K-HEALTHinAIR — Pilot NO (Norway): Indoor Air Quality Analysis
Description
# K-HEALTHinAIR — Pilot NO (Norway): Indoor Air Quality Analysis
## Overview
This dataset and set of analysis notebooks correspond to the **Norwegian pilot** of the K-HEALTHinAIR EU-funded project. The pilot monitors indoor and outdoor air quality in **canteens** (CAN) and **university lecture halls** (LEC), with campaigns running from November 2023 to January 2025.
These analyses are intended to be used with data collected from sensors as deployed in the pilot sites. The data provided is the subset filtered by pilot owners from the K-HEALTHinAIR platform to carry out specific analysis.
This pilot includes **formaldehyde** as an indoor measurement parameter across all building types. The lecture hall deployment additionally records **outdoor atmospheric pressure** and **outdoor VOC concentrations**, making it the only pilot with outdoor VOC data.
---
## Contents
```
NO/
├── README.md
├── EDA_NO_CAN.ipynb
├── EDA_NO_corr_I_O_file.ipynb
├── EDA_NO_corr_I_O.ipynb
└── Data/
├── NOCAN_*.csv (2 files — canteens)
└── NOLEC_*.csv (1 file — lecture halls)
```
---
## Notebooks
### `EDA_NO_CAN.ipynb`
Exploratory data analysis of canteen sensors. Includes descriptive statistics, Pearson and Spearman correlation matrices, boxplots, normality testing (Shapiro–Wilk), stationarity testing (ADF), air quality threshold assessment (CO₂ < 900 ppm; WHO-adapted TVOC categories; PM limits), logistic regression for working-day vs. non-working-day classification (60–77% accuracy across sensor areas), seasonal decomposition, lag plots, autocorrelation analysis, and rolling statistics.
### `EDA_NO_corr_I_O_file.ipynb`
File-level indoor–outdoor correlation analysis across all NO building types. Computes Pearson heatmaps, I/O ratios, and evaluates the relative contribution of outdoor air to indoor pollutant levels.
### `EDA_NO_corr_I_O.ipynb`
Indoor–outdoor correlation analysis with additional detail, including sensor-level comparisons and temporal stratification.
---
## Data Files
### Column structure — canteen files (`NOCAN_*`)
| Column | Description | Units |
|---|---|---|
| `_time` | Measurement timestamp (~5 min native resolution) | UTC datetime |
| `sub_scenario` | Sub-scenario code (e.g., `CAN02`) | — |
| `area` | Area identifier (e.g., `CAN02001`) | — |
| `sensor_id` | Anonymised sensor identifier (SHA hash) | — |
| `co2` | Indoor CO₂ | ppm |
| `formaldehyde` | Indoor formaldehyde | µg/m³ |
| `humidity` | Indoor relative humidity | % |
| `pm1` | Indoor PM₁ | µg/m³ |
| `pm10` | Indoor PM₁₀ | µg/m³ |
| `pm25` | Indoor PM₂.₅ | µg/m³ |
| `temperature` | Indoor temperature | °C |
| `tvocs` | Indoor total VOCs | ppb |
| `out_co` | Outdoor CO | mg/m³ |
| `out_humidity` | Outdoor relative humidity | % |
| `out_no2` | Outdoor NO₂ | µg/m³ |
| `out_o3` | Outdoor O₃ | µg/m³ |
| `out_pm10` | Outdoor PM₁₀ | µg/m³ |
| `out_pm25` | Outdoor PM₂.₅ | µg/m³ |
| `out_so2` | Outdoor SO₂ | µg/m³ |
| `out_temperature` | Outdoor temperature | °C |
### Additional columns in lecture hall files (`NOLEC_*`)
The lecture hall file contains all columns listed above, plus:
| Column | Description | Units |
|---|---|---|
| `out_pressure` | Outdoor atmospheric pressure | hPa |
| `out_vocs` | Outdoor VOC concentration | ppb |
### File inventory
| File | Period | Scenario |
|---|---|---|
| `NOCAN_2023-03-01_2024-07-30.csv` | Mar 2023 – Jul 2024 | Canteens |
| `NOCAN_2024-01-01_2025-01-01.csv` | Jan–Dec 2024 | Canteens |
| `NOLEC_2024-01-01_2025-01-01.csv` | Jan–Dec 2024 | Lecture halls |
Outdoor values are shared across all sensors in the same area (single reference station per area). Missing values are represented as empty cells.
---
## Requirements
Python 3.10+. Main dependencies:
```
pandas, numpy, matplotlib, seaborn, scipy, scikit-learn,
statsmodels, openpyxl
```
---
## License
Copyright (C) 2021–2026 Advanced Computing Spain SL – BULL.
Released under the **GNU General Public License v3.0**.
See <https://www.gnu.org/licenses/> for the full text.
---
## Acknowledgements
This work was carried out within the K-HEALTHinAIR project, funded by the European Union. Views expressed are those of the authors only and do not necessarily reflect those of the European Union or the funding agency.
Files
Norwegian pilot.zip
Additional details
Funding
Software
- Programming language
- Python