Prediction of water quality and its impact in the treatment steps

Province of North Holland, Netherlands

Prediction of water quality and its impact in the treatment steps


PWN supplies drinking water to over 800,000 customer connections in the province of North Holland. The company is well aware of the rise of digital water in the context of environmental challenges and technological opportunities and is in the process of digitalization itself. Central aspects of this development for PWN are the creation of a data lake and a digitalization vision and roadmap. However, the data lake and associated data flows have not been fully made into an integral part of PWN’s processes yet, and the finalization and implementation of the vision and roadmap will take time as well. The current state of development, the groundwork that has been laid, and the ambitions of PWN make an excellent combination both for feeding requirements and use cases into the creation of water data spaces and providing test beds for their implementation and testing.


  • The challenge PWN has to face in the next years is fundamentally how to match data from various sources and bring them together, making data more accessible within the organization (security, policy, governance concerns) and to other stakeholders.

  • At this moment, typically raw files are shared through email, while validation, cleaning and data pre-processing are done manually.

  • Typical problems are related to time series, and issues with data types, column names, missing values, date-time formats, duplicated, encoding issues.

  • More standardization activities are required both with respect to the generation of new data and to the usage of existing external data sources


The main objectives are:

  • Collection and harmonization of heterogeneous data.

  • Sharing of the collected data after its preparation.

  • Federation of external data to make them available to PWN teams.

The improved data provision and flow within PWN resulting from this project will:

  • Allow the company to optimize their technical and business processes;

  • also have better control on the interaction between different parts of the water supply chain (sources, treatment, transport & distribution), and;

  • better inform and engage other stakeholders in the challenges of the regional water system in a changing climate.