K-HEALTHinAIR — Pilot AT (Austria): Indoor Air Quality Analysis
Description
# K-HEALTHinAIR — Pilot AT (Austria): Indoor Air Quality Analysis
## Overview
This dataset and set of analysis notebooks correspond to the **Austrian pilot** of the K-HEALTHinAIR EU-funded project. The pilot monitors indoor and outdoor air quality in two building types: **residential homes** (HOM) and **schools** (SCH), with campaigns spanning from March 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.
A distinctive feature of this pilot is the integration of IAQ measurements with **health questionnaire filling dates**, enabling the computation of aggregated exposure statistics in the 2 and 7 days prior to each questionnaire response. The pilot also includes a **historical VOC analysis** covering archived measurements from 2001 to 2023.
---
## Contents
```
AT/
├── README.md
├── DataPreprocessing_AT_SCH.ipynb
├── EDA_AT_corr_I_O_file.ipynb
├── EDA_AT_HOM_Clustering.ipynb
├── AT_oldVOC_analysis.ipynb
└── Data/
├── ATHOM_*.csv (9 files — residential homes)
├── ATSCH_*.csv (4 files — schools, raw)
└── ATSCH_*_calculated_statistics_*.csv (2 files — aggregated statistics)
```
---
## Notebooks
### `DataPreprocessing_AT_SCH.ipynb`
Preprocessing of raw school sensor data. Aggregates raw measurements to hourly means and computes descriptive statistics (mean, max, min, median, std) for each sensor area over 2-day and 7-day windows aligned to health questionnaire filling dates (working hours 08:00–16:00). Outputs the `_calculated_statistics_*` CSV files.
### `EDA_AT_corr_I_O_file.ipynb`
Exploratory data analysis of indoor–outdoor relationships across both HOM and SCH scenarios. Includes Pearson correlation heatmaps between indoor pollutants and outdoor reference variables, and quantification of the indoor–outdoor (I/O) ratio to identify periods when outdoor air is the dominant pollution source.
### `EDA_AT_HOM_Clustering.ipynb`
Unsupervised analysis of residential homes. Homes equipped with different heating systems are characterised and grouped using K-means clustering with PCA and UMAP dimensionality reduction. The goal is to identify IAQ profiles associated with different heating technologies.
### `AT_oldVOC_analysis.ipynb`
Statistical analysis of a historical VOC dataset from Austrian buildings (2001–2023, ~1 125 measurements, ~50 compounds). Applies Centered Log-Ratio (CLR) transformation, PCA, K-means clustering, Pearson correlation matrix, and PERMANOVA to characterise compositional changes over time. Outputs a multi-sheet Excel report with figures embedded.
---
## Data Files
### Column structure — raw sensor files (`ATHOM_*`, `ATSCH_*`)
All raw CSV files share the following columns:
| Column | Description | Units |
|---|---|---|
| `_time` | Measurement timestamp (~5 min native resolution) | UTC datetime |
| `sub_scenario` | Sub-scenario code (e.g., `HOM04`, `SCH02`) | — |
| `area` | Area identifier (e.g., `HOM04001`) | — |
| `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 |
Outdoor values are shared across all sensors in the same area (single reference station per area). Missing values are represented as empty cells.
> **Note:** `ATSCH_*` files include the additional column `out_pm25`; `ATHOM_*` files do not.
### Column structure — aggregated statistics files (`ATSCH_*_calculated_statistics_*.csv`)
Pre-computed descriptive statistics linked to health questionnaire events. Wide format: one row per (area, filling date) pair.
| Column group | Description |
|---|---|
| `Area` | Sensor area identifier |
| `Filling Date-long` | Datetime of the questionnaire filling event |
| `Mean/Max/Min/Median/Std {param}` | Statistics computed over the 2-day or 7-day window prior to the filling date (working hours only) |
Parameters covered: CO₂, TVOCs, PM₁, PM₂.₅, PM₁₀, Humidity, Temperature.
### File inventory
| File | Period | Scenario |
|---|---|---|
| `ATHOM_2023-03-01_2023-09-22.csv` | Mar–Sep 2023 | Homes |
| `ATHOM_2023-12-01_2024-02-28.csv` | Dec 2023 – Feb 2024 | Homes |
| `ATHOM_2023-12-01_2024-03-01.csv` | Dec 2023 – Mar 2024 | Homes |
| `ATHOM_2024-01-01_2024-02-01.csv` | Jan–Feb 2024 | Homes |
| `ATHOM_2024-01-01_2024-05-01.csv` | Jan–May 2024 | Homes |
| `ATHOM_2024-03-01_2024-06-06.csv` | Mar–Jun 2024 | Homes |
| `ATHOM_2024-04-01_2024-05-01.csv` | Apr–May 2024 | Homes |
| `ATHOM_2024-07-01_2024-11-01.csv` | Jul–Nov 2024 | Homes |
| `ATHOM_2024-12-01_2025-03-01.csv` | Dec 2024 – Mar 2025 | Homes |
| `ATSCH_2023-12-01_2024-03-01.csv` | Dec 2023 – Mar 2024 | Schools |
| `ATSCH_2024-01-01_2024-12-12.csv` | Jan–Dec 2024 | Schools |
| `ATSCH_2024-01-01_2024-12-19.csv` | Jan–Dec 2024 | Schools |
| `ATSCH_2024-12-01_2025-03-01.csv` | Dec 2024 – Mar 2025 | Schools |
| `ATSCH_2024-01-01_2024-12-12_calculated_statistics_2days.csv` | Jan–Dec 2024 | Schools (aggregated) |
| `ATSCH_2024-01-01_2024-12-12_calculated_statistics_7days.csv` | Jan–Dec 2024 | Schools (aggregated) |
Multiple overlapping files for the same scenario represent different extraction windows used at different stages of analysis; they are not exact duplicates.
---
## Requirements
Python 3.10+. Main dependencies:
```
pandas, numpy, matplotlib, seaborn, scipy, scikit-learn,
statsmodels, scikit-bio, 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
Austrian pilot.zip
Additional details
Funding
Software
- Programming language
- Python