Dark Mode
Seoul Pollution Trends Cleaned
Data Science and Analytics
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
Air quality measurements captured across Seoul, South Korea, spanning the years 2017 to 2020. This collection aggregates hourly readings for six standard air pollutants, providing a robust foundation for environmental analysis and time-series forecasting. The data has been processed to exclude instrument errors, specifically removing lines with negative or zero readings to ensure analytical reliability. It facilitates the comparison of 2020 atmospheric conditions against the preceding three years, aiding in the development of predictive models and pollution trend assessments.
Columns
- Measurement date: Date and hour of recorded measurement (DateTime).
- Station code: Unique identifier for the station where data was collected.
- SO2: Sulphur dioxide concentration.
- NO2: Nitrogen dioxide concentration.
- O3: Ozone concentration.
- CO: Carbon monoxide concentration.
- PM10: Particulate matter 10 micrometres or less in diameter.
- PM2.5: Particulate matter 2.5 micrometres or less in diameter.
Distribution
- Format: CSV
- Size: 49.79 MB
- Rows: Approximately 866,000 records
- Structure: Tabular
Usage
- Predictive Modelling: Forecasting future air quality levels based on historical patterns (2017–2019).
- Trend Analysis: Comparing actual 2020 pollution data against predicted values or historical baselines.
- Visualisation: Creating temporal plots and geographic heatmaps using libraries such as Pandas and Plotly.
- Environmental Research: Assessing the impact of urban activity on specific pollutant levels like PM2.5 and NO2.
Coverage
- Geographic Scope: Seoul, South Korea.
- Time Range: January 2017 to December 2020.
- Data Availability Notes: Lines containing negative or zero instrument readings have been filtered out to maintain data integrity.
License
CC BY-SA 4.0
Who Can Use It
- Data Scientists working on time-series forecasting.
- Environmental Researchers monitoring urban pollution.
- Civic Planners analysing air quality trends.
- Machine Learning Engineers training regression models.
Dataset Name Suggestions
- Seoul Air Quality Hourly 2017-2020
- Seoul Pollution Trends Cleaned
- Atmospheric Pollutants Seoul Time-Series
Attributes
Original Data Source:Seoul Pollution Trends Cleaned
QUALITYLoading...