Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userNeural Network Surrogate Models for Absorptivity and Emissivity Spectra of Multiple Elements
64
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
Simulations of high energy density physics are expensive in terms of computational resources. In particular, the computation of opacities of plasmas, which are needed to accurately compute radiation transport in the non-local thermal equilibrium (NLTE) regime, are expensive to the point of easily requiring multiple times the sum-total compute time of all other components of the simulation. As such, there is great interest in finding ways to accelerate NLTE computations. Previous work has demonstrated that a combination of fully-connected autoencoders and a deep jointly-informed neural network (DJINN) can successfully replace the standard NLTE calculations for the opacity of krypton. This work expands this idea to multiple elements in demonstrating that individual surrogate models can be also be generated for other elements with the focus being on creating autoencoders that can accurately encode and decode the absorptivity and emissivity spectra. Furthermore, this work shows that multiple elements across a large range of atomic numbers can be combined into a single autoencoder when using a convolutional autoencoder while maintaining accuracy that is comparable to individual fully-connected autoencoders. Lastly, it is demonstrated that DJINN can effectively learn the latent space of a convolutional autoencoder that can encode multiple elements allowing the combination to effectively function as a surrogate model.
rate research
Read More
Invertible neural networks are a recent technique in machine learning promising neural network architectures that can be run in forward and reverse mode. In this paper, we will be introducing invertible surrogate models that approximate complex forward simulation of the physics involved in laser plasma accelerators: iLWFA. The bijective design of the surrogate model also provides all means for reconstruction of experimentally acquired diagnostics. The quality of our invertible laser wakefield acceleration network will be verified on a large set of numerical LWFA simulations.
Within integrated tokamak plasma modelling, turbulent transport codes are typically the computational bottleneck limiting their routine use outside of post-discharge analysis. Neural network (NN) surrogates have been used to accelerate these calculations while retaining the desired accuracy of the physics-based models. This paper extends a previous NN model, known as QLKNN-hyper-10D, by incorporating the impact of impurities, plasma rotation and magnetic equilibrium effects. This is achieved by adding a light impurity fractional density ($n_{imp,light} / n_e$) and its normalized gradient, the normalized pressure gradient ($alpha$), the toroidal Mach number ($M_{tor}$) and the normalized toroidal flow velocity gradient. The input space was sampled based on experimental data from the JET tokamak to avoid the curse of dimensionality. The resulting networks, named QLKNN-jetexp-15D, show good agreement with the original QuaLiKiz model, both by comparing individual transport quantity predictions as well as comparing its impact within the integrated model, JINTRAC. The profile-averaged RMS of the integrated modelling simulations is <10% for each of the 5 scenarios tested. This is non-trivial given the potential numerical instabilities present within the highly nonlinear system of equations governing plasma transport, especially considering the novel addition of momentum flux predictions to the model proposed here. An evaluation of all 25 NN output quantities at one radial location takes $sim$0.1 ms, $10^4$ times faster than the original QuaLiKiz model. Within the JINTRAC integrated modelling tests performed in this study, using QLKNN-jetexp-15D resulted in a speed increase of only 60 - 100 as other physics modules outside of turbulent transport become the bottleneck.
Graph neural networks, trained on experimental or calculated data are becoming an increasingly important tool in computational materials science. Networks, once trained, are able to make highly accurate predictions at a fraction of the cost of experiments or first-principles calculations of comparable accuracy. However these networks typically rely on large databases of labelled experiments to train the model. In scenarios where data is scarce or expensive to obtain this can be prohibitive. By building a neural network that provides a confidence on the predicted properties, we are able to develop an active learning scheme that can reduce the amount of labelled data required, by identifying the areas of chemical space where the model is most uncertain. We present a scheme for coupling a graph neural network with a Gaussian process to featurise solid-state materials and predict properties textit{including} a measure of confidence in the prediction. We then demonstrate that this scheme can be used in an active learning context to speed up the training of the model, by selecting the optimal next experiment for obtaining a data label. Our active learning scheme can double the rate at which the performance of the model on a test data set improves with additional data compared to choosing the next sample at random. This type of uncertainty quantification and active learning has the potential to open up new areas of materials science, where data are scarce and expensive to obtain, to the transformative power of graph neural networks.
Spiking neural networks (SNN) are usually more energy-efficient as compared to Artificial neural networks (ANN), and the way they work has a great similarity with our brain. Back-propagation (BP) has shown its strong power in training ANN in recent years. However, since spike behavior is non-differentiable, BP cannot be applied to SNN directly. Although prior works demonstrated several ways to approximate the BP-gradient in both spatial and temporal directions either through surrogate gradient or randomness, they omitted the temporal dependency introduced by the reset mechanism between each step. In this article, we target on theoretical completion and investigate the effect of the missing term thoroughly. By adding the temporal dependency of the reset mechanism, the new algorithm is more robust to learning-rate adjustments on a toy dataset but does not show much improvement on larger learning tasks like CIFAR-10. Empirically speaking, the benefits of the missing term are not worth the additional computational overhead. In many cases, the missing term can be ignored.
Machine learning has revolutionized the high-dimensional representations for molecular properties such as potential energy. However, there are scarce machine learning models targeting tensorial properties, which are rotationally covariant. Here, we propose tensorial neural network (NN) models to learn both tensorial response and transition properties, in which atomic coordinate vectors are multiplied with scalar NN outputs or their derivatives to preserve the rotationally covariant symmetry. This strategy keeps structural descriptors symmetry invariant so that the resulting tensorial NN models are as efficient as their scalar counterparts. We validate the performance and universality of this approach by learning response properties of water oligomers and liquid water, and transition dipole moment of a model structural unit of proteins. Machine learned tensorial models have enabled efficient simulations of vibrational spectra of liquid water and ultraviolet spectra of realistic proteins, promising feasible and accurate spectroscopic simulations for biomolecules and materials.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
