Predicting compositional changes of organic–inorganic hybrid materials with Augmented CycleGAN

Abstract

Despite its simplicity, the composition of a material can be used as input to machine learning models to predict a range of materials properties. However, many property optimization tasks require...

Using generative adversarial networks to match experimental and simulated inelastic neutron scattering data

“…25,26,28 Whereas GANs have been applied a few times in materials science, [31][32][33][34][35][36] unpaired image-to-image translation, which is frequently done with CycleGANs, has only been applied in few instances. 37,38 While CycleGANs are somewhat restricted in their applicability; 25,26,39 recent papers have employed contrastive learning to ensure similarity by teaching the network to ensure a degree of structural similarity between corresponding patches in the input and output images (white-white pairs, Figure 1) but not necessarily between non-corresponding patches of the input and output images (whitegrey pairs, Figure 1). 25,26 The process is optimized via a patch-wise contrastive loss;…”

“…25,26,28 While GANs have been applied a few times in materials science, 31–36 unpaired image-to-image translation, which is frequently done with CycleGANs, has only been applied in few instances. 37,38…”

What is missing in autonomous discovery: open challenges for the community

“…An open challenge is the incorporation of generative models 139–141 for compositions, 142–146 crystals, 147–152 and molecules 142,153–156 in SDLs. While being very successful in finding hypothetical molecules with tailormade properties, i.e.…”

“…Relating back to our discussions around data (Section 2), the availability of data would allow researchers to evaluate novel algorithms on multiple surrogate systems based on real experiments, while the absence of such datasets could considerably impede the development of dedicated algorithms and create obstacles for the development of autonomous platforms. 137,138 An open challenge is the incorporation of generative models [139][140][141] for compositions, [142][143][144][145][146] crystals, [147][148][149][150][151][152] and molecules 142,[153][154][155][156] in SDLs. While being very successful in nding hypothetical molecules with tailormade properties, i.e.…”

Using generative adversarial networks to match experimental and simulated inelastic neutron scattering data

“…25,26,28 Whereas GANs have been applied a few times in materials science, [31][32][33][34][35][36] unpaired image-to-image translation, which is frequently done with CycleGANs, has only been applied in few instances. 37,38 While CycleGANs are somewhat restricted in their applicability; 25,26,39 recent papers have employed contrastive learning to ensure similarity by teaching the network to ensure a degree of structural similarity between corresponding patches in the input and output images (white-white pairs, Figure 1) but not necessarily between non-corresponding patches of the input and output images (whitegrey pairs, Figure 1). 25,26 The process is optimized via a patch-wise contrastive loss;…”