Digital twins: What are they and why do they matter?

In 1949, the one-time crocodile hunter and economist Bill Phillips built a machine that simulated the dynamics of the British economy. His two-metre tall contraption used pipes, valves, tanks, pumps and water to model a range of economic variables. By opening and closing valves, the flow of the water would change to show, for example, how interest rate rises might affect savings and investments. Philips’ machine was quickly adopted not only at universities, but also by large companies across the globe.

You could say that the ‘‘Moniac” was the analogue forerunner of modern digital twin technology.

Digital twins are mathematical models that recreate a physical object or system. This could be a factory, a power plant or even a ski resort, to name just a few possibilities.

A variety of sensors installed on and around the real-world object record data about different aspects of its performance. This could include things such as energy output, temperature, weather conditions – any information that is relevant and recordable.

With the help of artificial intelligence (AI) and machine learning, the digital twin can analyze performance issues or run virtual “what if” simulations – similar to Phillips’ Moniac. The data and discoveries can subsequently be applied to the real-world object.

The big difference from traditional simulations is that digital twins use real-time data for their modelling. This enables experimentation with large objects or projects that don’t typically lend themselves to real-life experimentation due to their size – think buildings, jet engines or manufacturing sites.

By the mid-2020s, the global market for digital twins in the manufacturing industry alone is expected to reach more than $6 billion. That’s more than a tenfold increase from 2020, according to data from Statista.

The automotive and aviation sectors are not far behind with their take-up of these virtual replicas. The energy, healthcare, logistics and retail industries are also expected to expand their use of digital twins on a similar scale.

Digital twin technology is already helping to boost efficiency and productivity in factories, as well as at wind turbines and with other power generation equipment. Vehicle manufacturers are drawing on the technology to improve vehicle design and streamline how their plants operate.

Digital modelling also accelerated the design and construction of vaccine plants in the US during the COVID-19 pandemic. The technology was used to capture and analyze the layout of existing plants, and the insights helped improve the design and workflows of the new facilities.

In agriculture, AI is increasingly being used to boost crop yields, particularly for staples such as corn, soy and wheat. Using digital twin technology, farm-management company CropX has now taken this one step further.

Its system uses sensors to monitor soil and crop conditions, as well as the weather. This data feeds into digital analysis and planning tools for growers, enabling them to make more informed decisions to maximize yields.

With the UN warning that food crops are increasingly threatened by droughts and other natural events, such solutions could become important to ensuring food security for the growing world population.

Digital twins can even be scaled up to encompass an entire city.

Orlando in the US state of Florida has been digitally replicated in 3D, Bloomberg reports. This virtual model will be used to simulate how different urban planning projects will impact the environment and residents. Other US cities already use the technology for traffic management and to drive down emissions.

Among the most advanced users of digital twins is Singapore. Its 3D virtual model is made up of millions of images taken at street level and from the air. Along with corresponding data points, there are more than 100 terabytes of data covering anything from the tree cover and the city’s infrastructure to individual buildings – down to their roofs, facades and windows. This means new developments or plans can be modelled with great precision.

Digital twin technology is expected to play a key part in Singapore’s battle for sustainability and against rising temperatures, according to Bloomberg.

In the US state of Colorado, the fire service is working with 3D digital twins from graphics company Nvidia to visualize and study the spread of forest fires in order to improve prevention and help contain fires more effectively.

With 3D models proliferating, digital twin technology is progressing rapidly towards the metaverse, which promises to create a virtual world where people can work, socialize and shop.

Any digital world will need digital people, and just as a factory or power plant can have a virtual twin, so too can humans – and we’re talking much more than just an avatar.

A digital twin of a healthcare patient could help that person to track a variety of healthcare indicators. Digital human twins could also help simulate the impact of new strategies in urban transportation or social services, to determine the most effective approaches.

However, a big question mark hanging over the evolution from digital twins to the metaverse is the associated environmental impact. This is because high-end data storage and processing is an energy-hungry process. The rise in energy demand thanks to the growth of the Bitcoin market is an example of this. What chunk of power the metaverse will require – and how this will affect the environment – will only become clear as it evolves.

The World Economic Forum will discuss digital twins and the metaverse as part of the Tech and Innovation theme at the Annual Meeting in Davos 2022.