Graham McIntire 07558d17eb Two-phase training: pretrain on algorithm scores, fine-tune on QSOs ... - 15 features: add surface_refractivity and latitude - Bigger network: 128→64→32 (3 hidden layers) - Phase 1: pretrain on 500K stratified algorithm scores (all seasons/locations) - Phase 2: fine-tune on 57K real QSO-HRRR matched data (percentile target) - Lower LR (0.0003) for fine-tuning to preserve pretrained knowledge - Model.train accepts :initial_state option for transfer learning		2026-04-01 09:27:27 -05:00
..
band_config.ex	Use local solar time for time-of-day scoring, add PWAT factor and pressure refinements	2026-04-01 08:58:21 -05:00
freshness_monitor.ex	Prevent duplicate PropagationGridWorker jobs via Oban unique constraint	2026-03-31 17:16:40 -05:00
grid.ex	Increase grid to 0.125 degrees with smooth canvas overlay	2026-03-31 08:52:07 -05:00
grid_score.ex	Add CONUS grid definition and propagation score schema	2026-03-30 16:50:06 -05:00
model.ex	Two-phase training: pretrain on algorithm scores, fine-tune on QSOs	2026-04-01 09:27:27 -05:00
scorer.ex	Use local solar time for time-of-day scoring, add PWAT factor and pressure refinements	2026-04-01 08:58:21 -05:00