Climate health · Data science · Predict + report

Breathe

Predict the daily PM2.5 concentration at 250 monitoring sites across the United States from the weather, the season and the site.

Part of Season 1 — Four problems for the planet

upcoming

Cash prizes for the top three. Amounts are announced on Monday 2 November 2026 and paid after the audit. Prizes need a beaten baseline, a filed solution report and a reproducible pipeline — see the rules and terms.

Metric: MAE (lower is better)
Baseline: 3.401; The site's train-period mean for that calendar month
Honest model: 2.988; Default gradient-boosted tree on the shipped weather, site, region and calendar
Closes: 29 Nov 2026, 23:59 UTC; opens 5 Oct 2026, 00:00 UTC
Entrants: 0; 5/day · select 2

Overview

The problem. Fine particulate matter, PM2.5, is the largest environmental risk to human health: it drives heart and lung disease, and the WHO's 24-hour guideline is 15 µg/m³. Public-health alerts, school sports decisions and outdoor-work rules run on a day-level estimate of it, and most towns have no monitor at all. Your job: for 250 EPA monitoring sites, estimate the daily mean PM2.5 for every test day from that day's weather, the calendar and the site's own history.

The data. Train: January 2023 to March 2025, 199,231 site-days. Test: April to December 2025 at the same sites, 66,699 site-days. Each row has the site code, the date, the census division, coordinates to 0.5°, and NASA POWER daily weather at the site: temperature (mean, max, min), humidity, wind, precipitation, pressure and irradiance. The target is the EPA daily mean, µg/m³. No PM2.5 value on a test date is shipped, so persistence has to come from the training period.

Scoring. Mean absolute error in µg/m³, lower is better. Whole dates are public (30%) or private (70%) across every site; your standing is the private split.

Baselines (private split). The site's train-period mean for that calendar month: 3.40. A default gradient-boosted tree on the shipped columns: 2.99.

Why it matters. Wildfire smoke days are the tail, they are real, and they are where the metric is won or lost — and where an alert a day early keeps someone with asthma indoors.

How you are graded

70% the metric, 30% the report. Your selected submissions are scored on the withheld private split at close; your rank there becomes metric points (first of the field = 1, last = 0; below the baseline = 0). Your solution report is graded against the five criteria below by three independent, blind judges — two model families and one variant prompt — at temperature 0; each criterion takes the median level, and any spread of more than one level goes to a human. Final points = 70 × metric points + 30 × report score. Medals and prizes need a beaten baseline and a filed report; the top ten are audited by re-running their code from train.csv.

Criterion	Level 2 — Solid	Level 3 — Exemplary
Problem framing and impact	States the decision, the user and what a given error costs them.	As 2, and quantifies the value of the improvement over the baseline in the user's terms.
Data understanding and validation	A split that mirrors the test split; leakage risks named and handled.	As 2, with evidence the local validation tracks the public score, and a data finding that changed the approach.
Method and rigour	Choices justified, compared against both pinned baselines, at least one thing that failed reported honestly.	As 2, with an ablation or sensitivity check that shows which parts matter.
Error analysis and limitations	Shows where the model fails (segments, conditions) and gives a plausible reason.	As 2, and states the deployment risks: who is harmed if it is over-trusted, what would have to be monitored.
Reproducibility and clarity	Code, environment and steps that a reader could run; prose is clear and within length.	As 2, with fixed seeds, a one-command run, and results that match the report.

All four levels, the judge prompts, model ids and the calibration statistics are published with the results. Rules and terms.

Timeline

Mon, 5 Oct 2026OpensData released; submissions accepted.
Mon, 2 Nov 2026Mid-pointPrize pool announced; first clinic.
Sun, 29 Nov 2026ClosesReport and selections frozen; final 48 hours are the quiet period.
Mon, 7 Dec 2026ResultsPrivate standings, medals and the transparency pack. Seven days to appeal.

Data

Sources and licences

US EPA Air Quality System — daily summary, parameter 88101 PM2.5 FRM/FEM mass (2023, 2024, 2025 files) — US federal government work — public domain (17 U.S.C. §105) · retrieved 2026-09-21
US Environmental Protection Agency, Air Quality System (AQS) pre-generated daily summary files, parameter 88101.
NASA POWER daily meteorology and irradiance at each monitoring site (MERRA-2 / CERES) — NASA Earth-science data: full and open sharing, no restrictions on use (US government work) · retrieved 2026-09-21
Data obtained from the NASA Langley Research Center POWER Project, funded through the NASA Earth Science Directorate Applied Science Program.

Split. January 2023 to March 2025 is train; April to December 2025 is test, for the same sites. Within the test period, whole dates are public (30%) or private (70%) by a hash of the date across every site.

Changes made. Restricted to 250 sites in the 50 states and DC with ≥90% daily coverage, chosen at random from those eligible; 24-hour samples only, event-excluded records dropped, POCs averaged; joined to NASA POWER daily weather at the site; site ids replaced by opaque codes; coordinates rounded to 0.5°; state reduced to census division; rows shuffled; target removed from the test file.

Withheld. Site name, address and exact coordinates; State and county; The AQI and the 1-hour maximum; Any PM2.5 value on a test date (no lags are shipped).

Rows: train 199,231 · test 66,699 (public 18,463, private 48,236).

Artefact audit passed: No duplicate rows across train and test (0 of 66699 test rows have an identical feature row in train); 1-NN does not beat the honest model (1-NN mae 4.2531 vs honest 2.9876); No single feature encodes the target (strongest |corr| 0.170 (temp_max_c)); Row order is uncorrelated with the target (spearman(row index, target) = -0.004); The id does not encode the target (spearman(id number, target) = 0.001).

Wildfire smoke days are the tail: they are in the data, they are real, and they are where the metric is won or lost.

id	Row id (one per site-day). Use it in your submission.
site	Opaque monitoring-site code, consistent across train and test.
date	Local calendar date of the 24-hour sample.
division	US census division of the site (nine regions).
lat_r	Site latitude rounded to 0.5°.
lon_r	Site longitude rounded to 0.5°.
temp_c	Daily mean air temperature at 2 m, °C (NASA POWER).
temp_max_c	Daily maximum temperature, °C.
temp_min_c	Daily minimum temperature, °C.
rh_pct	Daily mean relative humidity at 2 m, %.
wind_ms	Daily mean wind speed at 10 m, m/s.
precip_mm	Daily precipitation, mm (bias-corrected).
pressure_kpa	Daily mean surface pressure, kPa.
ghi_kwh_m2	Daily all-sky surface shortwave downward irradiance, kWh/m²/day.
pm25	Target. Daily mean PM2.5 in µg/m³ at the site (train only). The WHO 24-hour guideline is 15.

Rules

One entry per person; your handle is fixed once you join. Entering means you accept the competition rules and terms.
Up to 5 submissions a day (resets 00:00 UTC). Select up to 2 for final scoring; if you select none, your best public score's file is used.
Train on the shipped data only. No external data beyond what the data card lists, and never the withheld targets from any source — looking them up is disqualification.
Your solution report (30% of your points) is written on this page and graded as it stands at close. Medals and prizes need a filed report and a beaten baseline; the top ten are audited by re-running their code from train.csv.
Sharing code or ideas publicly is fine; sharing a submission file is not (identical files are detected). One account per person. Text aimed at the grader scores zero.
The final 48 hours are the quiet period: the public board freezes for viewers while you still see your own scores. Results are published once, after the audit, and are final subject to appeal.

The full competition terms apply to every entry.