The disaster in July 2021 also caused a lot of damage to Andreas Groß’s company. The Wuppertal native has now developed a flood early warning system that is designed to learn for itself. It is already in use on the Wupper.

WZ, 04.01.2022

by Jörg Isringhausen

Wuppertal | On the night of July 14-15, Andreas Groß was standing knee-deep in the water that had flooded his company in Kohlfurth, Wuppertal, when he made a decision: to do everything humanly possible to ensure that such a catastrophe could not happen again. Around 90 percent of the Heinz Berger machine factory was flooded by the Wupper at the time, around 7500 of the 8000 square meters of factory space. Managing Director Groß and his employees desperately tried to push heavy machinery in front of the gates to push back the flood. “I thought we were going to lose the company,” he said. “That was the most difficult day of my life.” But it was also the birth of his flood early warning system.

In Groß’s view, the fact that he was able to consider developing such a procedure at all is due to a “favorable” constellation in retrospect. On the one hand, the Heinz Berger company had one of the highest loss totals in the Bergisch region; the motivation to protect itself from another crisis was therefore high. Secondly, it is a company that deals with machine construction, specifically with networked sensor technology and artificial intelligence (AI). Groß himself has a doctorate in the fields of AI and pattern recognition, and his company produces so-called intelligent agents, machines that are networked with one another. “Technically speaking, the topic of a networked warning system was nothing new,” says Groß.

Until then, there had been a total of four sensors along the course of the Wupper, two of which failed during the extreme flooding. As a result, it was of course no longer possible to obtain information about rising water levels, explains Groß, who then developed his own early warning system. His sensors, which are installed under bridges, measure the water level using ultrasound by registering the changing distance to the water surface from their position. The sensors are attached using a strong magnet and are equipped with a GPS positioning system and temperature sensors, among other things. Groß has already installed a total of 19 sensors along the Wupper and its tributaries in the Bergisch city triangle of Wuppertal-Remscheid-Solingen, with plans to install up to 50 along 116 kilometers of river. The sensors of the Wupper Association are also integrated. “This is the most closely meshed water level monitoring system in the whole of Wuppertal,” says the managing director.

However, the sensors alone are not enough for a reasonable forecast. Therefore, data on current precipitation levels from the entire region is added in order to calculate the development of water volumes in the rivers. Both the information on the water levels and the rainfall are transmitted to a computer via a so-called Long Range Wide Area Network, a common standard for data transmission in many cities. This can otherwise be used in urban areas to monitor traffic, control street lighting or determine whether waste containers are full, for example. “This system should be adaptive, i.e. self-learning, and calculate a potential risk from the data,” says Groß. The main aim is to give the affected regions a time advantage that will enable them to take precautions against the expected flooding. This stage is being worked on.

Groß would like to make the early warning system accessible to all citizens via an app. “It has to be public and free of charge,” he says, and it should be applicable to many different situations. For example, individual warning levels should be defined for residents and local water levels should be available online. The water levels could also be optimized in dry phases, for example during low water.

Groß, who is also the Vice President of the Bergisch Chamber of Industry and Commerce, hopes that his project will become a model project and attract interest in other flood regions. So far, he has invested around 80,000 euros in his system, but no subsidies have yet been received. However, Wuppertal’s public utility company is already on board, and the mayors of the three Bergisch towns and the University of Wuppertal are also supporting his project. Andreas Groß also plans to approach the NRW Ministry of Economic Affairs in the near future to secure funding for his project. “We simply want to show what is technically possible in flood prevention,” says the AI expert. “After all, this is a recurring topic that affects many people.”