Home » AI start-up to create digital twin of Swiss city

AI start-up to create digital twin of Swiss city

by Liam Turner
Aerial photo of Lugano in Switzerland at night

Industrial AI and sensor startup NNAISENSE is set to create a digital twin of the city of Lugano in Switzerland.

The digital twin, created using third-generation AI technology with evolutionary reinforcement learning, will enable the municipality to create a virtual ‘situation room’ to solve real-world issues such as pollution and congestion.

It will also allow for the testing of policies in a digital ‘sandbox’ before implementing them in the real world.

Faustino Gomez, CEO and one of the founders of NNAISENSE, said: “We have a focus on the industrial space for monitoring, process control, and fully autonomous control that involved the two main technologies of neural networks on GPUs and modelling.

“The digital twin comes in as a special case of the process modelling effort. Because of what you can do with supervised learning and DNN, what you end up learning is a process model that learns the dynamics of the system you are modelling and learns the behaviour direct from the data.

“We have a third generation digital twin – you may augment it with data for predictive maintenance or as a simulator to improve control, but what you typically don’t do is use the data to create the model. You work from first principles or physics models.

“We have done things that you can’t do that way, direct from the data.”

Established in 2015, NNAISENSE has so far focussed on optimising industrial processes using large-scale sensor networks and third-generation machine learning to create sophisticated custom models without the need for training – technology now being applied to city-wide digital twin networks.

The company develops recurrent neural networks (RNNs), long short-term networks (LSTM) algorithms, and HighwayNets.

An RNN is a network of neurons with feedback connections that can learn many behaviours not achievable by traditional machine learning methods.

Artificial RNNs can learn algorithms that map inputs to outputs with or without teaching and so are computationally more powerful than other adaptive approaches.

Image: Dave Z/Shutterstock


Read next: Smart ways to update your construction project management practices in 2022

Are you a building professional? Sign up for a FREE MEMBERSHIP to upload news stories, post job vacancies, and connect with colleagues on our secure social feed.

Leave a Comment

Related News

Online building news, features and opinions

This website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish. Accept Read More