SEMA-Berlin-1: Supporting Sewer Inspection and Investment Strategies

Recent studies about wastewater infrastructure in Germany show that current investments for sewer rehabilitation are not sufficient to tackle the aging and deterioration of the networks. In order to determine the extent of the damages and to support sewer rehabilitation planning, regular CCTV inspections are conducted. However, CCTV data are insufficient for the long-term definition of asset management strategies, since they deliver only a snapshot of the sewer condition at the time of its inspection.

To forecast the evolution of the system according to current and past observations through CCTV inspections, sewer deterioration models have been developed. These models can also be used to simulate the condition of non-inspected pipes. The results can be used to determine sewer inspection and cost-effective rehabilitation strategies.

Deterioration models are not commonly used by wastewater utilities, since there was still no evidence that the models were actually able to accurately predict future sewer conditions. Within the project SEMA, carried out by KWB from 2012 to 2015, this gap was closed. Based on a comprehensive inspection data set from the city of Braunschweig, Germany, the capability to reproduce the condition distribution of the sewer system has been successfully demonstrated.

Within the scope of SEMA-Berlin, these promising results will be verified with Berlin local data. After a thorough analysis of the sewer condition and its influencing factors, several statistical and data-driven modelling approaches will be tested to evaluate their prediction quality in Berlin, a crucial step for the further use of sewer deterioration models.

When embedding this video, cookies from third parties may be set. You must agree to this if you want to watch the video. You can change your decision later in the privacy settings.


Do you want to download “{filename}” {filesize}?

In order to optimally design and continuously improve our website for you, we use cookies. By continuing to use the website, you agree to the use of cookies. For more information on cookies, please see our privacy policy.