Researchers for the very fist time have used artificial intelligence(AI) to create complex three-dimensional simulations of the Universe. It is called the Deep Density Displacement Model, or D3M. It is so fast and so accurate that even the astrophysicists who have designed it have no clue how it does what it does.
To make the D3M functional, researchers have used a deep neural network. This neural network was fed with about 8000 different simulations from a highly accurate model. Neural networks are great since they are not only highly accurate but they’re also quite adaptive, and mimics the human brain. But what they need is to be trained with an extensive data set to make them work properly. Furthermore, researchers also ran simulations of a “box-shaped universe 600 million light-years across” and compared its results with both, slow and fast models where D3M performed brilliantly.
“It’s like teaching image-recognition software with lots of pictures of cats and dogs, but then it’s able to recognize elephants,” study co-author Shirley Ho, a theoretical astrophysicist at the Center for Computational Astrophysics in New York City, said in a statement. “Nobody knows how it does this, and it’s a great mystery to be solved.”
The fact that D3M is able to handle such “parameter variations” with so much ease makes it a very useful and a flexible tool for the researchers. Now, researchers want to further explore modeling hydrodynamics and dive deeper into the internal workings of the model. The model might also be a time-saver for researchers interested in universal origins. The new neural network can easily complete simulations in 30 milliseconds, compared to several minutes for the fastest non-artificial intelligence simulation method. The network also had an error rate of 2.8%, compared with 9.3% for the existing fastest model.
The research has been published in PNAS.