Related Experiment Video
Updated: Aug 18, 2025

Vegetated Treatment Systems for Removing Contaminants Associated with Surface Water Toxicity in Agriculture and Urban Runoff
Published on: May 15, 2017
Impact of rainfall characteristics on urban stormwater quality using data mining framework
Haibin Yan1, David Z Zhu2, Mark R Loewen1
1Department of Civil and Environmental Engineering University of Alberta, Edmonton, AB T6G 1H9, Canada.
This study reveals that antecedent dry days, rainfall intensity, and duration significantly impact urban stormwater quality, unlike total rainfall volume. A novel rainfall type-based model improves stormwater quality predictions.
Area of Science:
- Environmental Science
- Hydrology
- Water Quality Management
Background:
- Effective urban stormwater management necessitates understanding how rainfall characteristics influence water quality.
- Existing models struggle to integrate rainfall-stormwater quality relationships due to complexities.
- Data mining offers a framework to address these challenges.
Purpose of the Study:
- To develop and evaluate a data mining framework for assessing rainfall impacts on urban stormwater quality.
- To introduce a rainfall type-based (RTB) calibration approach for enhancing water quality model performance.
- To identify critical rainfall characteristics influencing key stormwater pollutants.
Main Methods:
- Utilized principal component analysis and correlation analysis to examine rainfall-stormwater quality relationships.
- Employed K-means clustering to classify rainfall events into distinct types based on characteristics.
- Developed and calibrated RTB models for each rainfall type to optimize stormwater quality model parameters.
Main Results:
- Antecedent dry days, average rainfall intensity, and rainfall duration were identified as critical factors influencing event mean concentrations (EMCs) of total suspended solids, total nitrogen, and total phosphorus.
- Total rainfall volume showed negligible importance for stormwater quality.
- K-means clustering successfully categorized rainfall events into four representative types.
- The RTB model calibration significantly improved water quality model accuracy, reducing relative error by 11.4%–16.4% compared to traditional models.
Conclusions:
- The developed data mining framework and RTB calibration approach effectively improve urban stormwater quality modeling.
- Critical rainfall characteristics provide a robust basis for classifying events and calibrating models.
- Calibrated model parameters demonstrate transferability to similar catchments, enhancing practical application in stormwater management.
Related Concept Videos
Design Example: Analyzing Capacity Contours for Flood Risk Assessment
Responses to Drought and Flooding
Precipitation Processes
Precipitation and Co-precipitation
Precipitation Titration: Endpoint Detection Methods
In the Volhard method, a standard excess of AgNO3 is first added to the...
Applications of GIS: Disaster Management and Emergency Response

