Realistic mask generation for matter-wave lithography via machine learning
This work addresses a critical bottleneck for the semiconductor and quantum device industries by enabling fast, high-resolution lithography as an alternative to EUV methods, though it is incremental as it builds on existing mask generation concepts with a new computational method.
The authors tackled the problem of generating realistic masks for matter-wave lithography, which is hindered by wavefront perturbations not accounted for in classical theory, by developing a machine learning approach that combines deep learning and genetic optimization to produce arbitrary 1D patterns with nanometre resolution.
Fast production of large area patterns with nanometre resolution is crucial for the established semiconductor industry and for enabling industrial-scale production of next-generation quantum devices. Metastable atom lithography with binary holography masks has been suggested as a higher resolution/low-cost alternative to the current state of the art: extreme ultraviolet (EUV) lithography. However, it was recently shown that the interaction of the metastable atoms with the mask material (SiN) leads to a strong perturbation of the wavefront, not included in existing mask generation theory, which is based on classical scalar waves. This means that the inverse problem (creating a mask based on the desired pattern) cannot be solved analytically even in 1D. Here we present a machine learning approach to mask generation targeted for metastable atoms. Our algorithm uses a combination of genetic optimisation and deep learning to obtain the mask. A novel deep neural architecture is trained to produce an initial approximation of the mask. This approximation is then used to generate the initial population of the genetic optimisation algorithm that can converge to arbitrary precision. We demonstrate the generation of arbitrary 1D patterns for system dimensions within the Fraunhofer approximation limit.