Graham McIntire 10cbbf47b3 Train ML model on real QSO-HRRR data instead of algorithm scores ... Features: HRRR conditions averaged at both QSO endpoints + solar time Target: distance_km normalized per-band (distance / p99_range, capped at 1.0) This trains on actual propagation outcomes from 57K+ QSOs, not the hand-tuned algorithm output.		2026-04-01 09:13:05 -05:00
..
microwaveprop	Normalize ML features to prevent NaN gradient explosion	2026-04-01 09:08:33 -05:00
microwaveprop_web	Default forecast timeline selection to closest hour to now	2026-03-31 17:45:54 -05:00
mix/tasks	Train ML model on real QSO-HRRR data instead of algorithm scores	2026-04-01 09:13:05 -05:00
microwaveprop.ex	initial	2026-03-28 11:28:47 -05:00
microwaveprop_web.ex	initial	2026-03-28 11:28:47 -05:00