arXiv subjects

Ankit Agrawal

Publications and source records attributed to Ankit Agrawal.

52 records · Page 3Linked to original sources

arXiv2019

A real-time iterative machine learning approach for temperature profile prediction in additive manufacturing processes

Additive Manufacturing (AM) is a manufacturing paradigm that builds three-dimensional objects from a computer-aided design model by successively adding material layer by layer. AM has become very popular in the past decade due to its utility for fast prototyping such as 3D printing as well as manufacturing functional parts with complex geometries using processes such as laser metal deposition that would be difficult to create using traditional machining. As the process for creating an intricate part for an expensive metal such as Titanium is prohibitive with respect to cost, computational models are used to simulate the behavior of AM processes before the experimental run. However, as the simulations are computationally costly and time-consuming for predicting multiscale multi-physics phenomena in AM, physics-informed data-driven machine-learning systems for predicting the behavior of AM processes are immensely beneficial. Such models accelerate not only multiscale simulation tools but also empower real-time control systems using in-situ data. In this paper, we design and develop essential components of a scientific framework for developing a data-driven model-based real-time control system. Finite element methods are employed for solving time-dependent heat equations and developing the database. The proposed framework uses extremely randomized trees - an ensemble of bagged decision trees as the regression algorithm iteratively using temperatures of prior voxels and laser information as inputs to predict temperatures of subsequent voxels. The models achieve mean absolute percentage errors below 1% for predicting temperature profiles for AM processes. The code is made available for the research community at https://github.com/paularindam/ml-iter-additive.

cs.LG↗

arXiv2019

Improving MPI Collective I/O Performance With Intra-node Request Aggregation

Two-phase I/O is a well-known strategy for implementing collective MPI-IO functions. It redistributes I/O requests among the calling processes into a form that minimizes the file access costs. As modern parallel computers continue to grow into the exascale era, the communication cost of such request redistribution can quickly overwhelm collective I/O performance. This effect has been observed from parallel jobs that run on multiple compute nodes with a high count of MPI processes on each node. To reduce the communication cost, we present a new design for collective I/O by adding an extra communication layer that performs request aggregation among processes within the same compute nodes. This approach can significantly reduce inter-node communication congestion when redistributing the I/O requests. We evaluate the performance and compare with the original two-phase I/O on a Cray XC40 parallel computer with Intel KNL processors. Using I/O patterns from two large-scale production applications and an I/O benchmark, we show the performance improvement of up to 29 times when running 16384 MPI processes on 256 compute nodes.

cs.DC↗

arXiv2019

Transfer Learning Using Ensemble Neural Networks for Organic Solar Cell Screening

Organic Solar Cells are a promising technology for solving the clean energy crisis in the world. However, generating candidate chemical compounds for solar cells is a time-consuming process requiring thousands of hours of laboratory analysis. For a solar cell, the most important property is the power conversion efficiency which is dependent on the highest occupied molecular orbitals (HOMO) values of the donor molecules. Recently, machine learning techniques have proved to be very useful in building predictive models for HOMO values of donor structures of Organic Photovoltaic Cells (OPVs). Since experimental datasets are limited in size, current machine learning models are trained on data derived from calculations based on density functional theory (DFT). Molecular line notations such as SMILES or InChI are popular input representations for describing the molecular structure of donor molecules. The two types of line representations encode different information, such as SMILES defines the bond types while InChi defines protonation. In this work, we present an ensemble deep neural network architecture, called SINet, which harnesses both the SMILES and InChI molecular representations to predict HOMO values and leverage the potential of transfer learning from a sizeable DFT-computed dataset- Harvard CEP to build more robust predictive models for relatively smaller HOPV datasets. Harvard CEP dataset contains molecular structures and properties for 2.3 million candidate donor structures for OPV while HOPV contains DFT-computed and experimental values of 350 and 243 molecules respectively. Our results demonstrate significant performance improvement from the use of transfer learning and leveraging both molecular representations.

cs.LG↗

arXiv2019

IRNet: A General Purpose Deep Residual Regression Framework for Materials Discovery

Materials discovery is crucial for making scientific advances in many domains. Collections of data from experiments and first-principle computations have spurred interest in applying machine learning methods to create predictive models capable of mapping from composition and crystal structures to materials properties. Generally, these are regression problems with the input being a 1D vector composed of numerical attributes representing the material composition and/or crystal structure. While neural networks consisting of fully connected layers have been applied to such problems, their performance often suffers from the vanishing gradient problem when network depth is increased. In this paper, we study and propose design principles for building deep regression networks composed of fully connected layers with numerical vectors as input. We introduce a novel deep regression network with individual residual learning, IRNet, that places shortcut connections after each layer so that each layer learns the residual mapping between its output and input. We use the problem of learning properties of inorganic materials from numerical attributes derived from material composition and/or crystal structure to compare IRNet's performance against that of other machine learning techniques. Using multiple datasets from the Open Quantum Materials Database (OQMD) and Materials Project for training and evaluation, we show that IRNet provides significantly better prediction performance than the state-of-the-art machine learning approaches currently used by domain scientists. We also show that IRNet's use of individual residual learning leads to better convergence during the training phase than when shortcut connections are between multi-layer stacks while maintaining the same number of parameters.

physics.comp-ph↗

arXiv2019

Microstructural Materials Design via Deep Adversarial Learning Methodology

Identifying the key microstructure representations is crucial for Computational Materials Design (CMD). However, existing microstructure characterization and reconstruction (MCR) techniques have limitations to be applied for materials design. Model-based MCR approaches do not have parameters that can serve as design variables, while MCR techniques that rely on dimension reduction tend to lose important microstructural information. In this work, we present a deep adversarial learning methodology that overcomes the limitations of existing MCR techniques. In the proposed methodology, generative adversarial networks (GAN) are trained to learn the mapping between latent variables and microstructures. Thereafter, the low-dimensional latent variables serve as design variables, and a Bayesian optimization framework is applied to obtain microstructures with desired material property. Due to the special design of the network architecture, the proposed methodology is able to identify the latent (design) variables with desired dimensionality, as well as minimize the information loss even for complex material microstructures. The validity of the proposed methodology is tested numerically on a synthetic microstructure dataset and its effectiveness for materials design is evaluated through a case study of optimizing optical performance for energy absorption. In addition, the scalability and transferability of proposed methodology are also demonstrated in this work. Specifically, the proposed methodology is scalable to generate arbitrary sized microstructures, and it can serve as a pre-trained model to improve the performance of a structure-property predictive model via transfer learning.

cond-mat.mtrl-sci↗

arXiv2018

CheMixNet: Mixed DNN Architectures for Predicting Chemical Properties using Multiple Molecular Representations

SMILES is a linear representation of chemical structures which encodes the connection table, and the stereochemistry of a molecule as a line of text with a grammar structure denoting atoms, bonds, rings and chains, and this information can be used to predict chemical properties. Molecular fingerprints are representations of chemical structures, successfully used in similarity search, clustering, classification, drug discovery, and virtual screening and are a standard and computationally efficient abstract representation where structural features are represented as a bit string. Both SMILES and molecular fingerprints are different representations for describing the structure of a molecule. There exist several predictive models for learning chemical properties based on either SMILES or molecular fingerprints. Here, our goal is to build predictive models that can leverage both these molecular representations. In this work, we present CheMixNet -- a set of neural networks for predicting chemical properties from a mixture of features learned from the two molecular representations -- SMILES as sequences and molecular fingerprints as vector inputs. We demonstrate the efficacy of CheMixNet architectures by evaluating on six different datasets. The proposed CheMixNet models not only outperforms the candidate neural architectures such as contemporary fully connected networks that uses molecular fingerprints and 1-D CNN and RNN models trained SMILES sequences, but also other state-of-the-art architectures such as Chemception and Molecular Graph Convolutions.

cs.LG↗

arXiv2018

Analysis of Dynamic Memory Bandwidth Regulation in Multi-core Real-Time Systems

One of the primary sources of unpredictability in modern multi-core embedded systems is contention over shared memory resources, such as caches, interconnects, and DRAM. Despite significant achievements in the design and analysis of multi-core systems, there is a need for a theoretical framework that can be used to reason on the worst-case behavior of real-time workload when both processors and memory resources are subject to scheduling decisions. In this paper, we focus our attention on dynamic allocation of main memory bandwidth. In particular, we study how to determine the worst-case response time of tasks spanning through a sequence of time intervals, each with a different bandwidth-to-core assignment. We show that the response time computation can be reduced to a maximization problem over assignment of memory requests to different time intervals, and we provide an efficient way to solve such problem. As a case study, we then demonstrate how our proposed analysis can be used to improve the schedulability of Integrated Modular Avionics systems in the presence of memory-intensive workload.

cs.DC↗

arXiv2018

Gelation of Plasmonic Metal Oxide Nanocrystals by Polymer-Induced Depletion-Attractions

Gelation of colloidal nanocrystals (NCs) emerged as a strategy to preserve inherent nanoscale properties in multiscale architectures. Yet available gelation methods still struggle to reliably control nanoscale optical phenomena such as photoluminescence and localized surface plasmon resonance (LSPR) across NC systems due to processing variability. Here, we report on an alternative gelation method based on physical inter-NC interactions: short-range depletion-attractions balanced by long-range electrostatic repulsions. The latter are established by removing the native organic ligands that passivate tin-doped indium oxide (ITO) NCs while the former are introduced by mixing with small polyethylene glycol (PEG) chains. As we incorporate increasing concentrations of PEG, we observe a reentrant phase behavior featuring two favorable gelation windows; the first arises from bridging effects while the second is attributed to depletion-attractions according to phase behavior predicted by our unified theoretical model. The NCs remain discrete within the gel network, based on X-ray scattering and high-resolution transmission electron microscopy. The infrared optical response of the gel is reflective of both the NC building blocks and the network architecture, being characteristic of ITO NC LSPR with coupling interactions between neighboring NCs.

cond-mat.mes-hall↗

arXiv2018

Tuning Nanocrystal Surface Depletion by Controlling Dopant Distribution as a Route Toward Enhanced Film Conductivity

Electron conduction through bare metal oxide nanocrystal (NC) films is hindered by surface depletion regions resulting from the presence of surface states. We control the radial dopant distribution in tin-doped indium oxide (ITO) NCs as a means to manipulate the NC depletion width. We find in films of ITO NCs of equal overall dopant concentration that those with dopant-enriched surfaces show decreased depletion width and increased conductivity. Variable temperature conductivity data shows electron localization length increases and associated depletion width decreases monotonically with increased density of dopants near the NC surface. We calculate band profiles for NCs of differing radial dopant distributions and, in agreement with variable temperature conductivity fits, find NCs with dopant-enriched surfaces have narrower depletion widths and longer localization lengths than those with dopant-enriched cores. Following amelioration of NC surface depletion by atomic layer deposition of alumina, all films of equal overall dopant concentration have similar conductivity. Variable temperature conductivity measurements on alumina-capped films indicate all films behave as granular metals. Herein, we conclude that dopant-enriched surfaces decrease the near-surface depletion region, which directly increases the electron localization length and conductivity of NC films.

cond-mat.mes-hall↗

arXiv2018

Impacts of Surface Depletion on the Plasmonic Properties of Doped Semiconductor Nanocrystals

Degenerately doped semiconductor nanocrystals (NCs) exhibit a localized surface plasmon resonance (LSPR) in the infrared range of the electromagnetic spectrum. Unlike metals, semiconductor NCs offer tunable LSPR characteristics enabled by doping, or via electrochemical or photochemical charging. Tuning plasmonic properties through carrier density modulation suggests potential applications in smart optoelectronics, catalysis, and sensing. Here, we elucidate fundamental aspects of LSPR modulation through dynamic carrier density tuning in Sn-doped Indium Oxide NCs. Monodisperse Sn-doped Indium Oxide NCs with various doping level and sizes were synthesized and assembled in uniform films. NC films were then charged in an in situ electrochemical cell and the LSPR modulation spectra were monitored. Based on spectral shifts and intensity modulation of the LSPR, combined with optical modeling, it was found that often-neglected semiconductor properties, specifically band structure modification due to doping and surface states, strongly affect LSPR modulation. Fermi level pinning by surface defect states creates a surface depletion layer that alters the LSPR properties; it determines the extent of LSPR frequency modulation, diminishes the expected near field enhancement, and strongly reduces sensitivity of the LSPR to the surroundings.

physics.optics↗

arXiv2017

Parallel Implementation of Lossy Data Compression for Temporal Data Sets

Many scientific data sets contain temporal dimensions. These are the data storing information at the same spatial location but different time stamps. Some of the biggest temporal datasets are produced by parallel computing applications such as simulations of climate change and fluid dynamics. Temporal datasets can be very large and cost a huge amount of time to transfer among storage locations. Using data compression techniques, files can be transferred faster and save storage space. NUMARCK is a lossy data compression algorithm for temporal data sets that can learn emerging distributions of element-wise change ratios along the temporal dimension and encodes them into an index table to be concisely represented. This paper presents a parallel implementation of NUMARCK. Evaluated with six data sets obtained from climate and astrophysics simulations, parallel NUMARCK achieved scalable speedups of up to 8788 when running 12800 MPI processes on a parallel computer. We also compare the compression ratios against two lossy data compression algorithms, ISABELA and ZFP. The results show that NUMARCK achieved higher compression ratio than ISABELA and ZFP.

cs.DC↗

arXiv2016

A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials

A very active area of materials research is to devise methods that use machine learning to automatically extract predictive models from existing materials data. While prior examples have demonstrated successful models for some applications, many more applications exist where machine learning can make a strong impact. To enable faster development of machine-learning-based models for such applications, we have created a framework capable of being applied to a broad range of materials data. Our method works by using a chemically diverse list of attributes, which we demonstrate are suitable for describing a wide variety of properties, and a novel method for partitioning the data set into groups of similar materials in order to boost the predictive accuracy. In this manuscript, we demonstrate how this new method can be used to predict diverse properties of crystalline and amorphous materials, such as band gap energy and glass-forming ability.

cond-mat.mtrl-sci↗

arXiv2016

A New Parallel Algorithm for Two-Pass Connected Component Labeling

Connected Component Labeling (CCL) is an important step in pattern recognition and image processing. It assigns labels to the pixels such that adjacent pixels sharing the same features are assigned the same label. Typically, CCL requires several passes over the data. We focus on two-pass technique where each pixel is given a provisional label in the first pass whereas an actual label is assigned in the second pass. We present a scalable parallel two-pass CCL algorithm, called PAREMSP, which employs a scan strategy and the best union-find technique called REMSP, which uses REM's algorithm for storing label equivalence information of pixels in a 2-D image. In the first pass, we divide the image among threads and each thread runs the scan phase along with REMSP simultaneously. In the second phase, we assign the final labels to the pixels. As REMSP is easily parallelizable, we use the parallel version of REMSP for merging the pixels on the boundary. Our experiments show the scalability of PAREMSP achieving speedups up to $20.1$ using $24$ cores on shared memory architecture using OpenMP for an image of size $465.20$ MB. We find that our proposed parallel algorithm achieves linear scaling for a large resolution fixed problem size as the number of processing elements are increased. Additionally, the parallel algorithm does not make use of any hardware specific routines, and thus is highly portable.

cs.DS↗

arXiv2015

Qualitative Decision Methods for Multi-Attribute Decision Making

The fundamental problem underlying all multi-criteria decision analysis (MCDA) problems is that of dominance between any two alternatives: "Given two alternatives A and B, each described by a set criteria, is A preferred to B with respect to a set of decision maker (DM) preferences over the criteria?". Depending on the application in which MCDA is performed, the alternatives may represent strategies and policies for business, potential locations for setting up new facilities, designs of buildings, etc. The general objective of MCDA is to enable the DM to order all alternatives in order of the stated preferences, and choose the ones that are best, i.e., optimal with respect to the preferences over the criteria. This article presents and summarizes a recently developed MCDA framework that orders the set of alternatives when the relative importance preferences are incomplete, imprecise, or qualitative in nature.

cs.AI↗

arXiv2015

SunPy - Python for Solar Physics

This paper presents SunPy (version 0.5), a community-developed Python package for solar physics. Python, a free, cross-platform, general-purpose, high-level programming language, has seen widespread adoption among the scientific community, resulting in the availability of a large number of software packages, from numerical computation (NumPy, SciPy) and machine learning (scikit-learn) to visualisation and plotting (matplotlib). SunPy is a data-analysis environment specialising in providing the software necessary to analyse solar and heliospheric data in Python. SunPy is open-source software (BSD licence) and has an open and transparent development workflow that anyone can contribute to. SunPy provides access to solar data through integration with the Virtual Solar Observatory (VSO), the Heliophysics Event Knowledgebase (HEK), and the HELiophysics Integrated Observatory (HELIO) webservices. It currently supports image data from major solar missions (e.g., SDO, SOHO, STEREO, and IRIS), time-series data from missions such as GOES, SDO/EVE, and PROBA2/LYRA, and radio spectra from e-Callisto and STEREO/SWAVES. We describe SunPy's functionality, provide examples of solar data analysis in SunPy, and show how Python-based solar data-analysis can leverage the many existing tools already available in Python. We discuss the future goals of the project and encourage interested users to become involved in the planning and development of SunPy.

astro-ph.IM↗

arXiv2014

Quantifying randomness in protein-protein interaction networks of different species: A random matrix approach

We analyze protein-protein interaction networks for six different species under the framework of random matrix theory. Nearest neighbor spacing distribution of the eigenvalues of adjacency matrices of the largest connected part of these networks emulate universal Gaussian orthogonal statistics of random matrix theory. We demonstrate that spectral rigidity, which quantifies long range correlations in eigenvalues, for all protein-protein interaction networks follow random matrix prediction up to certain ranges indicating randomness in interactions. After this range, deviation from the universality evinces underlying structural features in network.

q-bio.MN↗