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

San Francisco Intl · ECMWF AIFS Single · lead day 5

KSFO · 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 QC4.52 [3.76, 5.33]2.22-4.22 [-5.16, -3.21]5.11 [4.34, 5.81]8% [0%, 18%]16%28%-0.07+0.462026-08-06 → 2026-08-30
tmax00Zbilinear90d25 1 QC4.52 [3.60, 5.35]2.22-4.22 [-5.21, -3.04]5.11 [4.20, 5.85]8% [0%, 20%]16%28%-0.07+0.462026-08-06 → 2026-08-30
tmax00Zbilinear365d25 1 QC4.52 [3.59, 5.55]2.22-4.22 [-5.33, -3.01]5.11 [4.13, 5.99]8% [0%, 19%]16%28%-0.07+0.462026-08-06 → 2026-08-30
tmax00Zbilinearall25 1 QC4.52 [3.67, 5.42]2.22-4.22 [-5.26, -3.11]5.11 [4.22, 5.91]8% [0%, 20%]16%28%-0.07+0.462026-08-06 → 2026-08-30
tmax00Znearest30d25 1 QC2.62 [1.57, 3.74]2.43-0.57 [-1.73, 1.02]3.36 [2.13, 4.44]32% [11%, 58%]44%64%+0.38+0.402026-08-06 → 2026-08-30
tmax00Znearest90d25 1 QC2.62 [1.45, 3.90]2.43-0.57 [-1.82, 1.51]3.36 [2.03, 4.58]32% [7%, 61%]44%64%+0.38+0.402026-08-06 → 2026-08-30
tmax00Znearest365d25 1 QC2.62 [1.36, 4.03]2.43-0.57 [-1.90, 1.46]3.36 [1.97, 4.62]32% [6%, 65%]44%64%+0.38+0.402026-08-06 → 2026-08-30
tmax00Znearestall25 1 QC2.62 [1.51, 4.02]2.43-0.57 [-1.82, 1.38]3.36 [2.06, 4.67]32% [7%, 58%]44%64%+0.38+0.402026-08-06 → 2026-08-30
tmax12Zbilinear30d24 1 QC4.73 [3.73, 5.82]2.63-4.50 [-5.61, -3.40]5.47 [4.54, 6.34]12% [0%, 31%]21%38%-0.08+0.372026-08-06 → 2026-08-30
tmax12Zbilinear90d24 1 QC4.73 [3.47, 5.88]2.63-4.50 [-5.76, -3.17]5.47 [4.27, 6.42]12% [0%, 35%]21%38%-0.08+0.372026-08-06 → 2026-08-30
tmax12Zbilinear365d24 1 QC4.73 [3.51, 5.98]2.63-4.50 [-5.82, -3.16]5.47 [4.27, 6.49]12% [0%, 33%]21%38%-0.08+0.372026-08-06 → 2026-08-30
tmax12Zbilinearall24 1 QC4.73 [3.62, 5.92]2.63-4.50 [-5.79, -3.28]5.47 [4.41, 6.49]12% [0%, 34%]21%38%-0.08+0.372026-08-06 → 2026-08-30
tmax12Znearest30d24 1 QC3.06 [2.12, 4.03]2.85-0.87 [-2.22, 0.76]3.59 [2.68, 4.44]17% [0%, 36%]38%50%+0.30+0.312026-08-06 → 2026-08-30
tmax12Znearest90d24 1 QC3.06 [2.02, 4.19]2.85-0.87 [-2.33, 1.27]3.59 [2.56, 4.55]17% [0%, 38%]38%50%+0.30+0.312026-08-06 → 2026-08-30
tmax12Znearest365d24 1 QC3.06 [1.86, 4.23]2.85-0.87 [-2.43, 1.24]3.59 [2.42, 4.63]17% [0%, 43%]38%50%+0.30+0.312026-08-06 → 2026-08-30
tmax12Znearestall24 1 QC3.06 [2.12, 4.23]2.85-0.87 [-2.36, 1.20]3.59 [2.65, 4.65]17% [0%, 43%]38%50%+0.30+0.312026-08-06 → 2026-08-30
tmin00Zbilinear30d25 1 QC1.36 [1.04, 1.66]1.18-0.60 [-1.24, 0.12]1.56 [1.22, 1.82]32% [14%, 48%]76%100%-0.21-0.032026-08-06 → 2026-08-30
tmin00Zbilinear90d25 1 QC1.36 [0.99, 1.69]1.18-0.60 [-1.27, 0.20]1.56 [1.15, 1.83]32% [12%, 50%]76%100%-0.21-0.032026-08-06 → 2026-08-30
tmin00Zbilinear365d25 1 QC1.36 [1.01, 1.68]1.18-0.60 [-1.31, 0.31]1.56 [1.15, 1.85]32% [12%, 50%]76%100%-0.21-0.032026-08-06 → 2026-08-30
tmin00Zbilinearall25 1 QC1.36 [1.02, 1.69]1.18-0.60 [-1.35, 0.16]1.56 [1.13, 1.85]32% [12%, 50%]76%100%-0.21-0.032026-08-06 → 2026-08-30
tmin00Znearest30d25 1 QC1.46 [1.04, 1.88]1.40-0.23 [-1.02, 0.62]1.70 [1.27, 2.10]36% [17%, 59%]68%96%-0.31-0.222026-08-06 → 2026-08-30
tmin00Znearest90d25 1 QC1.46 [0.93, 1.94]1.40-0.23 [-1.05, 0.68]1.70 [1.15, 2.15]36% [17%, 65%]68%96%-0.31-0.222026-08-06 → 2026-08-30
tmin00Znearest365d25 1 QC1.46 [0.93, 1.96]1.40-0.23 [-1.08, 0.67]1.70 [1.15, 2.20]36% [17%, 62%]68%96%-0.31-0.222026-08-06 → 2026-08-30
tmin00Znearestall25 1 QC1.46 [0.93, 1.94]1.40-0.23 [-1.13, 0.66]1.70 [1.13, 2.15]36% [14%, 67%]68%96%-0.31-0.222026-08-06 → 2026-08-30
tmin12Zbilinear30d24 1 QC1.37 [1.17, 1.57]1.01-0.97 [-1.47, -0.38]1.57 [1.37, 1.77]29% [13%, 43%]79%100%-0.22+0.122026-08-06 → 2026-08-30
tmin12Zbilinear90d24 1 QC1.37 [1.16, 1.58]1.01-0.97 [-1.52, -0.34]1.57 [1.35, 1.78]29% [11%, 45%]79%100%-0.22+0.122026-08-06 → 2026-08-30
tmin12Zbilinear365d24 1 QC1.37 [1.17, 1.59]1.01-0.97 [-1.48, -0.19]1.57 [1.34, 1.78]29% [10%, 46%]79%100%-0.22+0.122026-08-06 → 2026-08-30
tmin12Zbilinearall24 1 QC1.37 [1.18, 1.60]1.01-0.97 [-1.56, -0.35]1.57 [1.36, 1.82]29% [8%, 45%]79%100%-0.22+0.122026-08-06 → 2026-08-30
tmin12Znearest30d24 1 QC1.34 [0.98, 1.62]1.17-0.64 [-1.19, -0.02]1.55 [1.23, 1.76]38% [24%, 50%]75%100%-0.19-0.022026-08-06 → 2026-08-30
tmin12Znearest90d24 1 QC1.34 [0.86, 1.65]1.17-0.64 [-1.20, 0.05]1.55 [1.06, 1.79]38% [23%, 54%]75%100%-0.19-0.022026-08-06 → 2026-08-30
tmin12Znearest365d24 1 QC1.34 [0.90, 1.63]1.17-0.64 [-1.22, 0.04]1.55 [1.12, 1.77]38% [23%, 54%]75%100%-0.19-0.022026-08-06 → 2026-08-30
tmin12Znearestall24 1 QC1.34 [0.90, 1.65]1.17-0.64 [-1.25, 0.02]1.55 [1.11, 1.77]38% [22%, 54%]75%100%-0.19-0.022026-08-06 → 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 KSFO, lead day 5, 00Z bilinear tmax+10+50-5-102026-08-06: -5.51 °F2026-08-07: -0.74 °F2026-08-08: +2.27 °F2026-08-09: -1.32 °F2026-08-10: -5.85 °F2026-08-11: -9.77 °F2026-08-12: -6.63 °F2026-08-13: -6.27 °F2026-08-14: -5.37 °F2026-08-15: -4.32 °F2026-08-16: -4.29 °F2026-08-17: -4.84 °F2026-08-18: -4.74 °F2026-08-19: -2.78 °F2026-08-20: -2.9 °F2026-08-21: -3.07 °F2026-08-22: -3.09 °F2026-08-23: -8.98 °F2026-08-24: -6.09 °F2026-08-25: +0.07 °F2026-08-26: -4.57 °F2026-08-27: -5.41 °F2026-08-28: +1.31 °F2026-08-29: -5 °F2026-08-30: -7.71 °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
2026-08-30-7.71
2026-08-29-5.00
2026-08-28+1.31
2026-08-27-5.41
2026-08-26-4.57
2026-08-25+0.07
2026-08-24-6.09
2026-08-23-8.98
2026-08-22-3.09
2026-08-21-3.07
2026-08-20-2.90
2026-08-19-2.78
2026-08-18-4.74
2026-08-17-4.84
2026-08-16-4.29
2026-08-15-4.32
2026-08-14-5.37
2026-08-13-6.27
2026-08-12-6.63
2026-08-11-9.77
2026-08-10-5.85
2026-08-09-1.32
2026-08-08+2.27
2026-08-07-0.74
2026-08-06-5.51

Error distribution

Distribution of the signed daily error in °F for ECMWF AIFS Single at KSFO, lead day 5-10 to -9 °F: 1 day-9 to -8 °F: 1 day-8 to -7 °F: 1 day-7 to -6 °F: 3 days-6 to -5 °F: 5 days-5 to -4 °F: 5 days-4 to -3 °F: 2 days-3 to -2 °F: 2 days-2 to -1 °F: 1 day-1 to 0 °F: 1 day0 to 1 °F: 1 day1 to 2 °F: 1 day2 to 3 °F: 1 day3 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| 4.74 · P90 |e| 7.28 °F-100+10 °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
-10.00-9.001
-9.00-8.001
-8.00-7.001
-7.00-6.003
-6.00-5.005
-5.00-4.005
-4.00-3.002
-3.00-2.002
-2.00-1.001
-1.00+0.001
+0.00+1.001
+1.00+2.001
+2.00+3.001
+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
2026-08254.52 -4.22

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 -0.18 [-1.43, 0.81] no
GraphCast (IFS init) 25 -1.04 [-1.50, -0.65] yes
ECMWF IFS HRES 18 -1.54 [-2.72, 0.86] no
Persistence (baseline) 25 +0.28 [-2.08, 1.97] no

Cite this page

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

LongCastCheck (2026). Station-level verification of raw weather-model 2 m temperature forecasts: KSFO (San Francisco Intl), 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/KSFO/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