Air Quality Dataset

Air Quality Monitoring
Dataset

The air quality dataset of Italian cities from the UCI Machine Learning Repository, containing 9,357 hourly sensor records, covering concentrations of pollutants such as CO, NOx, C6H6, and meteorological data, suitable for time series analysis and sensor calibration research.

Get the Dataset Now
9,357 records 15 features CC BY 4.0 license S. De Vito et al. (2008)
Air Quality Dataset
📊
9,357
Total Records
🔬
15
Feature Dimensions
⏰
1 year
Collection Period
📜
CC BY 4.0
Open License Agreement

Dataset Highlights

Real environmental monitoring data, suitable for time series and sensor data analysis

🌆

Real Monitoring Data

Data comes from an outdoor air quality monitoring station in a city in Italy, recording complete hourly data for the year 2004-2005.

🔬

Multidimensional Sensors

Includes response data from 5 metal oxide sensors (CO, non-methane hydrocarbons, benzene, NOx, NO2).

🌡️

Meteorological Features

Simultaneously records temperature, relative humidity, and absolute humidity, allowing analysis of the impact of meteorological conditions on sensor performance.

⏰

Time Series Structure

Hourly timestamps make it very suitable for time series analysis, seasonal decomposition, and trend forecasting.

❓

Missing Value Handling

The dataset contains missing values encoded as -200, allowing practice in missing value detection and imputation techniques.

🏛️

UCI Authoritative Source

Originates from the UCI Machine Learning Repository, widely cited in sensor calibration and environmental monitoring research.

Applicable Scenarios

From environmental monitoring to sensor research, the application scenarios are extensive

🌍

Pollution Prediction

Predict trends in air pollutant concentration changes based on sensor and meteorological data

📡

Sensor Calibration

Calibrate low-cost metal oxide sensors using reference analyzer data

⏰

Time Series

Analyze daily and seasonal variations in air quality, practicing time series decomposition

🔧

Missing Value Handling

Handle a large number of missing values encoded as -200, practicing various imputation strategies

Environmental Monitoring Time Series Sensor Data Missing Value Handling Regression Analysis

Data Preview

The following are the first few rows of the air quality dataset (semicolon separated)

CSV
Date;Time;CO(GT);PT08.S1(CO);NMHC(GT);C6H6(GT);PT08.S2(NMHC);NOx(GT);PT08.S3(NOx);NO2(GT);PT08.S4(NO2);PT08.S5(O3);T;RH;AH
10/03/2004;18.00.00;2,6;1360;150;11,9;1046;166;1056;113;1692;1268;13,6;48,9;0,7578
10/03/2004;19.00.00;2;1292;112;9,4;955;103;1174;92;1559;972;13,3;47,7;0,7255
10/03/2004;20.00.00;2,2;1402;88;9,0;939;131;1140;114;1555;1074;11,9;54,0;0,7502
10/03/2004;21.00.00;2,2;1376;80;9,2;948;172;1092;122;1584;1203;11,0;60,0;0,7867

3 Steps to Get Started

From browsing to analysis, you can start your data science project in minutes

01

Browse the Dataset

View dataset details on the Ace Data Cloud platform, including field descriptions, sample size, and licensing agreements.

02

Download Data

Download the CSV file (755 KB), noting that the data uses semicolons as separators and commas as decimal points.

03

Load and Analyze

Use pandas.read_csv(sep=\";\") to load the data, replacing -200 with NaN before starting the analysis.

Get the Dataset

Start Exploring Air Quality Data

A classic environmental monitoring dataset, open license, available for immediate download. Complete hourly sensor data for a full year, ideal for time series analysis and sensor calibration research.

Get the Dataset Now