Heterogeneous catalysis is key for chemical transformations. Understanding how catalyst active sites dynamically evolve at the atomic scale under reaction conditions is a prerequisite for accurate determination of catalytic mechanisms and predictably developing catalysts. We combine in-situ observation and Machine Learning accelerated first-principle atomistic simulations to uncover the mechanism of restructuring for Pt catalysts under a pressure of carbon monoxide CO. We show that a high CO coverage at a Pt step edge triggers the formation of atomic protrusions of low-coordination Pt atoms, that then detach from the step edge to create sub-nano-islands on the terraces, where undercoordinated sites are stabilized by the CO adsorbates. These studies open an avenue to achieve an atom-scale understanding of structural dynamics of more complex metal nanoparticles under reaction.

In this work we explore the task of learning filters for the dual-tree complex wavelet transform [9, 17]. This transform was introduced to address several shortcomings of the separable, real-valued wavelet transform algorithm. However, the dual-tree transform requires greater care when designing filters. The added complexity makes the transform a good candidate to replace the traditional filter derivations with learning. We demonstrate that it is possible to learn filters for the dual-tree complex wavelet transform in a similar fashion to [16, 15]. We show that very few changes to the original autoencoder framework are necessary to learn filters that overcome the limitations of the separable 2D wavelet transform. Wavelet representations have been shown to perform well on a variety of machine learning tasks. Specifically, wavelet scattering networks have shown stateof-the-art results despite the fact they use a fixed representation (in contrast to the learned representations of convolutional neural networks) [2, 11, 3, 12].