Related papers: Empirical modeling and hybrid machine learning fra…

Simulating water from first principles remains a significant computational challenge due to the slow dynamics of the underlying system. Although machine-learned interatomic potentials (MLPs) can accelerate these simulations, they often fail…

Physics-informed machine learning (PIML) represents an emerging paradigm that integrates various forms of physical knowledge into machine learning (ML) components, thereby enhancing the physical consistency of ML models compared to purely…

We introduce the Hierarchically Interacting Particle Neural Network (HIP-NN) to model molecular properties from datasets of quantum calculations. Inspired by a many-body expansion, HIP-NN decomposes properties, such as energy, as a sum over…

Accurate hydrological understanding and water cycle prediction are crucial for addressing scientific and societal challenges associated with the management of water resources, particularly under the dynamic influence of anthropogenic…

The ability to perform ab initio molecular dynamics simulations using potential energies calculated on quantum computers would allow virtually exact dynamics for chemical and biochemical systems, with substantial impacts on the fields of…

This work is the second in a series focused on ferrofluid bend channel flows. Here, ferrofluid flows in bend channels are modeled using machine learning methods, based on data generated from the CFD simulation discussed in the first work in…

Oxide-water interfaces govern a wide range of physical and chemical processes fundamental to many fields like catalysis, geochemistry, corrosion, electrochemistry, and sensor technology. Near solid oxide surfaces, water behaves differently…

We develop inductive biases for the machine learning of complex physical systems based on the port-Hamiltonian formalism. To satisfy by construction the principles of thermodynamics in the learned physics (conservation of energy,…

This study employed an artificial intelligence-enhanced molecular simulation framework to enable efficient Path Integral Molecular Dynamics (PIMD) simulations. Owing to its modular architecture and high-throughput capabilities, the…

The availability of property data is one of the major bottlenecks in the development of chemical processes, often requiring time-consuming and expensive experiments or limiting the design space to a small number of known molecules. This…

Microchannel heat sinks (MCHS) are widely used for thermal management in high-power electronics due to their ability to dissipate large heat fluxes with minimal coolant consumption. While numerous strategies - such as geometric…

Soft particles such as microgels and core-shell particles can undergo significant and anisotropic deformations when adsorbed to a liquid interface. This, in turn, leads to a complex phase behavior upon compression. Here we develop a…

Hydrogen bubble formation within nanoscale voids is a critical mechanism underlying the embrittlement of metallic materials, yet its atomistic origins remains elusive. Here, we present an accurate and transferable machine-learned potential…

Machine learning (ML) can facilitate efficient thermoelectric (TE) material discovery essential to address the environmental crisis. However, ML models often suffer from poor experimental generalizability despite high metrics. This study…

Edge plasma turbulence is critical to the performance of magnetic confinement fusion devices. Towards better understanding edge turbulence in both theory and experiment, a custom-built physics-informed deep learning framework constrained by…

A theoretical model for the effect of water hydrogen bonding on the thermodynamics of hydrophobic hydration is proposed as a combination of the classical density functional theory with the recently developed probabilistic approach to water…

One of the ultimate goals of computational modeling in condensed matter is to be able to accurately compute materials properties with minimal empirical information. First-principles approaches such as the density functional theory (DFT)…

Data-driven techniques are increasingly used to replace electronic-structure calculations of matter. In this context, a relevant question is whether machine learning (ML) should be applied directly to predict the desired properties or be…

In this work, physical dealloying was explored as a simple and green method to microstructure the surface of commercial brass for pool boiling heat transfer coefficient enhancement. Three samples were dealloyed for 0.5, 1 and 3 hours at 650…

High-intensity laser plasma interactions create complex computational problems because they involve both fluid and kinetic regimes, which need models that maintain physical precision while keeping computational speed. The research…