In the race to create and contain zero-carbon nuclear fusion power, the newest contributor is DeepMind, Alphabet’s artificial intelligence lab.
Working with the Swiss Plasma Center at EPFL – a university in Lausanne, Switzerland – the DeepMind AI applied its algorithms to control the plasma inside the nuclear fusion reactor, which is hotter than the surface of the sun, and maintain its temperature long enough to to absorb energy. All of this was previously almost impossible.
Before we get into the scientific jargon, let’s break it down for you:
What is nuclear fusion
The best and most easily understood example of nuclear fusion energy is the sun. The process of nuclear fusion creates heat in the sun.
The generation of nuclear fusion energy in laboratories has proven difficult, as it consumes far more energy than it produces, making it unusable as a large-scale energy source.
Existing nuclear power plants use nuclear fission reactions, which produce energy by splitting atoms apart, a nuclear fusion reactor works in the opposite way, releasing energy by joining atoms.
Recently, the Joint European Torus (JET), a fusion reactor in Oxfordshire, UK, produced 59 megajoules of energy, equivalent to 11 megawatts of power, over a period of five seconds.
Also Read: British Scientists Make Major Breakthrough in Nuclear Fusion Energy: Everything You Need to Know
Scientists built a process that allowed plasma-state matter to self-heat through nuclear fusion, which could represent a major step toward exploiting nuclear fusion.
Accordingly Independent, The scientists took the hydrogen isotopes deuterium – found in seawater – and tritium, which is made in a reactor. They used the hydrogen isotopes to create a burning plasma.
In short, the researchers were able to compress and heat a plasma, which is then heated by the reactions themselves, allowing the energy to be self-sustaining.
Due to the enormous gravitational pressure in the core of the sun, nuclear fusion is possible at a temperature of around 10 million Celsius. Since it is not possible to generate such pressure on Earth, the temperatures must be much higher – over 100 million degrees Celsius.
Since no material can withstand such a temperature, fusion is achieved in a superheated gas or plasma held in an annular magnetic field.
The problems of obtaining nuclear fusion energy
Although scientists have succeeded in creating nuclear fusion energy, they still face a technical challenge – heating up the plasma and holding it together to extract energy from it.
The process of confining and controlling the plasma can use more energy than is produced from it, making it a counterproductive process.
To put it in perspective, the latest experiment at the JET lab generated enough power to boil 60 kettles for five seconds. Still, it was considered a major breakthrough.
Researchers have attempted to confine nuclear fusion reactions and use powerful magnetic coils to shape them into various shapes capable of maximum output.
In doing so, however, they must prevent the plasma from touching the walls, which would not only damage the walls but also waste heat. This slows down the nuclear fusion process.
What is DeepMind?
DeepMind, a division of Google’s parent company Alphabet, is responsible for developing general-purpose artificial intelligence technologies. The technology absorbs input and learns from experience.
DeepMind claims that its system is not pre-programmed: it learns from experience and only uses raw pixels as data input.
To put it simply, it used to be used to learn and play games alone. When tasked with beating the library of Atari games, it learned to understand the games and over time the AI could play the games better and more efficiently than humans.
The AI made headlines in 2016 when its AlphaGo program defeated Go World Champion Lee Sedol in a five-game match.
After proving its power playing video and board games, AI has been used in healthcare to detect eye diseases and kidney injuries, create computer programs, and is now making advances in nuclear fusion research.
DeepMind’s contribution to nuclear fusion research
According to a report by Business Insider, TThe artificial intelligence lab and its fellow researchers trained an algorithm on the Swiss Center’s simulator to hypothesize how best to control the magnetic coils using reinforcement learning.
This is where algorithms are effectively “rewarded” for achieving strong results.
It developed an architecture to receive the plasma, shaping it into various shapes while maintaining a separate plasma.
The algorithm was then applied to the real tokamak – a ring-shaped vacuum chamber using metal coils and a giant magnet to create sun-like conditions on Earth.
According to the report, the AI managed to manipulate the magnetic field for over two seconds, just like in the simulator.
“This work is a significant step in our understanding of how we might design new tokamaks that incorporate AI, and we expect the use of reinforcement learning in this area to become increasingly sophisticated in the future,” said Ambrogio Fasoli, director of Swiss Plasma center as quoted from Business Insider.
With contributions from agencies
Read all Latest news, Trending News, Cricket News, Bollywood News,
India News and entertainment news Here. follow us on facebook, Twitter and Instagram.
This article was previously published on Source link
