METRAQ: Madrid Hourly Air Quality, Meteorology and Traffic Dataset (2001-2024)

Provider
David María-Arribas, Alejandra Abalo-García, Antonio S. Montemayor, Juan J. Pantrigo, Alfredo Cuesta-Infante (Universidad Rey Juan Carlos)
License
MIT (source)
Size
27 files
Format
CSV (in sampled files)
Stored at
Hugging Face (https://huggingface.co/datasets/dmariaa70/METRAQ-Air-Quality)
Access
Free and public. No account with the data provider is needed.
DOI
10.57967/hf/5519
Category
Environmental Science
Source
https://github.com/dmariaa/metraq-aq

About METRAQ: Madrid Hourly Air Quality, Meteorology and Traffic Dataset (2001-2024)

METRAQ is an hourly air-quality dataset for the city of Madrid, Spain, built from the Madrid City Council open data portal and aligned with meteorology and road traffic for forecasting and spatio-temporal imputation of pollutant concentrations. It holds measurements of up to 14 pollutants (including NO2, NO, NOx, O3, PM10, PM2.5, CO, SO2 and benzene) from the municipal monitoring network, with up to seven meteorological parameters since 2019 and three traffic metrics since 2015, interpolated to the monitoring stations with five methods. The enriched subset has 64,881,744 records over 210,384 hourly timestamps: 25.5 million air-quality, 8.8 million meteorological and 30.5 million traffic rows. Files are 24 yearly CSVs (metraq_aq-2001.csv to 2024, about 6 GB). The authors provide baseline forecasting and imputation models in the companion repository github.com/dmariaa/metraq-aq. Read with pandas. Released under the MIT License by David María Arribas (card and LICENSE file); cite María-Arribas et al. 2025 (doi:10.57967/hf/5519).

How to load this dataset in Python

import pandas as pd
df = pd.read_csv("hf://datasets/dmariaa70/METRAQ-Air-Quality/metraq_aq-2001.csv")
df.head()

Data structure

File types in sampled files: CSV

Files

Example file: metraq_aq-2001.csv

Analyze this dataset without downloading it

On Scigantic, METRAQ: Madrid Hourly Air Quality, Meteorology and Traffic Dataset (2001-2024) opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

This page is also available as Markdown and as JSON.

Related Environmental Science datasets