Cite this page

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

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KAUS (Austin Bergstrom), model fourcastnet_ifs, 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/KAUS/model/fourcastnet_ifs/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