Checklist OPEIA 2026 Virtual Phase · ML task
Sentinel of the Metropolis
Build a soft sensor that estimates a carbon-monoxide sensor response in Lima from temperature, humidity and nitrogen-oxide readings.
The task
Lima's humidity, weak winds and ageing vehicle fleet trap pollutants under a thermal inversion, and precise CO sensors degrade quickly. Contestants predict the tin-oxide CO sensor response PT08.S1(CO) from Temp_Lima, Humedad_Relativa, Emisiones_Diesel (NO₂) and NOx(GT). Sensors report −200 on failure, in both features and target, and these values must be handled.
Split: 6,549 training rows (70%), 1,872 validation rows (20%, public leaderboard) and 936 test rows (10%, private leaderboard).
Abridged by SOTA from the official materials. The official statement has the exact rules, and it wins wherever this summary differs.
At a glance
- You get
X_train.csv,y_train.csv,X_val.csv,X_test.csv,sample_submission.csv.- You submit
- CSV with Id (
val_0…val_1871,test_0…test_935) and y (2,808 rows). - Scoring
- RMSE (lower is better).
- Rules
- Solutions must be reproducible; the notebook used must also be submitted.
- Up to 5 submissions per day.
- Only the free version of ChatGPT may be used as an assistant (OPEIA page).
- Format
- OPEIA 2026, a single virtual phase on Kaggle (the OPEIA page gives 19 March – 5 April 2026; the public Kaggle competitions show a window of 23–24 April 2026).