electricsheepafrica/africa-sensorsafrica-airquality-archive-meru-mobile-sensor

---
annotations_creators:
- no-annotation
language_creators:
- found
language:
- en
license: cc-by-4.0
multilinguality:
- monolingual
size_categories:
- 10K<n<100K
source_datasets:
- original
task_categories:
- tabular-regression
- other
task_ids: []
tags:
- africa
- humanitarian
- hdx
- electric-sheep-africa
- pm1
- pm10
- pm2.5
- airqu
- particulate-matter
- sensorsafrica-airquality-archive
pretty_name: "sensors.AFRICA Air Quality Archive Meru mobile sensor"
dataset_info:
splits:
- name: train
num_examples: 25460
- name: test
num_examples: 6365
---

# sensors.AFRICA Air Quality Archive Meru mobile sensor

**Publisher:** sensors.AFRICA · **Source:** [OpenAfrica](https://open.africa/dataset/sensorsafrica-airquality-archive-meru-mobile-sensor) · **License:** `cc-by` · **Updated:** 2025-07-15

---

## Abstract

This data set contains PM (particulate matter), temperature, and humidity readings taken with low-cost sensors. These sensors measure the concentration of PM in the air, including particles with diameters less than or equal to 1 micrometer (PM1), 2.5 micrometers (PM2.5), and particles with diameters less than or equal to 10 micrometers (PM10). The data set includes information on the sensor type, date, time, and location of the readings, as well as the sensor’s specific measurement values for Temperature (C), Humidity (%), PM1, PM2.5, and PM10. The data set is ideal for researchers and individuals interested in studying air quality and low-cost sensors in PM measurement. The dataset is stored in CSV format and can be opened using editors like Microsoft Excel, Google Sheets, LibreOffice Calc, etc. Note that P0 in the data represents PM1, P2 represents PM2.5, and P1 represents PM10

Each row in this dataset represents geolocated point observations. Data was last updated on OpenAfrica on 2025-07-15. Geographic scope: **SENSORSAFRICA-AIRQUALITY-ARCHIVE**.

*Curated into ML-ready Parquet format by [Electric Sheep Africa](https://huggingface.co/electricsheepafrica).*

---

## Dataset Characteristics

| | |
|---|---|
| **Domain** | Humanitarian and development data |
| **Unit of observation** | Geolocated point observations |
| **Rows (total)** | 31,825 |
| **Columns** | 3 (0 numeric, 3 categorical, 0 datetime) |
| **Train split** | 25,460 rows |
| **Test split** | 6,365 rows |
| **Geographic scope** | SENSORSAFRICA-AIRQUALITY-ARCHIVE |
| **Publisher** | sensors.AFRICA |
| **OpenAfrica last updated** | 2025-07-15 |

---

## Variables

**Geographic** — `sensor_id_sensor_type_location_lat_lon_timestamp_value_type_value` (908;pms5003;3651;0.000;0.000;2024-02-02T05:50:19.360254+00:00;P2;4.33, 896;pms5003;3654;0.000;0.000;2024-02-23T12:13:05.479636+00:00;P1;7.00, 897;DHT22;3654;0.000;0.000;2024-02-23T12:18:57.840442+00:00;temperature;34.00).

**Identifier / Metadata** — `esa_source` (HDX), `esa_processed` (2026-04-27).

---

## Quick Start

```python
from datasets import load_dataset

ds = load_dataset("electricsheepafrica/africa-sensorsafrica-airquality-archive-meru-mobile-sensor")
train = ds["train"].to_pandas()
test = ds["test"].to_pandas()

print(train.shape)
train.head()
```

---

## Schema

| Column | Type | Null % | Range / Sample Values |
|---|---|---|---|
| `sensor_id_sensor_type_location_lat_lon_timestamp_value_type_value` | object | 0.0% | 908;pms5003;3651;0.000;0.000;2024-02-02T05:50:19.360254+00:00;P2;4.33, 896;pms5003;3654;0.000;0.000;2024-02-23T12:13:05.479636+00:00;P1;7.00, 897;DHT22;3654;0.000;0.000;2024-02-23T12:18:57.840442+00:00;temperature;34.00 |
| `esa_source` | object | 0.0% | HDX |
| `esa_processed` | object | 0.0% | 2026-04-27 |

---

## Numeric Summary

| Column | Min | Max | Mean | Median |
|---|---|---|---|---|
_No numeric columns._

---

## Curation

Raw data was downloaded from OpenAfrica via the CKAN API and converted to Parquet. Column names were lowercased and standardised to snake_case. Common missing-value markers (`N/A`, `null`, `none`, `-`, `unknown`, `no data`, `#N/A`) were unified to `NaN`. The dataset was split 80/20 into train and test partitions using a fixed random seed (42) and saved as Snappy-compressed Parquet.

---

## Limitations

- Data originates from sensors.AFRICA and has not been independently validated by ESA.
- Automated cleaning cannot correct for misreported values, definitional inconsistencies, or sampling bias in the original collection.
- Refer to the [original HDX dataset page](https://open.africa/dataset/sensorsafrica-airquality-archive-meru-mobile-sensor) for the publisher's own methodology notes and caveats.

---

## Citation

```bibtex
@dataset{openafrica_africa_sensorsafrica_airquality_archive_meru_mobile_sensor,
title = {sensors.AFRICA Air Quality Archive Meru mobile sensor},
author = {sensors.AFRICA},
year = {2025},
url = {https://open.africa/dataset/sensorsafrica-airquality-archive-meru-mobile-sensor},
note = {Repackaged for machine learning by Electric Sheep Africa (https://huggingface.co/electricsheepafrica)}
}
```

---

*[Electric Sheep Africa](https://huggingface.co/electricsheepafrica) — Africa's ML dataset infrastructure. Lagos, Nigeria.*