THE RESULT
What the data shows
The largest computed metric is 1.018 for Median baseline; the smallest is 0.379 for Extra trees. Metric: mae (CO reference-unit MAE).
This estimates a simultaneous reference reading, not a future concentration. Test dates follow training among observed target rows.
| model | mae | rmse | r2 | bias |
|---|---|---|---|---|
| Median baseline | 1.018 | 1.348 | -0.005772 | -0.1021 |
| Ridge | 0.3842 | 0.6417 | 0.7722 | -0.1292 |
| Extra trees | 0.379 | 0.6204 | 0.7871 | -0.04536 |
THE METHOD
From source to answer
Chronological regression benchmark using sensors and environmental measurements, excluding other gas references.
The Python source exposes this study’s transformations. The complete project download includes shared preparation and evaluation routines.
EVALUATION
How the result was checked
First 80% of ordered observations train; final 20% test.
Fixed configurations specified before scoring; no tuning on the holdout.
Target and input features
Target: co_gt
Inputs: pt08_s1_co, pt08_s2_nmhc, pt08_s3_nox, pt08_s4_no2, pt08_s5_o3, t, rh, ah
THE NEXT DECISION
What follows from the finding
Validate on a later instrument period before filling reference gaps.
Where the conclusion stops
The -200 sentinel is treated as missing. Reference instruments have incomplete coverage; comparisons use paired observations. Sensor calibration is retrospective, not a health or regulatory compliance assessment.
Related studies may reuse observations or holdouts. These are historical analyses; associations and backtests do not demonstrate commercial impact. Further model tuning needs new, untouched evaluation data.