4,502 Hits in 7.2 sec

Automating Crystal-Structure Phase Mapping: Combining Deep Learning with Constraint Reasoning [article]

Di Chen, Yiwei Bai, Sebastian Ament, Wenting Zhao, Dan Guevarra, Lan Zhou, Bart Selman, R. Bruce van Dover, John M. Gregoire, Carla P. Gomes
2021 arXiv   pre-print
Herein we show how to automate crystal-structure phase mapping.  ...  DRNets combine deep learning with constraint reasoning for incorporating scientific prior knowledge and consequently require only a modest amount of (unlabeled) data.  ...  DRNets for phase mapping and corresponding experimental work were also supported by AFOSR Multidisciplinary University Research Initiatives (MURI) Program FA9550-18-1-0136, ARO awards W911NF-14-1-0498  ... 
arXiv:2108.09523v1 fatcat:sed2voog2nhm3iz4yp77xyqksm

Perspective: Composition–structure–property mapping in high-throughput experiments: Turning data into knowledge

Jason R. Hattrick-Simpers, John M. Gregoire, A. Gilad Kusne
2016 APL Materials  
We will discuss four methods with proven success in phase diagram determination: feature learning, clustering, matrix factorization, and constraint reasoning.  ...  Combined with the capability to generate a comprehensive set of heat maps for XRD data sets in high-order composition spaces, the phase map problem could in principle be solved by brute force human computation  ... 
doi:10.1063/1.4950995 fatcat:4vrqjh4cqjggte7hb5p4hygq54

Inverse design of crystal structures for multicomponent systems [article]

Teng Long, Yixuan Zhang, Nuno M. Fortunato, Chen Shen, Mian Dai, Hongbin Zhang
2021 arXiv   pre-print
We developed an inverse design framework enabling automated generation of stable multi-component crystal structures by optimizing the formation energies in the latent space based on reversible crystal  ...  Moreover, the generation efficiency can be further improved by considering extra hypothetical structures in the training.  ...  Such models act on the crystal graphs, which are one-to-one mapping to the crystal structures, with the transformations managed by the autoencoder, i.e., encoder and decoder.  ... 
arXiv:2104.08040v3 fatcat:zx6ve6pfvnb77ls2udg6iaoame

Constrained crystals deep convolutional generative adversarial network for the inverse design of crystal structures

Teng Long, Nuno M. Fortunato, Ingo Opahle, Yixuan Zhang, Ilias Samathrakis, Chen Shen, Oliver Gutfleisch, Hongbin Zhang
2021 npj Computational Materials  
Applying the deep learning techniques, we have developed a generative model, which can predict distinct stable crystal structures by optimizing the formation energy in the latent space.  ...  Applying the generative models on the binary Bi-Se system reveals that distinct crystal structures can be obtained covering the whole composition range, and the phases on the convex hull can be reproduced  ...  deep learning.  ... 
doi:10.1038/s41524-021-00526-4 fatcat:3peyhnl3sfcirn6o3m7kzlofkq

Probabilistic Assessment of Glass Forming Ability Rules for Metallic Glasses Aided by Automated Analysis of Phase Diagrams

Aparajita Dasgupta, Scott R. Broderick, Connor Mack, Bhargava U. Kota, Ramachandran Subramanian, Srirangaraj Setlur, Venu Govindaraju, Krishna Rajan
2019 Scientific Reports  
Acknowledgements This material is based upon work supported by the National Science Foundation under Grant No. 1640867.  ...  For the latter, we demonstrate the use of automated machine learning methods that go far beyond text recognition approaches by also being able to interpret phase diagrams.  ...  Combining Machine Learning with the Heuristics Space. A focus on the design of BMG systems has been the eutectic points within the thermodynamic phase diagram of a system.  ... 
doi:10.1038/s41598-018-36224-3 fatcat:o5pnl6bc3rcijgvby4kmqad5ve

Contact Map based Crystal Structure Prediction using Global Optimization [article]

Jianjun Hu, Wenhui Yang, Rongzhi Dong, Yuxin Li, Xiang Li, Shaobo Li
2021 arXiv   pre-print
Inspired by the knowledge-rich protein structure prediction approach, herein we explore whether known geometric constraints such as the atomic contact map of a target crystal material can help predict  ...  Global optimization methods such as genetic algorithms (GA) and particle swarm optimization (PSO) have been combined with first principle free energy calculations to predict crystal structures given composition  ...  structures that can be learned by the deep neural network models.  ... 
arXiv:2008.07016v2 fatcat:ypyl3dtyhvhetlqw2nm567yree

Automated prediction of lattice parameters from X-ray powder diffraction patterns

Sathya R. Chitturi, Daniel Ratner, Richard C. Walroth, Vivek Thampy, Evan J. Reed, Mike Dunne, Christopher J. Tassone, Kevin H. Stone
2021 Journal of Applied Crystallography  
The models learn from nearly one million crystal structures contained within the Inorganic Crystal Structure Database and the Cambridge Structural Database and, due to the nature of these two complimentary  ...  In order to obtain accurate results, a new approach is introduced which uses the initial machine learning estimates with existing iterative whole-pattern refinement schemes to tackle automated unit-cell  ...  Acknowledgements SRC gratefully acknowledges very helpful discussions with Alan Coelho regarding the Lp-Search algorithm.  ... 
doi:10.1107/s1600576721010840 pmid:34963768 pmcid:PMC8662964 fatcat:7khyeiyyv5aerimhpvcbhjglti

Mapping the Design Space of Photonic Topological States via Deep Learning [article]

Robin Singh, Anuradha Murthy Agarwal, Brian W Anthony
2020 arXiv   pre-print
In this manuscript, we develop a deep learning framework to map the design space of topological states in the photonic crystals.  ...  This framework overcomes the limitations of existing deep learning implementations.  ...  ACKNOWLEDGMENTS Authors would like to thank Manish Singh, a member of Laboratory of Financial Engineering & CSAIL MIT for the useful insights in machine learning methods.  ... 
arXiv:2006.09163v1 fatcat:pi6lcbbdkzam5bpaoqd4ehkhly

Crystallography companion agent for high-throughput materials discovery [article]

Phillip M. Maffettone, Lars Banko, Peng Cui, Yury Lysogorskiy, Marc A. Little, Daniel Olds, Alfred Ludwig, Andrew I. Cooper
2021 arXiv   pre-print
The discovery of new structural and functional materials is driven by phase identification, often using X-ray diffraction (XRD).  ...  With the advent of autonomous robotic scientists or self-driving labs, contemporary techniques prohibit the integration of XRD.  ...  The exact datasets are available from the authors on reasonable request, with the code used for construction available on the Github below.  ... 
arXiv:2008.00283v2 fatcat:3x76navyrzga7hosstyhsehcqe

Implications of the BATTERY 2030+ AI‐Assisted Toolkit on Future Low‐TRL Battery Discoveries and Chemistries

Arghya Bhowmik, Maitane Berecibar, Montse Casas‐Cabanas, Gabor Csanyi, Robert Dominko, Kersti Hermansson, M. Rosa Palacin, Helge S. Stein, Tejs Vegge
2021 Advanced Energy Materials  
The methodological perspectives and challenges in areas like predictive long time-and length-scale simulations of multi-species systems, dynamic processes at battery interfaces, deep learned multi-scaling  ...  the main scientific and technological challenges facing emerging low-technology readiness level (TRL) battery chemistries and concepts, and specifically how the AI-assisted toolkit developed within BIG-MAP  ...  Acknowledgements The authors acknowledge the European Union's Horizon 2020 research and innovation program under grant agreements no. 957189 (BIG-MAP) and no. 957213 (BATTERY 2030+).  ... 
doi:10.1002/aenm.202102698 fatcat:muafelf4yrb7licg3lqpbmqmry

Machine-Enabled Inverse Design of Inorganic Solid Materials: Promises and Challenges

Juhwan Noh, Geun Ho Gu, Sungwon Kim, Yousung Jung
2020 Chemical Science  
Random structure search, oen constrained by a few chemical rules, is one of the simplest yet successful search strategies to nd new phases of crystals, and Pickard and Needs combined it with rst-principles  ...  In an inverse mapping, by contrast, one denes the desired properties rst and attempts to nd materials with such properties in an inverse manner using mathematical algorithms and automations.  ... 
doi:10.1039/d0sc00594k pmid:34122942 pmcid:PMC8159218 fatcat:pjdy37k7pndtnldcaaf267gvha

Generative models for inverse design of inorganic solid materials

Litao Chen, Wentao Zhang, Zhiwei Nie, Shunning Li, Feng Pan
2021 Journal of Materials Informatics  
properties are mapped to the chemical structures.  ...  While the conventional approach to innovation relies mainly on experimentation, the generative models stemming from the field of machine learning can realize the long-held dream of inverse design, where  ...  unacceptable errors in encoding crystals with similar or identical structures.  ... 
doi:10.20517/jmi.2021.07 fatcat:i2rvycr73zeznii43zltreiloy

Recent Trends in Artificial Intelligence-inspired Electronic Thermal Management [article]

Aviral Chharia, Nishi Mehta, Shivam Gupta, Shivam Prajapati
2021 arXiv   pre-print
The present study discusses in detail, the current uses of deep learning in the domain of 'electronic' thermal management.  ...  However, they come with some limitations.  ...  Wei Liu, Ying Tan and Qinru Qiu (2010) ‘Enhanced Q-learning algorithm for dynamic power management with performance constraint’, in 2010 Design, Automation & Test in Europe Conference & Exhibition (DATE  ... 
arXiv:2112.14837v1 fatcat:w5jdrf55mnfb3iqfnrld3mqz4i

Recent Advances and Applications of Deep Learning Methods in Materials Science [article]

Kamal Choudhary, Brian DeCost, Chi Chen, Anubhav Jain, Francesca Tavazza, Ryan Cohn, Cheol WooPark, Alok Choudhary, Ankit Agrawal, Simon J. L. Billinge, Elizabeth Holm, Shyue Ping Ong (+1 others)
2021 arXiv   pre-print
In this article, we present a high-level overview of deep-learning methods followed by a detailed discussion of recent developments of deep learning in atomistic simulation, materials imaging, spectral  ...  Deep learning (DL) is one of the fastest growing topics in materials data science, with rapidly emerging applications spanning atomistic, image-based, spectral, and textual data modalities.  ...  Deep ensemble methodologies [338] [339] [340] [341] combine deep learning modelling with ensemble learning.  ... 
arXiv:2110.14820v1 fatcat:gn5xd7fazjftpcpzkei2aemgpe

Mapping mesoscopic phase evolution during e-beam induced transformations via deep learning of atomically resolved images [article]

Rama K. Vasudevan, Nouamane Laanait, Erik M. Ferragut, Kai Wang, David B. Geohegan, Kai Xiao, Maxim A. Ziatdinov, Stephen Jesse, Ondrej E. Dyck, Sergei V. Kalinin
2018 arXiv   pre-print
Understanding transformations under electron beam irradiation requires mapping the structural phases and their evolution in real time.  ...  To date, this has mostly been a manual endeavor comprising of difficult frame-by-frame analysis that is simultaneously tedious and prone to error.  ...  Combined with other recent advances in deep learning for atomic scale image analysis 36 , we believe these studies lay the foundation for a 2D AI crystallographer, which will be integral in future automated  ... 
arXiv:1802.10518v1 fatcat:4ysd4szc4fdbneluned4t3zyje
« Previous Showing results 1 — 15 out of 4,502 results