scholarly journals pNeRF: Parallelized Conversion from Internal to Cartesian Coordinates

2018 ◽  
Author(s):  
Mohammed AlQuraishi
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Molecular Modeling ◽  
Reference Frame ◽  
Natural Extension ◽  
Computational Cost ◽  
Cartesian Coordinates ◽  
Order Of Magnitude ◽  
Speed Up ◽  
Coordinate Conversion

ABSTRACTThe conversion of polymer parameterization from internal coordinates (bond lengths, angles, and torsions) to Cartesian coordinates is a fundamental task in molecular modeling, often performed using the Natural Extension Reference Frame (NeRF) algorithm. NeRF can be parallelized to process multiple polymers simultaneously, but is not parallelizable along the length of a single polymer. A mathematically equivalent algorithm, pNeRF, has been derived that is parallelizable along a polymer’s length. Empirical analysis demonstrates an order-of-magnitude speed up using modern GPUs and CPUs. In machine learning-based workflows, in which partial derivatives are backpropagated through NeRF equations and neural network primitives, switching to pNeRF can reduce the fractional computational cost of coordinate conversion from over two-thirds to around 10%. An optimized TensorFlow-based implementation of pNeRF is available on GitHub.

A 3D Complexity-Adaptive Approach to Exploit Sparsity in Elastic Wave Propagation

Geophysics ◽  
2021 ◽  
pp. 1-64
Author(s):  
Claudia Haindl ◽  
Kuangdai Leng ◽  
Tarje Nissen-Meyer
Keyword(s):  
Degrees Of Freedom ◽  
Computational Cost ◽  
Parameter Tuning ◽  
Performance Limits ◽  
Absorbing Boundary ◽  
Adaptive Approach ◽  
Order Of Magnitude ◽  
Speed Up ◽  
Complex Settings ◽  
Close Fit

We present an adaptive approach to seismic modeling by which the computational cost of a 3D simulation can be reduced while retaining resolution and accuracy. This Azimuthal Complexity Adaptation (ACA) approach relies upon the inherent smoothness of wavefields around the azimuth of a source-centered cylindrical coordinate system. Azimuthal oversampling is thereby detected and eliminated. The ACA method has recently been introduced as part of AxiSEM3D, an open-source solver for global seismology. We employ a generalization of this solver which can handle local-scale Cartesian models, and which features a combination of an absorbing boundary condition and a sponge boundary with automated parameter tuning. The ACA method is benchmarked against an established 3D method using a model featuring bathymetry and a salt body. We obtain a close fit where the models are implemented equally in both solvers and an expectedly poor fit otherwise, with the ACA method running an order of magnitude faster than the classic 3D method. Further, we present maps of maximum azimuthal wavenumbers that are created to facilitate azimuthal complexity adaptation. We show how these maps can be interpreted in terms of the 3D complexity of the wavefield and in terms of seismic resolution. The expected performance limits of the ACA method for complex 3D structures are tested on the SEG/EAGE salt model. In this case, ACA still reduces the overall degrees of freedom by 92% compared to a complexity-blind AxiSEM3D simulation. In comparison with the reference 3D method, we again find a close fit and a speed-up of a factor 7. We explore how the performance of ACA is affected by model smoothness by subjecting the SEG/EAGE salt model to Gaussian smoothing. This results in a doubling of the speed-up. ACA thus represents a convergent, versatile and efficient method for a variety of complex settings and scales.

scholarly journals A machine-learning approach for identifying the counterparts of submillimetre galaxies and applications to the GOODS-North field

2019 ◽  
Vol 489 (2) ◽  
pp. 1770-1786 ◽  
Author(s):  
Ruihan Henry Liu ◽  
Ryley Hill ◽  
Douglas Scott ◽  
Omar Almaini ◽  
Fangxia An ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Near Infrared ◽  
Spectral Energy Distribution ◽  
Computational Cost ◽  
Spectral Energy ◽  
Distribution Fitting ◽  
Star Forming ◽  
Trained Neural Network ◽  
Validation Tests

ABSTRACT Identifying the counterparts of submillimetre (submm) galaxies (SMGs) in multiwavelength images is a critical step towards building accurate models of the evolution of strongly star-forming galaxies in the early Universe. However, obtaining a statistically significant sample of robust associations is very challenging due to the poor angular resolution of single-dish submm facilities. Recently, a large sample of single-dish-detected SMGs in the UKIDSS UDS field, a subset of the SCUBA-2 Cosmology Legacy Survey (S2CLS), was followed up with the Atacama Large Millimeter/submillimeter Array (ALMA), which has provided the resolution necessary for identification in optical and near-infrared images. We use this ALMA sample to develop a training set suitable for machine-learning (ML) algorithms to determine how to identify SMG counterparts in multiwavelength images, using a combination of magnitudes and other derived features. We test several ML algorithms and find that a deep neural network performs the best, accurately identifying 85 per cent of the ALMA-detected optical SMG counterparts in our cross-validation tests. When we carefully tune traditional colour-cut methods, we find that the improvement in using machine learning is modest (about 5 per cent), but importantly it comes at little additional computational cost. We apply our trained neural network to the GOODS-North field, which also has single-dish submm observations from the S2CLS and deep multiwavelength data but little high-resolution interferometric submm imaging, and we find that we are able to classify SMG counterparts for 36/67 of the single-dish submm sources. We discuss future improvements to our ML approach, including combining ML with spectral energy distribution fitting techniques and using longer wavelength data as additional features.

scholarly journals Accelerating numerical wave propagation using wavefield adapted meshes. Part I: forward and adjoint modelling

2020 ◽  
Vol 221 (3) ◽  
pp. 1580-1590 ◽  
Author(s):  
M van Driel ◽  
C Boehm ◽  
L Krischer ◽  
M Afanasiev
Keyword(s):  
Wave Propagation ◽  
Adaptive Mesh Refinement ◽  
Waveform Inversion ◽  
Computational Cost ◽  
Model Space ◽  
Adaptive Mesh ◽  
Order Of Magnitude ◽  
Speed Up ◽  
Adjoint Modelling ◽  
The Waves

SUMMARY An order of magnitude speed-up in finite-element modelling of wave propagation can be achieved by adapting the mesh to the anticipated space-dependent complexity and smoothness of the waves. This can be achieved by designing the mesh not only to respect the local wavelengths, but also the propagation direction of the waves depending on the source location, hence by anisotropic adaptive mesh refinement. Discrete gradients with respect to material properties as needed in full waveform inversion can still be computed exactly, but at greatly reduced computational cost. In order to do this, we explicitly distinguish the discretization of the model space from the discretization of the wavefield and derive the necessary expressions to map the discrete gradient into the model space. While the idea is applicable to any wave propagation problem that retains predictable smoothness in the solution, we highlight the idea of this approach with instructive 2-D examples of forward as well as inverse elastic wave propagation. Furthermore, we apply the method to 3-D global seismic wave simulations and demonstrate how meshes can be constructed that take advantage of high-order mappings from the reference coordinates of the finite elements to physical coordinates. Error level and speed-ups are estimated based on convergence tests with 1-D and 3-D models.

scholarly journals Efficient Hyperparameter Tuning with Grid Search for Text Categorization using kNN Approach with BM25 Similarity

2019 ◽  
Vol 9 (1) ◽  
pp. 160-180 ◽  
Author(s):  
Raji Ghawi ◽  
Jürgen Pfeffer
Keyword(s):  
Machine Learning ◽  
Text Categorization ◽  
Learning Algorithm ◽  
Efficient Technique ◽  
Grid Search ◽  
Order Of Magnitude ◽  
Speed Up

AbstractIn machine learning, hyperparameter tuning is the problem of choosing a set of optimal hyperparameters for a learning algorithm. Several approaches have been widely adopted for hyperparameter tuning, which is typically a time consuming process. We propose an efficient technique to speed up the process of hyperparameter tuning with Grid Search. We applied this technique on text categorization using kNN algorithm with BM25 similarity, where three hyperparameters need to be tuned. Our experiments show that our proposed technique is at least an order of magnitude faster than conventional tuning.

scholarly journals Improving the accuracy of the neuroevolution machine learning potential for multi-component systems

2021 ◽  
Author(s):  
Zheyong Fan
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Computational Cost ◽  
Md Simulations ◽  
Training Process ◽  
Learning Potential ◽  
Natural Evolution ◽  
Radial Functions ◽  
Component Systems ◽  
Training Neural Network

Abstract In a previous paper [Fan Z et al. 2021 Phys. Rev. B, 104, 104309], we developed the neuroevolution potential (NEP), a framework of training neural network based machine-learning potentials using a natural evolution strategy and performing molecular dynamics (MD) simulations using the trained potentials. The atom-environment descriptor in NEP was constructed based on a set of radial and angular functions. For multi-component systems, all the radial functions between two atoms are multiplied by some fixed factors that depend on the types of the two atoms only. In this paper, we introduce an improved descriptor for multi-component systems, in which different radial functions are multiplied by different factors that are also optimized during the training process, and show that it can significantly improve the regression accuracy without increasing the computational cost in MD simulations.

Application of Machine Learning in Turbulent Combustion for Aviation Gas Turbine Combustor Design

2021 ◽  
Author(s):  
Vishwas Verma ◽  
Kiran Manoharan ◽  
Jaydeep Basani
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Flow Field ◽  
Gas Turbine ◽  
Computational Cost ◽  
Data Driven ◽  
Navier Stokes ◽  
Computational Time ◽  
Reacting Flow ◽  
Data Driven Approach

Abstract Numerical simulation of gas turbine combustors requires resolving a broad spectrum of length and time scales for accurate flow field and emission predictions. Reynold’s Averaged Navier Stokes (RANS) approach can generate solutions in few hours; however, it fails to produce accurate predictions for turbulent reacting flow field seen in general combustors. On the other hand, the Large Eddy Simulation (LES) approach can overcome this challenge, but it requires orders of magnitude higher computational cost. This limits designers to use the LES approach in combustor development cycles and prohibits them from using the same in numerical optimization. The current work tries to build an alternate approach using a data-driven method to generate fast and consistent results. In this work, deep learning (DL) dense neural network framework is used to improve the RANS solution accuracy using LES data as truth data. A supervised regression learning multilayer perceptron (MLP) neural network engine is developed. The machine learning (ML) engine developed in the present study can compute data with LES accuracy in 95% lesser computational time than performing LES simulations. The output of the ML engine shows good agreement with the trend of LES, which is entirely different from RANS, and to a reasonable extent, captures magnitudes of actual flow variables. However, it is recommended that the ML engine be trained using broad design space and physical laws along with a purely data-driven approach for better generalization.

scholarly journals A neural network protocol for electronic excitations of N-methylacetamide

2019 ◽  
pp. 201821044 ◽  
Author(s):  
Sheng Ye ◽  
Wei Hu ◽  
Xin Li ◽  
Jinxiao Zhang ◽  
Kai Zhong ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Ground State ◽  
Density Functional ◽  
Electronic Absorption Spectra ◽  
Dipole Moments ◽  
Computational Cost ◽  
Density Functional Theory Calculations ◽  
Peptide Bond ◽  
Transition Dipole

UV absorption is widely used for characterizing proteins structures. The mapping of UV spectra to atomic structure of proteins relies on expensive theoretical simulations, circumventing the heavy computational cost which involves repeated quantum-mechanical simulations of excited-state properties of many fluctuating protein geometries, which has been a long-time challenge. Here we show that a neural network machine-learning technique can predict electronic absorption spectra of N-methylacetamide (NMA), which is a widely used model system for the peptide bond. Using ground-state geometric parameters and charge information as descriptors, we employed a neural network to predict transition energies, ground-state, and transition dipole moments of many molecular-dynamics conformations at different temperatures, in agreement with time-dependent density-functional theory calculations. The neural network simulations are nearly 3,000× faster than comparable quantum calculations. Machine learning should provide a cost-effective tool for simulating optical properties of proteins.

scholarly journals An Attempt to Boost Posterior Population Expansion Using Fast Machine Learning Algorithms

2021 ◽  
Vol 4 ◽  
Author(s):  
Przemysław Juda ◽  
Philippe Renard
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Monte Carlo ◽  
Random Forest ◽  
Convolutional Neural Network ◽  
Population Expansion ◽  
Specific Storage ◽  
Speed Up ◽  
Learning Schemes ◽  
Forward Operator

In hydrogeology, inverse techniques have become indispensable to characterize subsurface parameters and their uncertainty. When modeling heterogeneous, geologically realistic discrete model spaces, such as categorical fields, Monte Carlo methods are needed to properly sample the solution space. Inversion algorithms use a forward operator, such as a numerical groundwater solver. The forward operator often represents the bottleneck for the high computational cost of the Monte Carlo sampling schemes. Even if efficient sampling methods (for example Posterior Population Expansion, PoPEx) have been developed, they need significant computing resources. It is therefore desirable to speed up such methods. As only a few models generated by the sampler have a significant likelihood, we propose to predict the significance of generated models by means of machine learning. Only models labeled as significant are passed to the forward solver, otherwise, they are rejected. This work compares the performance of AdaBoost, Random Forest, and convolutional neural network as classifiers integrated with the PoPEx framework. During initial iterations of the algorithm, the forward solver is always executed and subsurface models along with the likelihoods are stored. Then, the machine learning schemes are trained on the available data. We demonstrate the technique using a simulation of a tracer test in a fluvial aquifer. The geology is modeled by the multiple-point statistical approach, the field contains four geological facies, with associated permeability, porosity, and specific storage values. MODFLOW is used for groundwater flow and transport simulation. The solution of the inverse problem is used to estimate the 10 days protection zone around the pumping well. The estimated speed-ups with Random Forest and AdaBoost were higher than with the convolutional neural network. To validate the approach, computing times of inversion without and with machine learning schemes were computed and the error against the reference solution was calculated. For the same mean error, accelerated PoPEx achieved a speed-up rate of up to 2 with respect to the standard PoPEx.

scholarly journals A machine learning approach for efficient multi-dimensional integration

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Boram Yoon
Keyword(s):  
Machine Learning ◽  
Regression Model ◽  
Dimensional Space ◽  
Computational Cost ◽  
Gaussian Process Regression ◽  
Gradient Boosting ◽  
Prediction Errors ◽  
Integration Algorithm ◽  
Order Of Magnitude ◽  
Physics Problems

AbstractMany physics problems involve integration in multi-dimensional space whose analytic solution is not available. The integrals can be evaluated using numerical integration methods, but it requires a large computational cost in some cases, so an efficient algorithm plays an important role in solving the physics problems. We propose a novel numerical multi-dimensional integration algorithm using machine learning (ML). After training a ML regression model to mimic a target integrand, the regression model is used to evaluate an approximation of the integral. Then, the difference between the approximation and the true answer is calculated to correct the bias in the approximation of the integral induced by ML prediction errors. Because of the bias correction, the final estimate of the integral is unbiased and has a statistically correct error estimation. Three ML models of multi-layer perceptron, gradient boosting decision tree, and Gaussian process regression algorithms are investigated. The performance of the proposed algorithm is demonstrated on six different families of integrands that typically appear in physics problems at various dimensions and integrand difficulties. The results show that, for the same total number of integrand evaluations, the new algorithm provides integral estimates with more than an order of magnitude smaller uncertainties than those of the VEGAS algorithm in most of the test cases.

Sign in / Sign up

Export Citation Format

Share Document