A Generative Model for Accelerated Inverse Modelling Using a Novel Embedding for Continuous Variables
This work addresses the problem of accelerated materials design for materials scientists by providing an incremental improvement in generative modeling techniques for inverse problems.
The paper tackled the challenge of rapid prototyping materials with desired properties by developing a novel embedding strategy for generative models based on binary representation of floating point numbers, which eliminates normalization and preserves information for conditioning on continuous variables, enabling fine control over generated microstructure images.
In materials science, the challenge of rapid prototyping materials with desired properties often involves extensive experimentation to find suitable microstructures. Additionally, finding microstructures for given properties is typically an ill-posed problem where multiple solutions may exist. Using generative machine learning models can be a viable solution which also reduces the computational cost. This comes with new challenges because, e.g., a continuous property variable as conditioning input to the model is required. We investigate the shortcomings of an existing method and compare this to a novel embedding strategy for generative models that is based on the binary representation of floating point numbers. This eliminates the need for normalization, preserves information, and creates a versatile embedding space for conditioning the generative model. This technique can be applied to condition a network on any number, to provide fine control over generated microstructure images, thereby contributing to accelerated materials design.