Managing river pollution has recently emerged as one of the most pressing concerns globally. This blog post by Hannah Banton explores how data science, facilitated through DataCamp Donates, empowered the creation of one of the most crucial updates that we provide each year, the Sewage Map.

The Rivers Trust are experts in river conservation, and make use of a wealth of data to enhance our work. Hence our decision to partner with DataCamp, an organisation which provides a comprehensive online learning platform for Data Science education. Their DataCamp Donates programme aims to improve our world through data literacy by offering free access to the platform for disadvantaged users, students and research scientists.

Through their programme, DataCamp has provided free premium access to their data science education platform to the Rivers Trust movement which includes the 65 Member Trusts and their volunteers across Britain, Northern Ireland and Ireland.

With the skills and knowledge obtained from DataCamp training, our movement can process and analyse data more effectively, improving our decision making and making our work in improving rivers more effective.

This was particularly evident in our work to create the Sewage Map update for this year. The main aim of the Sewage Map project is to visually represent sewage pollution across the UK’s rivers. The genesis of this project was driven by the need to address a significant environmental issue—sewage discharge, which affects water quality and threatens aquatic life and human health. However, the main challenge was in conveying such complex data in an accessible manner. Rivers Trust technical analyst Harry, found his learning from DataCamp instrumental in his processing of the sewage data to create the map.

This was particularly evident in our work to create the Sewage Map update for this year. The main aim of the Sewage Map project is to visually represent sewage pollution across the UK’s rivers. The genesis of this project was driven by the need to address a significant environmental issue—sewage discharge, which affects water quality and threatens aquatic life and human health. However, the main challenge was in conveying such complex data in an accessible manner. Rivers Trust technical analyst Harry, found his learning from DataCamp instrumental in his processing of the sewage data to create the map.

"When Thames Water first released their near real-time CSO spill data as an API, it was important for us to add live data to our Sewage Map. To do this, we had to access the data via an API, process the data, and then add the updated data to a web map.

"To make sure I had the skills to do this, I completed the Python Fundamentals skill track in DataCamp, which covered topics on cleaning, manipulating, and analysing real-world data, as well as other key Python skills. I then completed the Intermediate Importing Data in Python course, which explains how to import data from APIs. All this, plus a bit of practicing, allowed me to pull in the live data and publish it to our own Sewage Map, displaying real-time data for the Thames catchment.

"This is not the end of my journey using DataCamp to make sewage data available. I am in the process of using my learnings from the Machine Learning Fundamentals with Python track to model downstream sewage movement and will expand on my earlier work to make near real-time sewage data available nationwide once all water companies have data accessible through a national hub with an API."

The Sewage Map has significantly impacted environmental advocacy and policy-making. It serves as a vital tool for the Rivers Trust, aiding in educational campaigns and regulatory discussions.

Data-driven environmental science is clearly pivotal in enhancing our river conservation work at the Rivers Trust. Some other success stories from our partnership include our Technical Director working with an Alan Turing Intern and formulating a business case for employing our first Artificial Intelligence Specialist by exploring the machine learning courses from DataCamp. Other learners have found courses on data types and purposes useful in collaborative citizen science projects. Our Technical Analysts have found the Python coding courses valuable to write scripts to pull information from our shared datasets and government APIs. Other technical leads have found the Data Engineering tutorials useful to guide the process of merging fish monitoring datasets from multiple local Rivers Trusts and sharing with the environmental regulator to aid in decision making.

Equipping our researchers with advanced data skills helps us to delve deeper into key ecological issues and therefore develop more targeted and effective solutions. More broadly, this could lead to more informed decisions and robust environmental policies. Partnerships like that between DataCamp Donates and the Rivers Trust can revolutionise environmental science. DataCamp Donates not only advanced our mission but also demonstrated the transformative power of data science in addressing global environmental challenges. We are pleased to be able to renew our partnership with DataCamp Donates again this year.