Zaandam, the Netherlands, September 16, 2021 – The first Kickstart AI challenge of the founding companies Ahold Delhaize, ING, KLM, NS and Philips has successfully concluded. The team, consisting of AI experts from all five organizations, created an early warning system to predict an expected increase in the number of COVID-19 hospitalization cases. A first version of this model has been produced and transferred to the Landelijke Meldkamer Samenwerking (LMS) and the Instituut Fysieke Veiligheid (IFV). The model is now offered to the safety regions for sustainable use and assessment via the jointly developed platform of the IFV and the LMS.
Predicting by using sewage water data
In partnering with the IFV and the LMS, the Kickstart AI COVID-Challenge team wanted to create an early warning system to better understand how COVID-19 developed in a given geographic area, national and/or regional. They learned that by using sewage water they could accurately measure the presence of germs and viruses, and these measurements can act as an early warning for upcoming virus outbreaks. These measurements, being taken at more than 300 sewage treatment plants across the Netherlands, create the perfect opportunity for an important element for the localized early warning system, by tracking in which municipalities the coronavirus is increasing or decreasing. The technique that has been employed to predict the trend is part of an ongoing Ph.D. research program, making this project a successful partnership between academia and real-life application.
A first version of the early warning system has already been produced and handed over to the LMS and the IFV for further development and sustainable use. The team managed to deliver its predictions in a production-ready and platform-agnostic way, leading to a smooth transfer and easy operation of the code and models. The developed model is an addition to human intuition and is expected to easily meet the minimally required accuracy for valuable usage.
Promoting AI capabilities in the Netherlands
The Kickstart AI COVID Challenge has proven to be a great way to bring together professionals and exchange experiences. Together they build valuable products that serve the broader society. Erick Webbe, Head of Data Science at bol.com, a great local brand of Ahold Delhaize, and Kickstart AI COVID-Challenge Lead said, “We brought together a team to promote the AI capability within the Netherlands and applied that to a very relevant use case. We successfully built a solution that has been adopted for sustainable use and the team is proud to have successfully transferred its project to meaningfully contribute to society in the fight against COVID-19.”
About Kickstart AI
Kickstart AI is a platform aimed at boosting the AI ecosystem in the Netherlands by accelerating and promoting the development of AI technology and nurturing AI talent in the country. The goal of Kickstart AI is to bridge the gap between the Netherlands and other leading countries that have made notable progress in Artificial Intelligence. The platform is driven by five Dutch companies: Ahold Delhaize, ING, NS, KLM and Royal Philips. This joint effort will add educational capacity, foster the development of the AI community in the Netherlands, and reiterate the position of the Netherlands as a competitive and relevant global AI hub.
For more information visit https://www.kickstartai.nl/
This communication includes forward-looking statements. All statements other than statements of historical facts may be forward-looking statements. Words and expressions such as will, be, further, strategy, until Fall 2021 or other similar words or expressions are typically used to identify forward-looking statements.
Forward-looking statements are subject to risks, uncertainties and other factors that are difficult to predict and that may cause actual results of Koninklijke Ahold Delhaize N.V. (the “Company”) to differ materially from future results expressed or implied by such forward-looking statements. Such factors include, but are not limited to, the risk factors set forth in the Company’s public filings and other disclosures. Forward-looking statements reflect the current views of the Company’s management and assumptions based on information currently available to the Company’s management. Forward-looking statements speak only as of the date they are made and the Company does not assume any obligation to update such statements, except as required by law.