WeatherBlend

Multi-model forecast blending for Bonehill Rocks, Dartmoor

Temperature models

2b (lean) + 2c (rich). MAE °C, lower better. Δ vs best single NWP — negative = blend wins.

Temperature — Bonehill Rocks

Phase 2c · v2026-08-02_135308_phase2c Δ +0.003 vs prev train

Rich blender, 88 features (adds dew/RH/cloud/wind/pressure). Trained 2026-08-02. Metric: Test MAE (°C).

Lead Blend Best single Δ vs best
+24h 0.586 temp_aifs (0.665) -11.8%
+48h 0.665 temp_aifs (0.709) -6.2%
+72h 0.768 temp_aifs (0.794) -3.2%
+96h 0.924 temp_aifs (0.924) 0.0%
+120h 1.156 temp_aifs (1.066) +8.4%
Verify history (29 runs)

Mon + Thu rolling MAE (°C). Per-lead cells turn red when the rolling metric breaches the lead-specific drift threshold; check the verify report for the per-cell breakdown. Version column names the trained model — a fresh champion takes ~5-9d to show.

Run (UTC) Version N +12h+24h+48h+72h+96h+120h
v2026-07-19_135415_phase2c
v2026-07-26_135942_phase2c
624 1.459
temp_aifs: 0.365
1.400
temp_aifs: 0.404
0.701
temp_aifs: 0.719
1.211
temp_aifs: 0.882
1.172
temp_aifs: 0.902
1.788
temp_aifs: 0.818
v2026-07-12_135730_phase2c
v2026-07-19_135415_phase2c
624 1.263
temp_aifs: 0.643
1.229
temp_aifs: 0.703
0.779
temp_aifs: 0.800
1.415
temp_aifs: 1.229
1.662
temp_ukmo: 0.723
1.675
temp_aifs: 0.926
v2026-07-12_135730_phase2c
v2026-07-19_135415_phase2c
624 1.301
temp_aifs: 0.809
1.322
temp_ukmo: 0.771
0.777
temp_aifs: 0.841
1.096
temp_aifs: 0.812
1.048
temp_aifs: 0.788
1.439
temp_aifs: 0.838
v2026-07-05_135420_phase2c
v2026-07-12_135730_phase2c
624 1.773
temp_ecmwf: 0.642
1.648
temp_ecmwf: 0.745
0.777
temp_ecmwf: 0.890
1.073
temp_aifs: 0.782
1.209
temp_aifs: 0.885
2.199
temp_aifs: 1.419
v2026-07-05_135420_phase2c
v2026-07-12_135730_phase2c
624 1.949
temp_ecmwf: 0.671
1.803
temp_ecmwf: 0.631
1.450
temp_aifs: 1.089
1.803
temp_aifs: 1.217
1.831
temp_ecmwf: 1.396
2.580
temp_icon: 1.193
v2026-06-28_140921_phase2c
v2026-07-05_135420_phase2c
648 1.713
temp_aifs: 0.828
1.849
temp_aifs: 0.926
1.558
temp_aifs: 1.003
2.025
temp_aifs: 0.983
2.546
temp_aifs: 1.058
2.381
temp_aifs: 1.265
v2026-06-28_140921_phase2c
v2026-07-05_135420_phase2c
648 1.626
temp_aifs: 0.702
2.033
temp_aifs: 0.694
0.710
temp_ecmwf: 0.727
1.141
temp_aifs: 0.987
1.291
temp_aifs: 1.181
1.769
temp_aifs: 1.265
v2026-06-21_135756_phase2c
v2026-06-28_140921_phase2c
648 0.986
temp_aifs: 0.512
0.924
temp_ecmwf: 0.457
0.300
temp_ecmwf: 0.486
0.656
temp_ecmwf: 0.530
0.501
temp_ecmwf: 0.279
1.278
temp_aifs: 0.819
v2026-06-21_135756_phase2c
v2026-06-28_140921_phase2c
648 0.839
temp_ecmwf: 0.522
0.619
temp_ecmwf: 0.242
1.310
temp_aifs: 0.952
1.480
temp_ecmwf: 0.847
1.141
temp_ecmwf: 0.831
1.511
temp_aifs: 0.893
v2026-06-15_083940_phase2c
v2026-06-21_135756_phase2c
600 2.874
temp_ecmwf: 0.813
3.190
temp_aifs: 1.040
2.552
temp_aifs: 1.132
3.273
temp_icon: 1.335
2.759
temp_icon: 0.669
3.570
temp_gfs: 1.613
v2026-06-15_083940_phase2c
v2026-06-21_135756_phase2c
600 1.823
temp_gfs: 0.807
1.968
temp_ukmo: 0.808
0.751
temp_ecmwf: 0.791
0.792
temp_ecmwf: 0.850
0.817
temp_ecmwf: 0.988
1.879
temp_ecmwf: 1.275
v2026-06-07_131622_phase2c
v2026-06-14_134614_phase2c
v2026-06-15_083940_phase2c
720 0.706
temp_aifs: 0.667
0.668
temp_ecmwf: 0.598
0.839
temp_ecmwf: 0.696
0.624
temp_ecmwf: 0.975
0.884
temp_ecmwf: 0.792
0.830
temp_ecmwf: 1.150
v2026-06-07_131622_phase2c
v2026-06-14_134614_phase2c
v2026-06-15_083940_phase2c
720 0.788
temp_aifs: 0.583
0.853
temp_aifs: 0.471
0.471
temp_aifs: 0.673
0.613
temp_aifs: 0.691
0.742
temp_ecmwf: 0.950
0.978
temp_ecmwf: 1.156
v2026-06-01_233346_phase2c
v2026-06-07_131622_phase2c
528 0.597
temp_icon: 0.524
0.382
temp_aifs: 0.468
0.337
temp_mf: 0.578
0.663
temp_aifs: 0.590
0.499
temp_aifs: 0.542
v2026-06-01_233346_phase2c
v2026-06-07_131622_phase2c
528 0.692
temp_aifs: 0.558
0.426
temp_aifs: 0.490
0.478
temp_ecmwf: 0.648
0.621
temp_ecmwf: 0.750
0.534
temp_aifs: 0.725
v2026-06-01_233346_phase2c 432 0.468
temp_aifs: 0.403
0.435
temp_aifs: 0.503
0.566
temp_ecmwf: 0.723
0.642
temp_mf: 0.720
0.949
temp_gfs: 0.871
v2026-05-26_104346_phase2c
v2026-06-01_233346_phase2c
528 0.485
temp_aifs: 0.354
0.325
temp_aifs: 0.401
0.417
temp_aifs: 0.238
0.614
temp_aifs: 0.724
0.490
temp_aifs: 0.745
v2026-05-26_104346_phase2c
v2026-05-31_201130_phase2c
528 0.284
temp_aifs: 0.338
0.521
temp_ecmwf: 0.753
0.580
temp_aifs: 0.746
0.734
temp_aifs: 0.718
0.646
temp_aifs: 0.711
v2026-05-17_173626_phase2c
v2026-05-24_130333_phase2c
v2026-05-26_104346_phase2c
744 0.736
temp_aifs: 0.927
0.707
temp_gfs: 0.994
0.850
temp_aifs: 1.137
1.021
temp_ecmwf: 1.252
1.633
temp_aifs: 1.749
v2026-05-17_173626_phase2c
v2026-05-24_130333_phase2c
744 0.835
temp_ecmwf: 1.164
0.919
temp_ecmwf: 1.035
1.108
temp_ecmwf: 1.401
1.320
temp_ukmo: 1.773
1.604
temp_aifs: 1.876
v2026-04-28_232637_phase2c
v2026-05-17_173626_phase2c
1600 0.349
temp_aifs: 0.429
0.367
temp_aifs: 0.477
0.465
temp_icon: 0.413
0.558
temp_icon: 0.575
0.741
temp_ecmwf: 0.767
v2026-04-28_232637_phase2c
v2026-05-17_173626_phase2c
2012 0.550
temp_ukmo: 0.396
0.477
temp_icon: 0.660
0.744
temp_ecmwf: 0.767
0.796
temp_ecmwf: 0.891
0.769
temp_ecmwf: 0.795
v2026-04-28_232637_phase2c 2012 0.433
temp_icon: 0.566
0.565
temp_ecmwf: 0.775
0.780
temp_aifs: 0.899
0.836
temp_aifs: 0.945
0.958
temp_ecmwf: 1.069
v2026-04-28_232637_phase2c 1694 0.455
temp_aifs: 0.586
0.635
temp_ecmwf: 0.772
0.696
temp_aifs: 0.782
1.029
temp_aifs: 1.098
1.290
temp_aifs: 1.147
v2026-04-28_232637_phase2c 388 0.509
temp_aifs: 0.598
0.597
temp_ecmwf: 0.689
0.615
temp_aifs: 0.703
0.908
temp_aifs: 0.764
0.630
temp_ecmwf: 0.778
v2026-04-28_232637_phase2c 173 0.462
temp_aifs: 0.558
0.789
temp_aifs: 0.798
0.940
temp_ecmwf: 0.805
1.110
temp_aifs: 0.814
0.623
temp_ecmwf: 0.944
v2026-04-27_191724_phase2c
v2026-04-27_225213_phase2c
v2026-04-28_232637_phase2c
9 0.800
temp_aifs: 0.556
0.823
temp_gem: 0.717
1.104
temp_gem: 0.000
v2026-04-23_132453_phase2c
v2026-04-27_181257_phase2c
v2026-04-27_191724_phase2c
9 0.735
temp_mf: 0.000
1.616
temp_icon: 0.000
1.047
temp_ecmwf: 1.189
v2026-04-23_132453_phase2c 10 0.834
temp_mf: 0.740
0.904
temp_gfs: 0.580
By actual NWP forecast lead (6h buckets)

Same data grouped by ValidTime − freshest contributing NWP cycle (6h buckets) instead of trained-lead label. Reveals MAE structure within a trained bucket once predict spread to hourly outputs (2026-05-04+). Buckets start at the trained lead — earlier figures measured from the cron-fire time, which made offset-day models look like sub-lead forecasts.

Run (UTC) -12--7h0-5h6-11h12-17h18-23h24-29h30-35h36-41h42-47h48-53h54-59h60-65h66-71h72-77h78-83h84-89h90-95h96-101h102-107h108-113h114-119h120-125h126-131h132-137h138-143h144-149h
1.4471.8881.3372.0941.4481.2070.7180.6500.6430.7511.1591.3681.4061.0271.1171.3351.3191.1641.7131.9442.1951.616
1.2770.8981.1571.4731.4571.0590.7630.7960.9460.6541.3071.8692.0110.6391.6881.3701.1940.7281.6221.9891.8760.847
1.3270.3891.3960.5091.6131.0690.7080.8631.0391.0131.0361.3561.2990.6211.0291.1691.1380.6921.4531.5261.5020.622
1.7901.3361.7261.5051.5071.0370.6980.8861.0541.3220.9891.3961.4970.7021.1801.5241.6710.9742.0532.5702.9091.5713.125
1.9611.5211.8521.2682.6431.3641.4201.5861.6510.9391.6372.3202.5001.0051.7592.1372.1631.0882.4113.0483.5141.6303.125
1.7341.1481.6782.3052.6181.4001.5711.5551.7010.9271.8972.2963.0761.5642.7000.8562.0821.3992.1322.9033.1282.1503.125
1.6351.3032.0681.6551.4301.0320.6720.7440.7360.9871.1171.1531.4430.9391.2021.4791.7341.0951.6522.1042.4740.910
1.0010.6050.8671.1561.0930.6410.2950.3100.2480.4830.6820.5290.6880.5140.5060.4460.8690.5611.2681.4041.3920.678
0.8480.4930.6330.4612.4981.2971.3041.5291.2590.6861.5381.5881.1600.8671.2051.0930.9290.5921.5011.6041.6450.948
2.8932.3372.8834.0484.4612.4592.4123.2822.9821.1213.2903.5612.7152.5682.8142.1643.0822.3023.2454.4014.5093.392
1.8231.8502.0341.2421.1710.9570.6701.0320.8380.7620.7860.8600.8250.4920.8170.8560.7960.6941.7812.3831.8781.543
0.7140.4670.7030.6150.4990.6460.6761.2921.1961.7080.5720.6511.3131.0840.9180.3760.7370.4410.8150.8470.8001.101
0.7880.3840.8810.4290.8570.5710.4800.4610.4460.4280.5880.7280.6440.4570.7390.7630.8500.4030.9870.9570.8021.468
0.6070.5380.5960.6880.3840.4260.3460.2100.2880.5260.4220.4990.6420.8900.6010.4970.4710.4700.5141.091
0.7240.3390.4320.3440.3950.5060.4970.4500.4350.5840.6060.4840.5800.7140.7800.6150.5020.5490.6540.792
0.4910.4410.3910.3460.4280.4640.4010.5440.5060.7270.6940.7830.5470.9030.9161.0590.9490.4260.4080.562
0.5300.4470.2970.2320.3200.2590.3260.7050.4170.4010.5000.3500.6670.4510.5480.4130.5110.4260.4080.562
0.2840.5500.4920.4170.5570.4270.4630.3100.6450.3560.5240.3100.8130.4690.6520.3080.6990.5680.3800.433
0.7310.7820.6560.8790.6830.7231.0221.1840.8520.7731.1760.3851.0780.3951.0890.7131.5951.9401.8370.688
0.7340.7171.0080.8540.8180.9100.8931.0990.4370.1760.9711.0101.3091.4541.2751.2961.0391.1691.5051.5841.7132.0801.1910.851
0.2410.2980.3760.3060.3240.3890.3680.3100.4040.5100.4710.4960.5510.4520.5280.5260.1330.0560.7120.6390.7720.9950.7610.698
0.2140.3961.1360.4270.3800.2670.3790.4630.5090.6680.7310.7190.7610.7970.7130.7710.8580.6820.6630.6950.7721.0380.8550.988
0.3100.3910.3840.4540.5000.4670.5380.5470.6140.7000.7850.6770.7940.8940.7850.7920.9040.9290.7480.8700.9051.0551.1551.291
0.4280.4330.4040.4550.4910.5230.6260.5700.6400.6360.6800.6070.8780.9740.9140.9201.1021.2811.0901.0671.3411.4831.5821.559
0.7110.4620.4910.5910.4600.4920.5030.6690.4260.5900.4810.6390.6310.6210.7240.8940.630
0.2010.1870.2570.6620.3110.3650.3860.7322.2520.9401.1100.623
1.7710.1090.8000.2891.0901.104
1.7711.6160.7350.8511.047

Phase 2b · v2026-08-02_135147 Δ +0.001 vs prev train

Lean blender, 13 features. Trained 2026-08-02. Metric: Test MAE (°C).

Lead Blend Best single Δ vs best
+24h 0.657 temp_aifs (0.665) -1.2%
+48h 0.741 temp_aifs (0.709) +4.6%
+72h 0.816 temp_aifs (0.794) +2.7%
+96h 0.979 temp_aifs (0.924) +6.0%
+120h 1.175 temp_aifs (1.066) +10.2%
Verify history (29 runs)

Mon + Thu rolling MAE (°C). Per-lead cells turn red when the rolling metric breaches the lead-specific drift threshold; check the verify report for the per-cell breakdown. Version column names the trained model — a fresh champion takes ~5-9d to show.

Run (UTC) Version N +24h+48h+72h+96h+120h
v2026-07-19_135314
v2026-07-26_135822
624 0.854
temp_aifs: 0.404
0.820
temp_aifs: 0.719
1.114
temp_aifs: 0.882
1.231
temp_aifs: 0.902
1.571
temp_aifs: 0.818
v2026-07-12_135640
v2026-07-19_135314
624 1.073
temp_aifs: 0.703
1.019
temp_aifs: 0.800
1.423
temp_aifs: 1.229
1.751
temp_gfs: 1.408
1.577
temp_aifs: 0.926
v2026-07-12_135640
v2026-07-19_135314
624 1.296
temp_aifs: 0.992
0.879
temp_aifs: 0.841
1.083
temp_aifs: 0.812
1.240
temp_aifs: 0.788
1.332
temp_aifs: 0.838
v2026-07-05_135325
v2026-07-12_135640
624 1.042
temp_ecmwf: 0.745
0.763
temp_ecmwf: 0.890
0.910
temp_aifs: 0.782
1.320
temp_aifs: 0.885
1.969
temp_aifs: 1.419
v2026-07-05_135325
v2026-07-12_135640
624 1.285
temp_ecmwf: 0.631
1.561
temp_aifs: 1.089
2.021
temp_aifs: 1.217
1.977
temp_ecmwf: 1.396
2.343
temp_icon: 1.193
v2026-06-28_140834
v2026-07-05_135325
648 1.671
temp_aifs: 0.926
1.715
temp_aifs: 1.003
2.415
temp_aifs: 0.983
2.723
temp_aifs: 1.058
2.312
temp_aifs: 1.265
v2026-06-28_140834
v2026-07-05_135325
648 1.787
temp_aifs: 0.694
0.854
temp_ecmwf: 0.727
1.186
temp_aifs: 0.987
1.297
temp_aifs: 1.181
1.814
temp_aifs: 1.265
v2026-06-21_135711
v2026-06-28_140834
648 0.614
temp_ecmwf: 0.457
0.410
temp_ecmwf: 0.486
0.628
temp_ecmwf: 0.530
0.593
temp_ecmwf: 0.279
1.045
temp_aifs: 0.819
v2026-06-21_135711
v2026-06-28_140834
648 0.398
temp_ecmwf: 0.242
1.302
temp_aifs: 0.952
1.333
temp_ecmwf: 0.847
1.101
temp_ecmwf: 0.831
1.285
temp_aifs: 0.893
v2026-06-14_134518
v2026-06-21_135711
672 2.348
temp_aifs: 1.040
2.512
temp_aifs: 1.132
3.011
temp_icon: 1.335
2.603
temp_icon: 0.669
2.787
temp_gfs: 1.701
v2026-06-14_134518
v2026-06-21_135711
672 1.187
temp_gfs: 0.873
0.756
temp_ecmwf: 0.776
0.765
temp_ecmwf: 0.803
0.889
temp_ecmwf: 0.934
1.333
temp_aifs: 1.222
v2026-06-07_131530
v2026-06-14_134518
720 0.564
temp_ecmwf: 0.679
0.821
temp_ecmwf: 0.683
0.655
temp_ecmwf: 0.742
0.966
temp_ecmwf: 0.792
0.906
temp_ecmwf: 1.150
v2026-06-07_131530
v2026-06-14_134518
720 0.543
temp_aifs: 0.471
0.599
temp_aifs: 0.673
0.663
temp_aifs: 0.691
0.783
temp_ecmwf: 0.950
1.091
temp_ecmwf: 1.156
v2026-06-05_091025
v2026-06-07_131530
384 0.564
temp_icon: 0.524
0.443
temp_aifs: 0.468
0.466
temp_mf: 0.578
0.696
temp_aifs: 0.590
0.516
temp_aifs: 0.415
v2026-06-01_214702
v2026-06-05_091025
v2026-06-07_131530
336 0.694
temp_aifs: 0.558
0.442
temp_aifs: 0.472
0.545
temp_aifs: 0.547
0.592
temp_ecmwf: 0.817
0.540
temp_aifs: 0.767
v2026-06-01_214702
v2026-06-05_091025
336 0.354
temp_aifs: 0.522
0.384
temp_aifs: 0.502
0.527
temp_aifs: 0.725
0.640
temp_mf: 0.764
0.835
temp_gfs: 0.871
v2026-05-26_104311
v2026-06-01_214702
528 0.458
temp_aifs: 0.354
0.295
temp_aifs: 0.416
0.565
temp_aifs: 0.238
0.617
temp_aifs: 0.724
0.463
temp_aifs: 0.745
v2026-05-26_104311
v2026-05-31_201040
528 0.285
temp_aifs: 0.338
0.636
temp_ecmwf: 0.753
0.699
temp_aifs: 0.746
0.776
temp_aifs: 0.718
0.670
temp_aifs: 0.711
v2026-05-17_173452
v2026-05-24_130255
v2026-05-26_104311
744 1.041
temp_aifs: 0.927
0.668
temp_gfs: 0.994
1.139
temp_aifs: 1.137
0.869
temp_ecmwf: 1.252
1.829
temp_aifs: 1.749
v2026-05-17_173452
v2026-05-24_130255
744 1.309
temp_ecmwf: 1.164
1.477
temp_ecmwf: 1.035
1.351
temp_ecmwf: 1.401
1.655
temp_gfs: 1.812
1.851
temp_aifs: 1.876
v2026-04-28_232613
v2026-05-17_173452
1600 0.424
temp_aifs: 0.429
0.418
temp_aifs: 0.477
0.491
temp_icon: 0.413
0.682
temp_icon: 0.575
0.672
temp_ecmwf: 0.767
v2026-04-28_232613
v2026-05-17_173452
2012 0.452
temp_icon: 0.413
0.489
temp_icon: 0.660
0.725
temp_ecmwf: 0.767
0.783
temp_ecmwf: 0.891
0.731
temp_ecmwf: 0.795
v2026-04-28_232613 2012 0.511
temp_icon: 0.566
0.609
temp_ecmwf: 0.775
0.823
temp_aifs: 0.899
0.857
temp_aifs: 0.945
0.976
temp_ecmwf: 1.069
v2026-04-28_232613 1694 0.516
temp_aifs: 0.586
0.688
temp_ecmwf: 0.772
0.790
temp_aifs: 0.782
1.078
temp_aifs: 1.098
1.360
temp_aifs: 1.147
v2026-04-28_232613 388 0.561
temp_aifs: 0.598
0.637
temp_ecmwf: 0.689
0.619
temp_aifs: 0.703
0.897
temp_aifs: 0.764
0.495
temp_ecmwf: 0.778
v2026-04-28_232613 173 0.576
temp_aifs: 0.558
0.813
temp_aifs: 0.798
0.906
temp_ecmwf: 0.805
1.013
temp_aifs: 0.814
0.527
temp_ecmwf: 0.944
v2026-04-27_204454
v2026-04-28_232613
9 1.202
temp_aifs: 0.556
1.076
temp_gem: 0.629
0.606
temp_gem: 0.700
v2026-04-21_201231_phase2redo
v2026-04-27_174346
v2026-04-27_204454
13 0.182
temp_icon: 0.000
1.580
temp_icon: 0.000
0.962
temp_gem: 1.054
v2026-04-21_201231_phase2redo 14 0.959
temp_mf: 0.743
0.943
temp_ecmwf: 1.122
0.888
temp_gem: 0.375
By actual NWP forecast lead (6h buckets)

Same data grouped by ValidTime − freshest contributing NWP cycle (6h buckets) instead of trained-lead label. Reveals MAE structure within a trained bucket once predict spread to hourly outputs (2026-05-04+). Buckets start at the trained lead — earlier figures measured from the cron-fire time, which made offset-day models look like sub-lead forecasts.

Run (UTC) -12--7h-6--1h0-5h6-11h12-17h18-23h24-29h30-35h36-41h42-47h48-53h54-59h60-65h66-71h72-77h78-83h84-89h90-95h96-101h102-107h108-113h114-119h120-125h126-131h132-137h138-143h144-149h
0.8001.4481.0770.6600.8740.7540.6840.4611.1021.1961.2350.6891.1781.3881.4151.1051.4761.7192.0731.599
1.1211.0790.9870.2761.0780.9460.9590.2221.4131.5551.7480.2051.8141.0511.4170.7191.5541.8211.7140.646
1.3640.5441.0910.7550.8370.9581.0630.8591.0781.2021.0990.6311.2281.3921.2960.6811.3581.3491.3920.576
1.0810.9250.9820.9020.6830.8831.0951.1330.9041.1070.8630.1891.3221.3031.8751.0001.8502.2652.5471.4792.715
1.3370.7152.1551.0411.5551.6331.7021.0231.9202.4522.5240.8371.8962.3042.4121.0522.2182.7123.0741.4182.715
1.6191.8302.0920.9841.7791.4941.7871.1112.3922.5522.9890.9042.9010.7552.0191.2432.0862.7913.0501.9812.715
1.8341.2670.9650.6330.8020.8940.9631.1341.1711.1891.4880.7921.2311.4311.7220.9321.7162.1192.4910.797
0.5640.7690.7890.5080.3890.4360.5280.4390.6310.5930.7130.4940.6020.4950.7880.5761.0371.1101.1100.756
0.3930.4471.8190.7311.3171.4161.2590.7021.4341.3500.9310.5721.1661.0500.8560.6451.2961.2831.3340.929
2.0803.1463.4971.2472.4003.0812.9491.0693.0793.2202.1941.7972.7411.4122.8822.0292.5253.4873.6092.502
1.2520.6340.7400.4690.6910.8990.9400.8690.7520.7960.8020.7910.9080.9230.8080.5951.2731.6911.4160.821
0.5250.6230.7100.7390.6991.1071.3101.0550.5380.8911.1461.5520.9970.4970.9270.5700.8740.9370.9331.253
0.5460.4930.6560.5890.5950.5890.6500.5930.6290.7540.6970.7410.7350.8281.1070.5101.0991.0540.9481.563
0.5850.4810.5520.5790.4640.4530.3350.2250.4420.6010.4510.4950.6780.8900.3970.5490.4370.5710.6462.227
0.7150.4670.5320.4380.3880.6480.5240.3060.5260.7680.2720.4770.5320.7590.7790.6800.5520.5010.4560.634
0.3320.4700.3150.2720.3830.3860.3380.4990.4960.6180.5880.7090.5251.0860.9851.2650.8350.4250.3520.393
0.5000.3860.2960.1930.2990.2630.2330.4790.5650.4050.5210.2220.6880.4160.4940.3390.4860.4250.3520.393
0.2850.5690.4960.3710.6910.4830.5850.2630.7740.4430.6910.2660.8680.4800.6410.3260.6870.7210.4520.556
1.1120.9770.5900.8170.6560.5761.0641.2201.2040.8381.3270.4110.9170.3471.6830.8851.7402.2702.1250.949
2.1621.5911.4461.2441.2221.3361.2781.4340.7700.9651.2671.2901.5361.5741.5441.7301.3351.5611.6941.7852.0892.3891.4551.055
0.3860.4080.4170.3590.4250.4100.4650.4210.4330.4480.4570.5410.7110.5410.6040.5480.5600.2610.6290.5910.7780.8030.5840.713
0.2660.3321.0500.2040.0160.2260.4100.5090.5160.7030.7510.7030.7360.7160.6890.7540.8520.6490.6540.6680.8290.8760.6880.804
0.4760.5750.4990.5780.5330.5130.6080.6070.6570.7880.8750.7180.7650.8670.7740.7440.9460.9330.8320.8860.9331.0311.1581.134
0.6460.6420.5350.5300.4870.5750.7090.6210.6790.7250.7720.6750.8760.9780.8910.9431.2231.3621.2131.0761.3971.6801.7381.618
0.8510.6340.5430.6560.4850.5230.5490.6910.5020.5970.5250.6280.5360.6570.7030.8830.495
0.6600.4510.4510.7560.3760.4270.4730.7660.6062.3540.9061.0130.527
0.9770.9770.1820.3921.2020.0570.5851.5770.6061.950
0.9770.9770.1821.5800.2280.9930.962

Phase 2d · v2026-08-02_135436_phase2d Δ +0.010 vs prev train

Exact-runtime blender. Trains on raw S3 cycles (GFS + AIFS required, IFS oper + MO Global + UKV optional) instead of Open-Meteo offset_day, with rigorous (RunTime, ValidTime, Lead) provenance per row. UKV pulled per-V-hour from 03Z + 15Z cycles. Trained 2026-08-02. Metric: Test MAE (°C).

Lead Blend Best single Δ vs best
+12h 0.687 temp_ifs (1.297) -47.1%
+24h 0.688 temp_ifs (1.310) -47.5%
+48h 0.756 temp_gfs (1.573) -51.9%
+72h 0.770 temp_moglobal (1.268) -39.3%
+96h 0.924 temp_ifs (1.188) -22.2%
+120h 1.122 temp_ifs (1.350) -16.9%
Verify history (25 runs)

Mon + Thu rolling MAE (°C). Per-lead cells turn red when the rolling metric breaches the lead-specific drift threshold; check the verify report for the per-cell breakdown. Version column names the trained model — a fresh champion takes ~5-9d to show.

Run (UTC) Version N +12h+24h+48h+72h+96h+120h
v2026-05-09_084413_phase2d
v2026-07-26_140108_phase2d
163 0.479
0.301
0.366
1.171
1.230
1.381
v2026-05-09_084413_phase2d
v2026-07-19_135526_phase2d
163 0.530
0.509
0.642
1.478
1.567
1.750
v2026-05-09_084413_phase2d
v2026-07-19_135526_phase2d
163 0.451
0.432
0.277
1.600
1.833
1.899
v2026-05-09_084413_phase2d
v2026-07-12_135827_phase2d
163 1.004
0.974
0.957
2.441
2.602
2.686
v2026-05-09_084413_phase2d
v2026-07-12_135827_phase2d
167 1.257
1.130
0.690
2.842
2.981
3.133
v2026-05-09_084413_phase2d
v2026-07-05_135520_phase2d
167 1.706
1.700
2.058
1.951
2.102
2.297
v2026-05-09_084413_phase2d
v2026-07-05_135520_phase2d
165 1.281
1.618
2.167
1.093
1.083
1.239
v2026-05-09_084413_phase2d
v2026-06-28_141013_phase2d
167 0.371
0.314
0.382
1.001
1.060
1.201
v2026-05-09_084413_phase2d
v2026-06-28_141013_phase2d
177 0.427
0.428
0.515
2.046
2.180
2.568
v2026-05-09_084413_phase2d
v2026-06-21_135847_phase2d
173 1.917
2.005
2.771
2.183
2.366
2.537
v2026-05-09_084413_phase2d
v2026-06-21_135847_phase2d
171 0.853
0.794
1.152
1.048
1.093
0.988
v2026-05-09_084413_phase2d
v2026-06-14_134717_phase2d
179 0.494
0.551
0.527
0.615
0.981
0.915
v2026-05-09_084413_phase2d
v2026-06-14_134717_phase2d
185 0.445
0.654
0.498
0.452
0.829
0.805
v2026-05-09_084413_phase2d
v2026-06-07_131721_phase2d
186 0.394
0.383
0.425
0.524
0.600
0.584
v2026-05-09_084413_phase2d
v2026-06-07_131721_phase2d
194 0.368
0.334
0.333
0.542
0.601
0.646
v2026-05-09_084413_phase2d
v2026-05-31_201225_phase2d
v2026-06-07_131721_phase2d
235 0.219
0.330
0.331
0.531
0.621
0.795
v2026-05-09_084413_phase2d
v2026-05-31_201225_phase2d
212 0.346
0.322
0.306
0.550
0.588
0.836
v2026-05-09_084413_phase2d
v2026-05-31_201225_phase2d
197 0.459
0.383
0.297
1.033
1.108
1.379
v2026-05-09_084413_phase2d
v2026-05-26_104427_phase2d
128 1.292
1.058
0.891
1.666
1.802
1.999
v2026-05-09_084413_phase2d
v2026-05-24_130417_phase2d
v2026-05-26_104427_phase2d
83 1.990
1.898
2.192
1.966
1.783
1.743
v2026-05-09_084413_phase2d
v2026-05-17_173814_phase2d
24 0.366
0.582
0.453
0.431
0.288
0.299
v2026-05-08_060055_phase2d
v2026-05-09_083929_phase2d
v2026-05-09_084413_phase2d
v2026-05-17_173814_phase2d
110 0.650
0.632
0.482
0.493
0.655
0.671
v2026-05-08_055817_phase2d
v2026-05-08_060055_phase2d
91 0.334
0.464
0.432
0.689
0.866
0.675
v2026-05-08_055817_phase2d
v2026-05-08_060055_phase2d
45 0.227
0.205
0.460
0.564
v2026-05-05_182234_phase2d 12 0.376
0.697
By actual NWP forecast lead (6h buckets)

Same data grouped by ValidTime − freshest contributing NWP cycle (6h buckets) instead of trained-lead label. Reveals MAE structure within a trained bucket once predict spread to hourly outputs (2026-05-04+). Buckets start at the trained lead — earlier figures measured from the cron-fire time, which made offset-day models look like sub-lead forecasts.

Run (UTC) -48--43h-42--37h-36--31h-30--25h-24--19h-18--13h-12--7h-6--1h0-5h6-11h12-17h18-23h24-29h30-35h36-41h42-47h48-53h54-59h60-65h66-71h72-77h78-83h84-89h90-95h96-101h102-107h108-113h
1.1301.0521.8692.3041.7821.6062.0423.3141.9991.6561.9842.3662.2522.3792.6472.6161.9601.5221.9922.7521.9151.3751.8393.8361.7081.1611.862
0.1860.1260.2340.1950.2590.0680.4350.5460.6770.5310.3700.4140.5340.3280.4180.4900.3820.2690.2610.2840.2200.368
0.8100.6060.7900.7900.4340.5530.4450.1420.2600.7650.6400.7570.5670.7660.6460.660
0.8100.3530.4380.4790.3360.5020.4000.6320.8120.5981.2370.9890.6610.7870.6320.697
0.2170.1220.3010.4530.5170.3980.8270.5080.514
0.5550.6000.607