Related papers: Deep Kernel Bayesian Optimisation for Closed-Loop …
Many deep generative models are defined as a push-forward of a Gaussian measure by a continuous generator, such as Generative Adversarial Networks (GANs) or Variational Auto-Encoders (VAEs). This work explores the latent space of such deep…
It is well-known that the microstructure of electrodes in lithium-ion batteries strongly affects their performance. Vice versa, the microstructure can exhibit strong changes during the usage of the battery due to aging effects. For a better…
Metal anodes provide the highest energy density in batteries. However, they still suffer from electrode/electrolyte interface side reactions and dendrite growth, especially under fast-charging conditions. In this paper, we consider a…
The properties of rechargeable lithium-ion batteries are determined by the electrochemical and kinetic properties of their constituent materials as well as by their underlying microstructure. Microstructural design can be leveraged to…
Understanding how to structure a porous electrode to facilitate fluid, mass, and charge transport is key to enhance the performance of electrochemical devices such as fuel cells, electrolyzers, and redox flow batteries (RFBs). Using a…
Generative adversarial networks (GANs) are a machine learning technique capable of producing high-quality synthetic images. In the field of materials science, when a crystallographic dataset includes inadequate or difficult-to-obtain…
Identifying the key microstructure representations is crucial for Computational Materials Design (CMD). However, existing microstructure characterization and reconstruction (MCR) techniques have limitations to be applied for materials…
Porous flow-through electrodes are used as the core reactive component across electrochemical technologies. Controlling the fluid flow, species transport, and reactive environment is critical to attaining high performance. However,…
The key challenge in advancing multivalent-ion batteries lies in finding suitable intercalation hosts. Open-tunnel oxides, featuring one-dimensional channels or nanopores, show promise for enabling effective ion transport. However, the vast…
Micro-CT scanning of rocks significantly enhances our understanding of pore-scale physics in porous media. With advancements in pore-scale simulation methods, such as pore network models, it is now possible to accurately simulate multiphase…
The performance of all-solid-state battery (ASSB) cathodes strongly depends on their microstructure. Optimizing the cathode morphology can therefore enhance effective macroscopic properties such as ionic and electronic conductivity. The…
Nanostructured electrodes with voids or interconnected pores accommodate large volume changes, shorten ion diffusion pathways, and enhance the structural reversibility of alloying electrodes. While these nanoporous features improve the…
Recently, considerable efforts have been made on research and improvement for Ni-rich lithium-ion batteries to meet the demand from vehicles and grid-level large-scale energy storage. Development of next-generation high-performance…
The structure of lithium ion battery components, such as electrodes and separators, are commonly characterised in terms of their porosity and tortuosity. The ratio of these values gives the effective transport of lithium ions in the…
Synthetic microbiomes offer new possibilities for modulating microbiota, to address the barriers in multidtug resistance (MDR) research. We present a Bayesian optimization approach to enable efficient searching over the space of synthetic…
Kernel-based nonparametric models have become very attractive for model-based control approaches for nonlinear systems. However, the selection of the kernel and its hyperparameters strongly influences the quality of the learned model.…
Deep neural networks have been applied in wireless communications system to intelligently adapt to dynamically changing channel conditions, while the users are still under the threat of the malicious attacks due to the broadcasting property…
In generative modeling, numerous successful approaches leverage a low-dimensional latent space, e.g., Stable Diffusion models the latent space induced by an encoder and generates images through a paired decoder. Although the selection of…
Learning controller parameters from closed-loop data has been shown to improve closed-loop performance. Bayesian optimization, a widely used black-box and sample-efficient learning method, constructs a probabilistic surrogate of the…
Variable-density cellular structures can overcome connectivity and manufacturability issues of topologically optimized structures, particularly those represented as discrete density maps. However, the optimization of such cellular…