An effective MLOps workflow developed within the Datalab team

The Waternet Datalab team aims to deliver projects that are actually implemented.  A robust MLOps workflow is essential to this. As part of the Datalab team, we set up the MLOps workflow and continue to maintain it. This includes an MLflow model registry, CI/CD templates, and deploying code and models to production. For example, we developed a machine learning model to minimise nitrous oxide emissions at a water treatment plant. We are now developing a model to reduce the use of iron chloride in the pretreatment of river water for drinking water production.