DS-03 · Tomorrow's air, from today's air and weather

Can you predict tomorrow's peak PM2.5 at a Richmond-area monitor better than "same as today"? Persistence is a genuinely hard baseline in air quality.

EPA Air Quality System pre-generated daily files (https://aqs.epa.gov/aqsweb/airdata/download_files.html). NOAA GHCN-Daily weather (https://www.ncei.noaa.gov/products/land-based-station/global-historical-climatology-network-daily).

Monitors go offline; missing days imputed as zero produce clean air that never happened. Wildfire smoke events are massive outliers that dominate error and are not predictable from local weather. Using tomorrow's weather as a feature is fine if forecast data is used, but using tomorrow's observed weather is leakage.

A next-day forecast evaluated against persistence and against a seasonal-average baseline, with the smoke-event days identified and reported separately rather than deleted quietly.

CT: recognizing that beating persistence is the real bar. CR: engineering features from wind and temperature that encode stagnation. CO: splitting monitor sites across a pair and comparing generalization. CM: a forecast card an asthma patient could act on. CZ: who changes their behavior on a bad-air day, and what a false "clean" prediction costs them.

An air-quality scientist, environmental engineer, or meteorologist reviews feature design at Checkpoint 1 and leakage checks at Checkpoint 2. School-supervised.

R1: one pollutant, one horizon, one site family. R2: missingness handled explicitly, never zero-filled. R3: persistence baseline present and beaten, or honestly not beaten. R4: outlier days reported, not deleted. R5: an actionable card. R6: false-negative cost stated in health terms.

(a) Missing days become zeros, the model learns that missing means clean, and the metric looks superb. (b) The student deletes wildfire days as "outliers," reports strong performance, and has built a model that fails precisely on the days anyone needed it.