WeatherBlend

Multi-model forecast blending for Sennen, Cornwall

Dry-window models

Per-(station, window) P(N-hour dry block in 09–18 local). 3b LightGBM + 3p copula MC. Brier, lower better. Δ vs best single NWP — negative = blend wins.

Dry window — Trengwainton — 2-hour

Phase 3q · v2026-10-04_161034_phase3q Δ +0.000 vs prev train

Phase 3q blender. Trained 2026-10-04. Metric: Test Brier.

Lead Blend Best single Δ vs best
+24h 0.000 — (0.000 val) —
+48h 0.000 — (0.000 val) —
+72h 0.000 — (0.000 val) —
Verify history (25 runs)

Mon + Thu rolling Brier. 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
v2026-09-06_155519_phase3q 8 0.000
—		0.000
—		0.000
—		——
v2026-08-30_152141_phase3q 24 0.000
—		0.001
—		0.002
—		——
v2026-08-30_152141_phase3q 11 0.000
—		0.001
—		0.005
—		——
v2026-08-23_154721_phase3q 18 0.003
—		0.003
—		0.005
—		——
v2026-08-23_154721_phase3q 9 0.002
—		0.001
—		0.002
—		——
v2026-08-09_160411_phase3q 36 0.000
—		0.000
—		0.001
—		——
v2026-08-09_160411_phase3q 38 0.000
—		0.000
—		0.001
—		——
v2026-08-09_160411_phase3q 21 0.000
—		0.000
—		0.000
—		——
v2026-08-09_160411_phase3q 9 0.000
—		0.000
—		0.000
—		——
v2026-08-02_154011_phase3q 19 0.000
—		0.000
—		0.000
—		——
v2026-08-02_154011_phase3q 15 0.000
—		0.000
—		0.000
—		——
v2026-07-26_154305_phase3q 20 0.000
—		0.000
—		0.000
—		——
v2026-07-26_154305_phase3q 8 0.000
—		0.000
—		0.000
—		——
v2026-07-19_152830_phase3q 22 0.000
—		0.000
—		0.000
—		——
v2026-07-19_152830_phase3q 10 0.000
—		0.000
—		0.000
—		——
v2026-07-12_153204_phase3q 22 0.000
—		0.000
—		0.000
—		——
v2026-07-12_153204_phase3q 10 0.000
—		0.000
—		0.000
—		——
v2026-07-05_152333_phase3q 14 0.000
—		0.000
—		0.000
—		——
v2026-07-05_152333_phase3q 10 0.000
—		0.000
—		0.000
—		——
v2026-06-28_223429_phase3q 16 0.000
—		0.000
—		0.000
—		——
v2026-06-28_164125_phase3q
v2026-06-28_223429_phase3q		 8 0.000
—		0.000
—		0.000
—		——
v2026-06-21_152916_phase3q 18 0.000
—		0.000
—		0.000
—		——
v2026-06-14_153851_phase3q
v2026-06-21_152916_phase3q		 23 0.000
—		0.000
—		0.003
—		——
v2026-06-14_153851_phase3q 21 0.007
—		0.004
—		0.005
—		——
v2026-06-14_153851_phase3q 9 0.016
—		0.009
—		0.001
—		——

Dry window — Trengwainton — 3-hour

Phase 3b · v2026-10-04_160843 Δ -0.000 vs prev train

53-feature LightGBM per-(station, window). Trained 2026-10-04. Metric: Test Brier.

Lead Blend Best single Δ vs best
+24h 0.031 has_dry_window_mf (0.026) +18.3%
+48h 0.028 has_dry_window_icon (0.060) -53.9%
+72h 0.031 has_dry_window_icon (0.081) -62.0%
Verify history (25 runs)

Mon + Thu rolling Brier. 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
v2026-09-06_155230 8 0.000
—		0.003
—		0.001
—		——
v2026-08-30_151859 24 0.001
—		0.002
—		0.004
—		——
v2026-08-30_151859 11 0.001
—		0.002
—		0.001
—		——
v2026-08-23_154438 18 0.022
—		0.010
—		0.019
—		——
v2026-08-23_154438 9 0.013
—		0.005
—		0.001
—		——
v2026-08-09_160131 36 0.001
—		0.001
—		0.010
—		——
v2026-08-09_160131 38 0.001
—		0.001
—		0.001
—		——
v2026-08-09_160131 21 0.001
—		0.000
—		0.000
—		——
v2026-08-09_160131 9 0.001
—		0.000
—		0.000
—		——
v2026-08-02_153737 19 0.196
—		0.063
—		0.001
—		——
v2026-08-02_153737 15 0.248
—		0.073
—		0.001
—		——
v2026-07-26_154025 20 0.000
—		0.001
—		0.001
—		——
v2026-07-26_154025 8 0.000
—		0.001
—		0.001
—		——
v2026-07-19_152622 22 0.000
—		0.001
—		0.001
—		——
v2026-07-19_152622 10 0.000
—		0.001
—		0.001
—		——
v2026-07-12_152939 22 0.000
—		0.001
—		0.003
—		——
v2026-07-12_152939 10 0.000
—		0.001
—		0.016
—		——
v2026-07-05_152108 14 0.000
—		0.001
—		0.000
—		——
v2026-07-05_152108 10 0.000
—		0.001
—		0.000
—		——
v2026-06-28_223229 16 0.000
—		0.001
—		0.001
—		——
v2026-06-28_164003
v2026-06-28_223229		 8 0.000
—		0.001
—		0.000
—		——
v2026-06-21_152620 18 0.000
—		0.001
—		0.000
—		——
v2026-06-14_153642
v2026-06-21_152620		 23 0.000
—		0.001
—		0.001
—		——
v2026-06-14_153642 21 0.024
—		0.004
—		0.002
—		——
v2026-06-14_153642 9 0.057
—		0.006
—		0.002
—		——

Phase 3q · v2026-10-04_161034_phase3q Δ +0.000 vs prev train

Phase 3q blender. Trained 2026-10-04. Metric: Test Brier.

Lead Blend Best single Δ vs best
+24h 0.000 — (0.000 val) —
+48h 0.000 — (0.000 val) —
+72h 0.000 — (0.000 val) —
Verify history (25 runs)

Mon + Thu rolling Brier. 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
v2026-09-06_155519_phase3q 8 0.000
—		0.001
—		0.001
—		——
v2026-08-30_152141_phase3q 24 0.002
—		0.006
—		0.014
—		——
v2026-08-30_152141_phase3q 11 0.001
—		0.007
—		0.028
—		——
v2026-08-23_154721_phase3q 18 0.020
—		0.019
—		0.027
—		——
v2026-08-23_154721_phase3q 9 0.017
—		0.012
—		0.018
—		——
v2026-08-09_160411_phase3q 36 0.002
—		0.003
—		0.010
—		——
v2026-08-09_160411_phase3q 38 0.001
—		0.002
—		0.006
—		——
v2026-08-09_160411_phase3q 21 0.000
—		0.000
—		0.001
—		——
v2026-08-09_160411_phase3q 9 0.000
—		0.000
—		0.000
—		——
v2026-08-02_154011_phase3q 19 0.167
—		0.061
—		0.001
—		——
v2026-08-02_154011_phase3q 15 0.212
—		0.070
—		0.000
—		——
v2026-07-26_154305_phase3q 20 0.000
—		0.000
—		0.001
—		——
v2026-07-26_154305_phase3q 8 0.000
—		0.000
—		0.000
—		——
v2026-07-19_152830_phase3q 22 0.000
—		0.000
—		0.000
—		——
v2026-07-19_152830_phase3q 10 0.000
—		0.000
—		0.000
—		——
v2026-07-12_153204_phase3q 22 0.000
—		0.000
—		0.001
—		——
v2026-07-12_153204_phase3q 10 0.000
—		0.001
—		0.002
—		——
v2026-07-05_152333_phase3q 14 0.000
—		0.000
—		0.000
—		——
v2026-07-05_152333_phase3q 10 0.000
—		0.000
—		0.000
—		——
v2026-06-28_223429_phase3q 16 0.000
—		0.000
—		0.001
—		——
v2026-06-28_164125_phase3q
v2026-06-28_223429_phase3q		 8 0.001
—		0.000
—		0.000
—		——
v2026-06-21_152916_phase3q 18 0.000
—		0.000
—		0.001
—		——
v2026-06-14_153851_phase3q
v2026-06-21_152916_phase3q		 23 0.000
—		0.000
—		0.016
—		——
v2026-06-14_153851_phase3q 21 0.032
—		0.020
—		0.028
—		——
v2026-06-14_153851_phase3q 9 0.068
—		0.045
—		0.016
—		——

Dry window — Trengwainton — 4-hour

Phase 3b · v2026-10-04_160903 Δ +0.001 vs prev train

53-feature LightGBM per-(station, window). Trained 2026-10-04. Metric: Test Brier.

Lead Blend Best single Δ vs best
+24h 0.076 has_dry_window_icon (0.141) -46.3%
+48h 0.076 has_dry_window_jma (0.161) -53.0%
+72h 0.069 has_dry_window_jma (0.148) -53.4%
Verify history (25 runs)

Mon + Thu rolling Brier. 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
v2026-09-06_155300 8 0.001
—		0.000
—		0.000
—		——
v2026-08-30_151928 24 0.009
—		0.009
—		0.012
—		——
v2026-08-30_151928 11 0.005
—		0.014
—		0.001
—		——
v2026-08-23_154507 18 0.223
—		0.130
—		0.051
—		——
v2026-08-23_154507 9 0.273
—		0.177
—		0.012
—		——
v2026-08-09_160200 36 0.005
—		0.007
—		0.009
—		——
v2026-08-09_160200 38 0.002
—		0.005
—		0.005
—		——
v2026-08-09_160200 21 0.000
—		0.001
—		0.001
—		——
v2026-08-09_160200 9 0.000
—		0.001
—		0.001
—		——
v2026-08-02_153805 19 0.162
—		0.060
—		0.001
—		——
v2026-08-02_153805 15 0.205
—		0.070
—		0.000
—		——
v2026-07-26_154053 20 0.001
—		0.001
—		0.001
—		——
v2026-07-26_154053 8 0.001
—		0.001
—		0.001
—		——
v2026-07-19_152644 22 0.001
—		0.001
—		0.000
—		——
v2026-07-19_152644 10 0.001
—		0.001
—		0.000
—		——
v2026-07-12_153005 22 0.001
—		0.000
—		0.002
—		——
v2026-07-12_153005 10 0.001
—		0.000
—		0.005
—		——
v2026-07-05_152133 14 0.001
—		0.001
—		0.000
—		——
v2026-07-05_152133 10 0.001
—		0.001
—		0.000
—		——
v2026-06-28_223252 16 0.224
—		0.001
—		0.000
—		——
v2026-06-28_164026
v2026-06-28_223252		 8 0.448
—		0.001
—		0.000
—		——
v2026-06-21_152640 18 0.053
—		0.001
—		0.000
—		——
v2026-06-14_153657
v2026-06-21_152640		 23 0.186
—		0.002
—		0.179
—		——
v2026-06-14_153657 21 0.046
—		0.024
—		0.015
—		——
v2026-06-14_153657 9 0.085
—		0.032
—		0.001
—		——

Phase 3q · v2026-10-04_161034_phase3q Δ +0.000 vs prev train

Phase 3q blender. Trained 2026-10-04. Metric: Test Brier.

Lead Blend Best single Δ vs best
+24h 0.000 — (0.000 val) —
+48h 0.000 — (0.000 val) —
+72h 0.000 — (0.000 val) —
Verify history (25 runs)

Mon + Thu rolling Brier. 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
v2026-09-06_155519_phase3q 8 0.003
—		0.003
—		0.004
—		——
v2026-08-30_152141_phase3q 24 0.009
—		0.021
—		0.043
—		——
v2026-08-30_152141_phase3q 11 0.007
—		0.025
—		0.083
—		——
v2026-08-23_154721_phase3q 18 0.154
—		0.096
—		0.074
—		——
v2026-08-23_154721_phase3q 9 0.251
—		0.157
—		0.056
—		——
v2026-08-09_160411_phase3q 36 0.008
—		0.011
—		0.033
—		——
v2026-08-09_160411_phase3q 38 0.005
—		0.007
—		0.020
—		——
v2026-08-09_160411_phase3q 21 0.000
—		0.001
—		0.006
—		——
v2026-08-09_160411_phase3q 9 0.000
—		0.000
—		0.002
—		——
v2026-08-02_154011_phase3q 19 0.138
—		0.054
—		0.005
—		——
v2026-08-02_154011_phase3q 15 0.174
—		0.063
—		0.003
—		——
v2026-07-26_154305_phase3q 20 0.002
—		0.001
—		0.004
—		——
v2026-07-26_154305_phase3q 8 0.001
—		0.001
—		0.002
—		——
v2026-07-19_152830_phase3q 22 0.001
—		0.000
—		0.003
—		——
v2026-07-19_152830_phase3q 10 0.000
—		0.000
—		0.001
—		——
v2026-07-12_153204_phase3q 22 0.001
—		0.002
—		0.004
—		——
v2026-07-12_153204_phase3q 10 0.001
—		0.003
—		0.008
—		——
v2026-07-05_152333_phase3q 14 0.000
—		0.001
—		0.003
—		——
v2026-07-05_152333_phase3q 10 0.000
—		0.001
—		0.001
—		——
v2026-06-28_223429_phase3q 16 0.202
—		0.001
—		0.004
—		——
v2026-06-28_164125_phase3q
v2026-06-28_223429_phase3q		 8 0.404
—		0.001
—		0.001
—		——
v2026-06-21_152916_phase3q 18 0.050
—		0.002
—		0.005
—		——
v2026-06-14_153851_phase3q
v2026-06-21_152916_phase3q		 23 0.178
—		0.001
—		0.194
—		——
v2026-06-14_153851_phase3q 21 0.076
—		0.050
—		0.061
—		——
v2026-06-14_153851_phase3q 9 0.154
—		0.099
—		0.033
—		——

Dry window — Trengwainton — 5-hour

Phase 3q · v2026-10-04_161034_phase3q Δ +0.000 vs prev train

Phase 3q blender. Trained 2026-10-04. Metric: Test Brier.

Lead Blend Best single Δ vs best
+24h 0.000 — (0.000 val) —
+48h 0.000 — (0.000 val) —
+72h 0.000 — (0.000 val) —
Verify history (25 runs)

Mon + Thu rolling Brier. 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
v2026-09-06_155519_phase3q 8 0.338
—		0.135
—		0.012
—		——
v2026-08-30_152141_phase3q 24 0.029
—		0.053
—		0.086
—		——
v2026-08-30_152141_phase3q 11 0.035
—		0.060
—		0.161
—		——
v2026-08-23_154721_phase3q 18 0.204
—		0.172
—		0.164
—		——
v2026-08-23_154721_phase3q 9 0.200
—		0.168
—		0.099
—		——
v2026-08-09_160411_phase3q 36 0.029
—		0.034
—		0.068
—		——
v2026-08-09_160411_phase3q 38 0.018
—		0.023
—		0.041
—		——
v2026-08-09_160411_phase3q 21 0.003
—		0.008
—		0.017
—		——
v2026-08-09_160411_phase3q 9 0.002
—		0.001
—		0.007
—		——
v2026-08-02_154011_phase3q 19 0.102
—		0.045
—		0.016
—		——
v2026-08-02_154011_phase3q 15 0.128
—		0.051
—		0.011
—		——
v2026-07-26_154305_phase3q 20 0.008
—		0.005
—		0.016
—		——
v2026-07-26_154305_phase3q 8 0.005
—		0.005
—		0.007
—		——
v2026-07-19_152830_phase3q 22 0.003
—		0.002
—		0.009
—		——
v2026-07-19_152830_phase3q 10 0.003
—		0.002
—		0.007
—		——
v2026-07-12_153204_phase3q 22 0.004
—		0.008
—		0.014
—		——
v2026-07-12_153204_phase3q 10 0.006
—		0.014
—		0.026
—		——
v2026-07-05_152333_phase3q 14 0.001
—		0.004
—		0.012
—		——
v2026-07-05_152333_phase3q 10 0.001
—		0.004
—		0.005
—		——
v2026-06-28_223429_phase3q 16 0.159
—		0.005
—		0.015
—		——
v2026-06-28_164125_phase3q
v2026-06-28_223429_phase3q		 8 0.315
—		0.003
—		0.006
—		——
v2026-06-21_152916_phase3q 18 0.049
—		0.009
—		0.017
—		——
v2026-06-14_153851_phase3q
v2026-06-21_152916_phase3q		 23 0.165
—		0.005
—		0.197
—		——
v2026-06-14_153851_phase3q 21 0.231
—		0.193
—		0.101
—		——
v2026-06-14_153851_phase3q 9 0.288
—		0.295
—		0.142
—		——

Dry window — Trengwainton — 6-hour

Phase 3b · v2026-10-04_160923 Δ +0.001 vs prev train

53-feature LightGBM per-(station, window). Trained 2026-10-04. Metric: Test Brier.

Lead Blend Best single Δ vs best
+24h 0.097 has_dry_window_icon (0.181) -46.4%
+48h 0.099 has_dry_window_ecmwf (0.221) -55.4%
+72h 0.103 has_dry_window_icon (0.235) -56.4%
Verify history (25 runs)

Mon + Thu rolling Brier. 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
v2026-09-06_155329 8 0.366
—		0.109
—		0.009
—		——
v2026-08-30_151956 24 0.057
—		0.123
—		0.063
—		——
v2026-08-30_151956 11 0.077
—		0.208
—		0.210
—		——
v2026-08-23_154535 18 0.275
—		0.257
—		0.346
—		——
v2026-08-23_154535 9 0.206
—		0.155
—		0.091
—		——
v2026-08-09_160228 36 0.131
—		0.190
—		0.179
—		——
v2026-08-09_160228 38 0.109
—		0.155
—		0.165
—		——
v2026-08-09_160228 21 0.006
—		0.002
—		0.004
—		——
v2026-08-09_160228 9 0.003
—		0.002
—		0.005
—		——
v2026-08-02_153831 19 0.090
—		0.037
—		0.014
—		——
v2026-08-02_153831 15 0.111
—		0.042
—		0.016
—		——
v2026-07-26_154121 20 0.017
—		0.015
—		0.009
—		——
v2026-07-26_154121 8 0.013
—		0.005
—		0.009
—		——
v2026-07-19_152707 22 0.011
—		0.005
—		0.006
—		——
v2026-07-19_152707 10 0.011
—		0.005
—		0.006
—		——
v2026-07-12_153030 22 0.023
—		0.006
—		0.011
—		——
v2026-07-12_153030 10 0.032
—		0.009
—		0.041
—		——
v2026-07-05_152159 14 0.010
—		0.004
—		0.007
—		——
v2026-07-05_152159 10 0.009
—		0.004
—		0.003
—		——
v2026-06-28_223313 16 0.150
—		0.006
—		0.005
—		——
v2026-06-28_164047
v2026-06-28_223313		 8 0.284
—		0.006
—		0.004
—		——
v2026-06-21_152700 18 0.064
—		0.008
—		0.010
—		——
v2026-06-14_153711
v2026-06-21_152700		 23 0.154
—		0.004
—		0.233
—		——
v2026-06-14_153711 21 0.209
—		0.157
—		0.149
—		——
v2026-06-14_153711 9 0.213
—		0.097
—		0.154
—		——

Phase 3q · v2026-10-04_161034_phase3q Δ +0.000 vs prev train

Phase 3q blender. Trained 2026-10-04. Metric: Test Brier.

Lead Blend Best single Δ vs best
+24h 0.000 — (0.000 val) —
+48h 0.000 — (0.000 val) —
+72h 0.000 — (0.000 val) —
Verify history (25 runs)

Mon + Thu rolling Brier. 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
v2026-09-06_155519_phase3q 8 0.278
—		0.114
—		0.029
—		——
v2026-08-30_152141_phase3q 24 0.059
—		0.095
—		0.148
—		——
v2026-08-30_152141_phase3q 11 0.075
—		0.108
—		0.255
—		——
v2026-08-23_154721_phase3q 18 0.255
—		0.282
—		0.262
—		——
v2026-08-23_154721_phase3q 9 0.172
—		0.190
—		0.178
—		——
v2026-08-09_160411_phase3q 36 0.145
—		0.143
—		0.197
—		——
v2026-08-09_160411_phase3q 38 0.117
—		0.126
—		0.169
—		——
v2026-08-09_160411_phase3q 21 0.008
—		0.020
—		0.041
—		——
v2026-08-09_160411_phase3q 9 0.008
—		0.004
—		0.019
—		——
v2026-08-02_154011_phase3q 19 0.084
—		0.043
—		0.037
—		——
v2026-08-02_154011_phase3q 15 0.104
—		0.049
—		0.026
—		——
v2026-07-26_154305_phase3q 20 0.018
—		0.013
—		0.037
—		——
v2026-07-26_154305_phase3q 8 0.012
—		0.013
—		0.018
—		——
v2026-07-19_152830_phase3q 22 0.009
—		0.007
—		0.025
—		——
v2026-07-19_152830_phase3q 10 0.009
—		0.006
—		0.018
—		——
v2026-07-12_153204_phase3q 22 0.010
—		0.019
—		0.033
—		——
v2026-07-12_153204_phase3q 10 0.015
—		0.029
—		0.052
—		——
v2026-07-05_152333_phase3q 14 0.005
—		0.011
—		0.027
—		——
v2026-07-05_152333_phase3q 10 0.004
—		0.012
—		0.014
—		——
v2026-06-28_223429_phase3q 16 0.127
—		0.013
—		0.033
—		——
v2026-06-28_164125_phase3q
v2026-06-28_223429_phase3q		 8 0.244
—		0.010
—		0.016
—		——
v2026-06-21_152916_phase3q 18 0.050
—		0.022
—		0.040
—		——
v2026-06-14_153851_phase3q
v2026-06-21_152916_phase3q		 23 0.143
—		0.015
—		0.184
—		——
v2026-06-14_153851_phase3q 21 0.212
—		0.198
—		0.100
—		——
v2026-06-14_153851_phase3q 9 0.289
—		0.358
—		0.406
—		——

Dry window — Lands End — 2-hour

Phase 3q · v2026-10-04_161035_phase3q Δ +0.000 vs prev train

Phase 3q blender. Trained 2026-10-04. Metric: Test Brier.

Lead Blend Best single Δ vs best
+24h 0.000 — (0.000 val) —
+48h 0.000 — (0.000 val) —
+72h 0.000 — (0.000 val) —
Verify history (no runs yet)

No verify rows yet for phase 3q. Next cycle: Mon/Thu 09:30 UTC, then 5d ERA5 latency.

Dry window — Lands End — 3-hour

Phase 3b · v2026-10-04_160942 Δ +0.000 vs prev train

53-feature LightGBM per-(station, window). Trained 2026-10-04. Metric: Test Brier.

Lead Blend Best single Δ vs best
+24h 0.027 has_dry_window_mf (0.093 val) -70.9%
+48h 0.027 has_dry_window_icon (0.173) -84.2%
+72h 0.030 has_dry_window_icon (0.150) -80.0%
Verify history (no runs yet)

No verify rows yet for phase 3b. Next cycle: Mon/Thu 09:30 UTC, then 5d ERA5 latency.

Phase 3q · v2026-10-04_161035_phase3q Δ +0.000 vs prev train

Phase 3q blender. Trained 2026-10-04. Metric: Test Brier.

Lead Blend Best single Δ vs best
+24h 0.000 — (0.000 val) —
+48h 0.000 — (0.000 val) —
+72h 0.000 — (0.000 val) —
Verify history (no runs yet)

No verify rows yet for phase 3q. Next cycle: Mon/Thu 09:30 UTC, then 5d ERA5 latency.

Dry window — Lands End — 4-hour

Phase 3b · v2026-10-04_160958 Δ +0.000 vs prev train

53-feature LightGBM per-(station, window). Trained 2026-10-04. Metric: Test Brier.

Lead Blend Best single Δ vs best
+24h 0.050 has_dry_window_mf (0.155 val) -67.4%
+48h 0.063 has_dry_window_icon (0.195) -67.9%
+72h 0.063 has_dry_window_icon (0.180) -64.9%
Verify history (no runs yet)

No verify rows yet for phase 3b. Next cycle: Mon/Thu 09:30 UTC, then 5d ERA5 latency.

Phase 3q · v2026-10-04_161035_phase3q Δ +0.000 vs prev train

Phase 3q blender. Trained 2026-10-04. Metric: Test Brier.

Lead Blend Best single Δ vs best
+24h 0.000 — (0.000 val) —
+48h 0.000 — (0.000 val) —
+72h 0.000 — (0.000 val) —
Verify history (no runs yet)

No verify rows yet for phase 3q. Next cycle: Mon/Thu 09:30 UTC, then 5d ERA5 latency.

Dry window — Lands End — 5-hour

Phase 3q · v2026-10-04_161035_phase3q Δ +0.000 vs prev train

Phase 3q blender. Trained 2026-10-04. Metric: Test Brier.

Lead Blend Best single Δ vs best
+24h 0.000 — (0.000 val) —
+48h 0.000 — (0.000 val) —
+72h 0.000 — (0.000 val) —
Verify history (no runs yet)

No verify rows yet for phase 3q. Next cycle: Mon/Thu 09:30 UTC, then 5d ERA5 latency.

Dry window — Lands End — 6-hour

Phase 3b · v2026-10-04_161015 Δ +0.000 vs prev train

53-feature LightGBM per-(station, window). Trained 2026-10-04. Metric: Test Brier.

Lead Blend Best single Δ vs best
+24h 0.102 has_dry_window_mf (0.292) -64.9%
+48h 0.114 has_dry_window_icon (0.248) -54.0%
+72h 0.125 has_dry_window_icon (0.188) -33.5%
Verify history (no runs yet)

No verify rows yet for phase 3b. Next cycle: Mon/Thu 09:30 UTC, then 5d ERA5 latency.

Phase 3q · v2026-10-04_161035_phase3q Δ +0.000 vs prev train

Phase 3q blender. Trained 2026-10-04. Metric: Test Brier.

Lead Blend Best single Δ vs best
+24h 0.000 — (0.000 val) —
+48h 0.000 — (0.000 val) —
+72h 0.000 — (0.000 val) —
Verify history (no runs yet)

No verify rows yet for phase 3q. Next cycle: Mon/Thu 09:30 UTC, then 5d ERA5 latency.