prop/docs
Graham McIntire f40e88e305
docs: plan for GFS-driven extended-horizon forecasts (18 h → 240 h)
HRRR caps at f018, so beyond ~18 hours the map and path calculator
go blank. This plan scopes a GFS open-data ingest that runs
alongside HRRR to drive the 18-240 hour forecast window, with a
visible seam on the timeline where the resolution drops from 3 km
to 0.25°.

Scope: GFS 0.25° CONUS subset from AWS S3, four runs/day on the
standard cycle, chained fetch/score workers that mirror the HRRR
pipeline shape, per-source binary score files so HRRR and GFS stay
independent. ECMWF IFS HRES listed as a follow-up once GFS works.
2026-04-18 12:35:08 -05:00
..
algo-reports feat(propagation): per-band weight calibration from full-corpus correlation 2026-04-18 10:19:26 -05:00
plans docs: plan for GFS-driven extended-horizon forecasts (18 h → 240 h) 2026-04-18 12:35:08 -05:00
research Phase 3 spike (parked) + Phase 6: temperature anomaly 2026-04-10 08:47:11 -05:00
algo_commercial.md Refactor HRRR fetch to batch points per hour 2026-03-30 17:21:47 -05:00
algo_original.md Refactor HRRR fetch to batch points per hour 2026-03-30 17:21:47 -05:00
algo_updated_with_data.md Refactor HRRR fetch to batch points per hour 2026-03-30 17:21:47 -05:00
analysis_output.txt Normalize ML features to prevent NaN gradient explosion 2026-04-01 09:08:33 -05:00
analysis_output_solar.txt Normalize ML features to prevent NaN gradient explosion 2026-04-01 09:08:33 -05:00
findings10.md Correct Finding 10: Great Lakes firing squad explains 24G PH anomaly 2026-04-01 11:07:58 -05:00
goes-r-research.md HRRR forecast hours (f00-f18) with timeline map UI 2026-03-31 16:44:47 -05:00
RRFS.md Add meteorologist feedback on model choice to RRFS doc 2026-03-31 09:27:23 -05:00