A new AI-based study was able to shed some light into the cloudy depths of Jupiter. The atmospheres of planets like Jupiter, however, crush matter with millions of pounds of pressure. In the most extreme circumstances, hydrogen’s atom’s covenant bonds break down and the material becomes more like a metallic solid then things get interesting. The field of astronomy seeks to understand the physical nature of gas giants and other worlds, but that knowledge has turned out to be quite elusive.
Its All About Phase
To understand more about whats going on, researchers have to take a look at hydrogen’s phase diagram. A phase diagram shows how a material’s physical properties vary with pressure and temperature. Hydrogen is already very well understood when it comes to its less exotic states. There is, however, a gap in knowledge that has inspired several studies to find just where to draw the line. Humanity has a lot to learn about the relationship between molecular liquid hydrogen and its solid counterpart, but it’s really hard to make those kinds of pressures in a lab. That’s where this new AI-based study comes in.
Physicists have recently been able to use computer simulations to model hydrogen under extreme conditions. Quantum and statistical mechanics were used to simulate interactions between atoms. These models predict that under intense pressure, hydrogen undergoes a sudden first-order phase-transition. It transforms to an atomic state from a molecular state. It’s important to note that these results can be applied to a gas giant’s interior. When doing that happens it points towards the possibility of distinct boundaries between conductive and insulating layers.
Plenty of Room for Advancement
The problem is that researches have faced quite a serious limitation. This has cast a bit of doubt on the theories. Bingqing Cheng explains at the University of Cambridge, ‘Even state-of-the-art methods can only model hundreds of hydrogen atoms. Since we were previously restricted to using such small system sizes, the first-order transition was assumed.
More atoms increase complexity. That is the fundamental problem with simulation. This is due to quantum interactions. Larger models would end up being far beyond the capabilities of today’s most powerful supercomputers. This is why this AI-based study can help. Cheng and his colleagues in Switzerland and the UK approached this project with machine learning. Machine learning builds models of highly complex systems by training itself on real data.
An AI-Based Study Was The Way to Go
Machine learning drastically reduced required computing power. It enabled the team to simulate more than 1700 atoms across a wide range of pressures and temperatures. Cheng further explained, ‘In a nutshell, we exploited machine learning techniques to learn the atomic interactions from quantum mechanics. The inputs to the neural network were the positions of each atom and the outputs were the energy and forces they experience.’
Cheng’s team had access to larger simulated samples. This helped them to discover that the molecular-to-atomic transitions. As it turns out, they don’t happen as a clearly defined boundary, as previously thought. Hydrogen, as it turns out, undergoes a smooth transition as the pressure increases. This phenomenon happens past a ‘critical point’ in the phase diagram. That’s where higher pressures and temperatures make the physical distinction between metal and liquid vanish. So, this means that the transformation between hydrogen’s conductive and insulating phases happens both continuously and gradually.
A New Understanding
Uncovering this ‘supercritical’ behavior of hydrogen using this AI-based study could have seriously implications. It could help humanity better understand material science. It could help help understand how planets work. As Cheng describes, his team’s discovery provides a much more accurate view of how hydrogen exists deep inside giant gas worlds. ‘Inside these bodies, the insulating and the metallic layers have a smooth density profile between them, instead of an abrupt change,’ he explained.
This would make a big impacts on the planetary sciences. Beyond that, researchers think the results highlight a promising potential for artifical intelligence. As it turns out, it’s great at exploring the hydrogen phase diagram. Cheng said, ‘We believe machine learning will not only change the way high pressure hydrogen is modelled, but will be in the standard toolbox of computational physicists. With machine learning, we can run nanosecond-scale simulations with thousands of atoms, with first principle accuracy. This was beyond our wildest dreams just ten years ago.’
University of Salford researcher John Proctor suggests that exploring this work for planetary interiors will not be a simple task. John wen’t on to say, ‘We propose that there is no first order liquid-liquid transition in hydrogen, and that planetary models assuming this therefore need to be revised. Since the actual interiors of Jupiter and Saturn do not consist of pure hydrogen – they are fluid mixtures predominantly composed of hydrogen and helium – a lot of further work is required to fully explore the implications of this work for planetary science.’
In other space-related news, SpaceX successfully landed its Falcon 9 booster for the 59th time.