San Diego Water Quality Project

In this data analysis project, volunteer data analysts are studying a range of public dataset to explore San Diego county water quality issues, such as beach closures and stream impairment. Volunteers join the project to learn new data analysis skills, get detailed knowledge of environmental issues, or to contribute to improving San Diego’s natural resources. Anyone is welcome to participate in the project.

Current Work: 10 Oct to 19 Nov, we are working on making submissions for a Water Quality Data Visualization Challenge.

Getting Started

If you’d like to join the project:

• Join the Mailing List/Google Group
• Attend a Meetup
• Join the #water channel on our Slack

After setting up your account, you should:

• Read the past project news.
• Study some of the example Jupyter notebooks for temporal correlations or logistic regression or other examples
• Find a ticket to work on.
• Come to the monthly meetings to show of your work, or to learn from others.
• Schedule office hours with the project manager, Eric Busboom, if you need more detailed help.

Project Resources

• Mailing List/Google Group
• The Github organization
• Google Drive File Share
• Data Repository
• Our Jupyter Lab server. Login with Github, after being listed on the access list

Datasets

The water-project tag in our Data Repository has all of the released datasets.

The two most important are:

• San Diego Beachwatch Data, With Features
• Tides, River Flow and Rain

All of the datsets can be built from source from our github repo.

Maps

• Interactive Station Map

Notebooks

• Beachwatch Exploration.ipynb
• Beachwatch Measurement Analysis.ipynb
• Beachwatch Stations.ipynb
• Beachwatch correlations.ipynb
• Beachwatch Logistic Regression.ipynb
• Beachwatch Seasonality.ipynb
• Tides Rain and River.ipynb
• SD River Streamflow EDA