Physics-guided AI reconstructs hidden patterns inside ultrathin magnets from external fields
To build faster and more energy-efficient computers, researchers need to understand nanoscale magnetic materials. But looking inside these tiny magnets is surprisingly difficult: Modern microscopes only measure the magnetic field outside the material, not the magnetic pattern inside. Because many different internal patterns can produce the exact same field, working backwards has long been a…
Physicists at the University of Vienna and collaborators have developed a method to reconstruct hidden magnetic patterns inside ultrathin magnets using only external magnetic fields. This breakthrough could significantly advance the development of faster, more energy-efficient computers and data storage devices. Traditional microscopes can only measure the magnetic field outside these tiny magnets, but the internal structure remains a mystery due to the vast number of possible internal arrangements that can produce identical external fields.
The Vienna-led team combined machine learning with fundamental magnetism laws to build an algorithm that evaluates possible magnetic patterns and selects the most realistic one, automatically ruling out any that violate basic physical laws. By incorporating the laws of physics directly into the machine learning method, the researchers were able to accurately determine both the magnetic pattern and the distance between the sensor and the sample.
This approach eliminates the major source of error associated with estimating sensor height, resulting in a far more reliable reconstructed map. The study, published in Physical Review Letters, demonstrates the method using diamond quantum sensors and is open source, allowing other researchers to apply the framework to their own measurements.
Written by urgent.news from Phys.org's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
