arXiv subjects

Jianjun Hu

Publications and source records attributed to Jianjun Hu.

61 records · Page 4Linked to original sources

arXiv2020

Machine Learning based prediction of noncentrosymmetric crystal materials

Noncentrosymmetric materials play a critical role in many important applications such as laser technology, communication systems,quantum computing, cybersecurity, and etc. However, the experimental discovery of new noncentrosymmetric materials is extremely difficult. Here we present a machine learning model that could predict whether the composition of a potential crystalline structure would be centrosymmetric or not. By evaluating a diverse set of composition features calculated using matminer featurizer package coupled with different machine learning algorithms, we find that Random Forest Classifiers give the best performance for noncentrosymmetric material prediction, reaching an accuracy of 84.8% when evaluated with 10 fold cross-validation on the dataset with 82,506 samples extracted from Materials Project. A random forest model trained with materials with only 3 elements gives even higher accuracy of 86.9%. We apply our ML model to screen potential noncentrosymmetric materials from 2,000,000 hypothetical materials generated by our inverse design engine and report the top 20 candidate noncentrosymmetric materials with 2 to 4 elements and top 20 borate candidates

physics.comp-ph↗

arXiv2020

Predicting Elastic Properties of Materials from Electronic Charge Density Using 3D Deep Convolutional Neural Networks

Materials representation plays a key role in machine learning based prediction of materials properties and new materials discovery. Currently both graph and 3D voxel representation methods are based on the heterogeneous elements of the crystal structures. Here, we propose to use electronic charge density (ECD) as a generic unified 3D descriptor for materials property prediction with the advantage of possessing close relation with the physical and chemical properties of materials. We developed an ECD based 3D convolutional neural networks (CNNs) for predicting elastic properties of materials, in which CNNs can learn effective hierarchical features with multiple convolving and pooling operations. Extensive benchmark experiments over 2,170 Fm-3m face-centered-cubic (FCC) materials show that our ECD based CNNs can achieve good performance for elasticity prediction. Especially, our CNN models based on the fusion of elemental Magpie features and ECD descriptors achieved the best 5-fold cross-validation performance. More importantly, we showed that our ECD based CNN models can achieve significantly better extrapolation performance when evaluated over non-redundant datasets where there are few neighbor training samples around test samples. As additional validation, we evaluated the predictive performance of our models on 329 materials of space group Fm-3m by comparing to DFT calculated values, which shows better prediction power of our model for bulk modulus than shear modulus. Due to the unified representation power of ECD, it is expected that our ECD based CNN approach can also be applied to predict other physical and chemical properties of crystalline materials.

cond-mat.mtrl-sci↗

arXiv2020

Global Attention based Graph Convolutional Neural Networks for Improved Materials Property Prediction

Machine learning (ML) methods have gained increasing popularity in exploring and developing new materials. More specifically, graph neural network (GNN) has been applied in predicting material properties. In this work, we develop a novel model, GATGNN, for predicting inorganic material properties based on graph neural networks composed of multiple graph-attention layers (GAT) and a global attention layer. Through the application of the GAT layers, our model can efficiently learn the complex bonds shared among the atoms within each atom's local neighborhood. Subsequently, the global attention layer provides the weight coefficients of each atom in the inorganic crystal material which are used to considerably improve our model's performance. Notably, with the development of our GATGNN model, we show that our method is able to both outperform the previous models' predictions and provide insight into the crystallization of the material.

physics.comp-ph↗

arXiv2019

Generative adversarial networks (GAN) based efficient sampling of chemical space for inverse design of inorganic materials

A major challenge in materials design is how to efficiently search the vast chemical design space to find the materials with desired properties. One effective strategy is to develop sampling algorithms that can exploit both explicit chemical knowledge and implicit composition rules embodied in the large materials database. Here, we propose a generative machine learning model (MatGAN) based on a generative adversarial network (GAN) for efficient generation of new hypothetical inorganic materials. Trained with materials from the ICSD database, our GAN model can generate hypothetical materials not existing in the training dataset, reaching a novelty of 92.53% when generating 2 million samples. The percentage of chemically valid (charge neutral and electronegativity balanced) samples out of all generated ones reaches 84.5% by our GAN when trained with materials from ICSD even though no such chemical rules are explicitly enforced in our GAN model, indicating its capability to learn implicit chemical composition rules. Our algorithm could be used to speed up inverse design or computational screening of inorganic materials.

cs.LG↗

arXiv2019

Anomalous thermal transport behavior in graphene-like carbon nitride (C$_3$N)

New classes 2D carbon-based materials beyond graphene have been intensively studied for their promising applications in nano-/opto-/spin-electronics, catalysis, sensors, clean energy, etc. Very recently, the controllable large-scale synthesis of 2D single crystalline carbon nitride (C3N) was reported, which is the first and the only crystalline, hole-free, single-layer carbon nitride with fascinating properties. Herein, we perform a comparative study of thermal transport between monolayer C3N and the parent graphene. The thermal conductivity (k) of C3N shows an anomalous temperature dependence, which is totally different from that for common crystalline materials and deviates largely from the well-known k~1/T relationship. Moreover, the k of C3N is found in surprise to be enlarged by applying bilateral tensile strain, despite its similar planar honeycomb structure as graphene, whose k is reduced upon stretching. The underlying mechanism is revealed by providing direct evidence for the interaction between lone-pair N-s electrons and bonding electrons from C atoms in C3N based on the analysis of orbital-projected electronic structures and electron localization function (ELF). Our study not only make a comprehensive investigation of the thermal transport in graphene-like C3N, but also reveals the physical origins for its anomalous properties, which deepens the understanding of phonon transport in 2D materials.

cond-mat.mtrl-sci↗

arXiv2018

A Deep Learning Algorithm for One-step Contour Aware Nuclei Segmentation of Histopathological Images

This paper addresses the task of nuclei segmentation in high-resolution histopathological images. We propose an auto- matic end-to-end deep neural network algorithm for segmenta- tion of individual nuclei. A nucleus-boundary model is introduced to predict nuclei and their boundaries simultaneously using a fully convolutional neural network. Given a color normalized image, the model directly outputs an estimated nuclei map and a boundary map. A simple, fast and parameter-free post-processing procedure is performed on the estimated nuclei map to produce the final segmented nuclei. An overlapped patch extraction and assembling method is also designed for seamless prediction of nuclei in large whole-slide images. We also show the effectiveness of data augmentation methods for nuclei segmentation task. Our experiments showed our method outperforms prior state-of-the- art methods. Moreover, it is efficient that one 1000X1000 image can be segmented in less than 5 seconds. This makes it possible to precisely segment the whole-slide image in acceptable time

cs.CV↗

arXiv2015

A 128-channel picoammeter system and its application on charged particle beam current distribution measurements

A 128-channel picoammeter system is constructed based on instrumentation amplifiers. Taking the advantages of high electric potential and narrow bandwidth in DC energetic charged beam measurements, current resolution better than 5 fA can be achieved. Two 128-channel Faraday cup arrays are built, and are employed for ion and electron beam current distribution measurements. Tests with 60 keV O3+ ions and 2 keV electrons show that it can provide exact boundaries when a positive charged particle beam current distribution is measured.

physics.ins-det↗