Published June 12, 2026 | Version v1

K-HEALTHinAIR — Pilot PL (Poland): Indoor Air Quality Analysis

  • 1. ROR icon Atos (Spain)

Description

# K-HEALTHinAIR — Pilot PL (Poland): Indoor Air Quality Analysis

## Overview

This dataset and set of analysis notebooks correspond to the **Polish pilot** of the K-HEALTHinAIR EU-funded project. The pilot monitors indoor and outdoor air quality in **schools** (SCH) and **residential homes** (HOM), with campaigns running from September 2023 to March 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 has two distinctive features: (1) a **microbiological component** that quantifies bacterial and fungal colony-forming units (CFU/m³) in school environments and relates them to occupancy, ventilation, and air purifier use; and (2) a **heating system analysis** that clusters homes according to their heating technology and resulting IAQ profiles.

---

## Contents

```
PL/
├── README.md
├── DataPreprocessing_PL_SCH.ipynb
├── EDA_PL_SCH.ipynb
├── EDA_PL_corr_I_O_file.ipynb
├── EDA_PL_SCH_corr_I_O.ipynb
├── EDA_PL_SCH_ventilation_approach01_v3.ipynb
├── EDA_PL_HOM_Clustering.ipynb
├── MCC_PL_SCH_Bacteria.ipynb
├── MCC_PL_SCH_Fungi.ipynb
└── Data/
    ├── PLHOM_*.csv          (4 files — residential homes, full scenario)
    ├── PLHOM02001_*.csv     (1 file  — single home area)
    └── PLSCH08002_*.csv     (1 file  — single school area)
```

---

## Notebooks

### `DataPreprocessing_PL_SCH.ipynb`
Preprocessing of raw school sensor data. Aggregates native-frequency measurements to hourly means and computes descriptive statistics per sensor area.

### `EDA_PL_SCH.ipynb`
Exploratory data analysis of school sensors. Includes descriptive statistics, Pearson and Spearman correlation matrices, intensity plots, 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 prediction, seasonal decomposition, lag plots, and rolling statistics.

### `EDA_PL_corr_I_O_file.ipynb`
File-level indoor–outdoor correlation analysis across all PL building types. Computes Pearson heatmaps and I/O ratios.

### `EDA_PL_SCH_corr_I_O.ipynb`
Indoor–outdoor correlation analysis specific to the school scenario, with sensor-level and area-level comparisons.

### `EDA_PL_SCH_ventilation_approach01_v3.ipynb`
Analysis of the effect of ventilation strategy on indoor air quality in schools. Evaluates how window-opening behaviour, mechanical ventilation, and cross-ventilation patterns influence CO₂, PM, and TVOC levels.

### `EDA_PL_HOM_Clustering.ipynb`
Unsupervised characterisation of residential homes. Homes are equipped with three different heating system types (HOM02, HOM04, HOM05). K-means and DBSCAN clustering combined with PCA and UMAP dimensionality reduction are used to identify IAQ profiles associated with each heating technology.

### `MCC_PL_SCH_Bacteria.ipynb`
Microbiological analysis of **bacterial** colony-forming units (CFU/m³) measured in school environments. Relates CFU concentrations to occupancy metrics (children/m³), window-opening fraction, cross-ventilation conditions, air purifier use, and outdoor reference CFU values.

### `MCC_PL_SCH_Fungi.ipynb`
Same microbiological analysis applied to **fungal** CFU concentrations. Evaluates the same environmental and occupancy predictors as the bacterial analysis.

---

## Data Files

### Column structure — full-scenario home files (`PLHOM_*`)

| Column | Description | Units |
|---|---|---|
| `_time` | Measurement timestamp (~5 min native resolution) | UTC datetime |
| `sub_scenario` | Sub-scenario code (e.g., `HOM05`) | — |
| `area` | Area identifier (e.g., `HOM05005`) | — |
| `sensor_id` | Anonymised sensor identifier (UUID) | — |
| `co2` | Indoor CO₂ | ppm |
| `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 |

### Column structure — single-area files (`PLHOM02001_*`, `PLSCH08002_*`)

These files correspond to a single monitored area and do not include the `sub_scenario` or `area` columns. All other indoor and outdoor columns are identical to the full-scenario format.

| Column | Description |
|---|---|
| `_time` | Measurement timestamp |
| `sensor_id` | Anonymised sensor identifier |
| *(indoor and outdoor columns as above)* | |

### File inventory

| File | Period | Scenario | Notes |
|---|---|---|---|
| `PLHOM_2023-09-01_2024-09-23.csv` | Sep 2023 – Sep 2024 | Homes | Full scenario |
| `PLHOM_2023-12-01_2024-03-01.csv` | Dec 2023 – Mar 2024 | Homes | Full scenario |
| `PLHOM_2024-01-01_2024-11-01.csv` | Jan–Nov 2024 | Homes | Full scenario |
| `PLHOM_2024-12-01_2025-03-01.csv` | Dec 2024 – Mar 2025 | Homes | Full scenario |
| `PLHOM02001_2024-01-01_2025-01-01.csv` | Jan 2024 – Jan 2025 | Home HOM02 / area 001 | Single area; no `sub_scenario`/`area` columns |
| `PLSCH08002_2024-12-30_2025-03-01.csv` | Dec 2024 – Mar 2025 | School SCH08 / area 002 | Single area; no `sub_scenario`/`area` columns |

Outdoor values are shared across all sensors in the same area (single reference station per area). Missing values are represented as empty cells. Multiple overlapping files for the same scenario represent different extraction windows used at different stages of analysis.

---

## Requirements

Python 3.10+. Main dependencies:

```
pandas, numpy, matplotlib, seaborn, scipy, scikit-learn,
statsmodels, umap-learn, 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

Polish pilot.zip

Files (209.6 MB)

Name Size
md5:a8e74f6dbf7c882bf70764ba2e982500
209.6 MB Preview Download

Additional details

Funding

European Commission
K-HEALTHinAIR - Knowledge for improving indoor AIR quality and HEALTH 101057693

Software

Programming language
Python