Related papers: Emulating the interstellar medium chemistry with n…
Supernova (SN) plays an important role in galaxy formation and evolution. In high-resolution galaxy simulations using massively parallel computing, short integration timesteps for SNe are serious bottlenecks. This is an urgent issue that…
We present a series of hydrodynamic simulations of isolated galaxies with stellar mass of $10^{9} \, \rm{M}_{\odot}$. The models use a resolution of $750 \, \rm{M}_{\odot}$ per particle and include a treatment for the full non-equilibrium…
Nonlinear conservation laws govern a broad class of important physical systems in science and industry and are central to scientific machine learning (SciML). Large general-purpose models offer speed, but replacing the numerical and…
Diffusion models are the state-of-the-art generative models for high-resolution images, but sampling from pretrained models is computationally expensive, motivating interest in fast sampling. Although Free-U Net is a training-free…
We emulate the Tolman-Oppenheimer-Volkoff (TOV) equations, including tidal deformability, for neutron stars using a new method based upon the Dynamic Mode Decomposition (DMD). This method, which we call Star Log-extended eMulation (SLM),…
Molecular circuits capable of autonomous learning could unlock novel applications in fields such as bioengineering and synthetic biology. To this end, existing chemical implementations of neural computing have mainly relied on emulating…
Making the most of next-generation galaxy clustering surveys requires overcoming challenges in complex, non-linear modelling to access the significant amount of information at smaller cosmological scales. Field-level inference has provided…
Machine learning can accelerate cosmological inferences that involve many sequential evaluations of computationally expensive data vectors. Previous works in this series have examined how machine learning architectures impact emulator…
We propose a novel approach for image segmentation that combines Neural Ordinary Differential Equations (NODEs) and the Level Set method. Our approach parametrizes the evolution of an initial contour with a NODE that implicitly learns from…
In the classical picture, electron-capture supernovae and the accretion-induced collapse of oxygen-neon white dwarfs (ONeWDs) undergo an oxygen deflagration phase before gravitational collapse produces a neutron star (NS). These types of…
The laboratory work presented here, simulates the chemistry on icy dust grains as typical for the 'CO freeze-out stage' in dark molecular clouds. It differs from previous studies in that solid-state hydrogenation and vacuum…
We present a Neural Network based emulator for the galaxy redshift-space power spectrum that enables several orders of magnitude acceleration in the galaxy clustering parameter inference, while preserving 3$\sigma$ accuracy better than…
A novel convolutional autoencoder neural ODE (CAE-NODE) framework is proposed for a reduced-order model (ROM) of transient 2D counterflow flames, as an extension of AE-NODE methods in homogeneous reactive systems to spatially resolved…
While it is widely known that neural networks are universal approximators of continuous functions, a less known and perhaps more powerful result is that a neural network with a single hidden layer can approximate accurately any nonlinear…
For the calculation of complex neutral/ionized gas phase chemical equilibria, we present a semi-analytical versatile and efficient computer program, called FastChem. The applied method is based on the solution of a system of coupled…
Star formation is a multi-scale problem, and only global simulations that account for the connection from the molecular cloud scale gas flow to the accreting protostar can reflect the observed complexity of protostellar systems.…
Nuclear quantum effects such as zero-point energy and hydrogen tunnelling play a central role in many biological and chemical processes. The nuclear-electronic orbital (NEO) approach captures these effects by treating selected nuclei…
We train convolutional neural networks to correct the output of fast and approximate N-body simulations at the field level. Our model, Neural Enhanced COLA --NECOLA--, takes as input a snapshot generated by the computationally efficient…
Molecular dynamics (MD) simulation is essential for various scientific domains but computationally expensive. Learning-based force fields have made significant progress in accelerating ab-initio MD simulation but are not fast enough for…
Differential equations in general and neural ODEs in particular are an essential technique in continuous-time system identification. While many deterministic learning algorithms have been designed based on numerical integration via the…