Related papers: Amending CALPHAD databases using a neural network …
Accelerated design of novel hard coating materials requires state-of-the-art computational tools, which include data-driven techniques, building databases, and training machine learning models against the databases. In this work, we present…
Lennard-Jones (LJ) fluids serve as an important theoretical framework for understanding molecular interactions. Binary LJ fluids, where two distinct species of particles interact based on the LJ potential, exhibit rich phase behavior and…
There currently exist no quantitative methods to determine the appropriate conditions for solid-state synthesis. This not only hinders the experimental realization of novel materials but also complicates the interpretation and understanding…
The on-wing engine performance is difficult to track for thermodynamic models because of its inaccurate component maps, and also difficult for data driven methods for their over-fitting to measurement errors. So, we propose a thermodynamic…
Vibrational properties of solids are key to determining stability, response and functionality. However, they are challenging to computationally predict at Ab-Initio accuracy, even for elemental systems. Ab-Initio methods for modeling atomic…
Nuclear power plant operators face significant challenges due to unpredictable deviations between offline and online thermal limits, a phenomenon known as thermal limit bias, which leads to conservative design margins, increased fuel costs,…
In CALPHAD-type thermodynamic databases, nonstoichiometric compounds are typically described by sublattice models where the sublattice site fractions represent the occupation probability of different atomic, ionic or defect species on…
Targeted free energy perturbation uses an invertible mapping to promote configuration space overlap and the convergence of free energy estimates. However, developing suitable mappings can be challenging. Wirnsberger et al. (2020)…
Thermodynamic descriptions of all binaries within the Cr-Fe-Mo-Nb-Ni system have been complied and, where necessary, remodeled. Notably, the Cr-Fe and Fe-Mo systems have been remodeled using comprehensive sublattice models for the…
Accurate characterization of the equilibrium distributions of complex molecular systems and their dependence on environmental factors such as temperature is essential for understanding thermodynamic properties and transition mechanisms.…
In this work, we propose data augmentation methods for embeddings from pre-trained deep learning models that take a weighted combination of a pair of input embeddings, as inspired by Mixup, and combine such augmentation with extra label…
The softmax function combined with a cross-entropy loss is a principled approach to modeling probability distributions that has become ubiquitous in deep learning. The softmax function is defined by a lone hyperparameter, the temperature,…
Predicting the melting temperature (Tm) of multi-component and high-entropy alloys (HEAs) is critical for high-temperature applications but computationally expensive using traditional CALPHAD or DFT methods. In this work, we develop a…
Though offering unprecedented pathways to molecular dynamics (MD) simulations of technologically-relevant materials and conditions, machine-learning interatomic potentials (MLIPs) are typically trained for ``simple'' materials and…
Foundational Machine Learning Potentials can resolve the accuracy and transferability limitations of classical force fields. They enable microscopic insights into material behavior through Molecular Dynamics simulations, which can crucially…
A new framework of thermodynamic modeling is proposed by introducing the concept of differentiable programming, where all the thermodynamic observables including both thermochemical quantities and phase equilibria can be differentiated with…
Liquid metals play a central role in new generation liquid metal cooled nuclear reactors, for which numerical investigations require the use of appropriate thermal turbulence models for low Prandtl number fluids. Given the limitations of…
Hybrid modelling enhances the accuracy and predictive capability of dynamic models by integrating first principles with data-driven methods, effectively mitigating epistemic uncertainties inherent in mechanistic approaches. However, hybrid…
New refractory alloys are being continuously designed and characterised for applications requiring good high-temperature mechanical properties and stability. Computational design from atomistic simulations is limited by interatomic…
We develop a method to learn physical systems from data that employs feedforward neural networks and whose predictions comply with the first and second principles of thermodynamics. The method employs a minimum amount of data by enforcing…