DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Autonomous reinforcement learning agent for stretchable kirigami design of 2D materials

Abstract

Abstract Mechanical behavior of 2D materials such as MoS 2 can be tuned by the ancient art of kirigami. Experiments and atomistic simulations show that 2D materials can be stretched more than 50% by strategic insertion of cuts. However, designing kirigami structures with desired mechanical properties is highly sensitive to the pattern and location of kirigami cuts. We use reinforcement learning (RL) to generate a wide range of highly stretchable MoS 2 kirigami structures. The RL agent is trained by a small fraction (1.45%) of molecular dynamics simulation data, randomly sampled from a search space of over 4 million candidates for MoS 2 kirigami structures with 6 cuts. After training, the RL agent not only proposes 6-cut kirigami structures that have stretchability above 45%, but also gains mechanistic insight to propose highly stretchable (above 40%) kirigami structures consisting of 8 and 10 cuts from a search space of billion candidates as zero-shot predictions.

Authors:
ORCiD logo; ; ; ; ORCiD logo; ; ORCiD logo
Publication Date:
Research Org.:
Argonne National Lab. (ANL), Argonne, IL (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES). Scientific User Facilities Division; National Science Foundation (NSF); Aurora Early Science Program
OSTI Identifier:
1806585
Alternate Identifier(s):
OSTI ID: 1863249
Grant/Contract Number:  
AC02-06CH11357
Resource Type:
Published Article
Journal Name:
npj Computational Materials
Additional Journal Information:
Journal Name: npj Computational Materials Journal Volume: 7 Journal Issue: 1; Journal ID: ISSN 2057-3960
Publisher:
Nature Publishing Group
Country of Publication:
United Kingdom
Language:
English
Subject:
36 MATERIALS SCIENCE

Citation Formats

Rajak, Pankaj, Wang, Beibei, Nomura, Ken-ichi, Luo, Ye, Nakano, Aiichiro, Kalia, Rajiv, and Vashishta, Priya. Autonomous reinforcement learning agent for stretchable kirigami design of 2D materials. United Kingdom: N. p., 2021. Web. doi:10.1038/s41524-021-00572-y.
Rajak, Pankaj, Wang, Beibei, Nomura, Ken-ichi, Luo, Ye, Nakano, Aiichiro, Kalia, Rajiv, & Vashishta, Priya. Autonomous reinforcement learning agent for stretchable kirigami design of 2D materials. United Kingdom. https://doi.org/10.1038/s41524-021-00572-y
Rajak, Pankaj, Wang, Beibei, Nomura, Ken-ichi, Luo, Ye, Nakano, Aiichiro, Kalia, Rajiv, and Vashishta, Priya. Fri . "Autonomous reinforcement learning agent for stretchable kirigami design of 2D materials". United Kingdom. https://doi.org/10.1038/s41524-021-00572-y.
@article{osti_1806585,
title = {Autonomous reinforcement learning agent for stretchable kirigami design of 2D materials},
author = {Rajak, Pankaj and Wang, Beibei and Nomura, Ken-ichi and Luo, Ye and Nakano, Aiichiro and Kalia, Rajiv and Vashishta, Priya},
abstractNote = {Abstract Mechanical behavior of 2D materials such as MoS 2 can be tuned by the ancient art of kirigami. Experiments and atomistic simulations show that 2D materials can be stretched more than 50% by strategic insertion of cuts. However, designing kirigami structures with desired mechanical properties is highly sensitive to the pattern and location of kirigami cuts. We use reinforcement learning (RL) to generate a wide range of highly stretchable MoS 2 kirigami structures. The RL agent is trained by a small fraction (1.45%) of molecular dynamics simulation data, randomly sampled from a search space of over 4 million candidates for MoS 2 kirigami structures with 6 cuts. After training, the RL agent not only proposes 6-cut kirigami structures that have stretchability above 45%, but also gains mechanistic insight to propose highly stretchable (above 40%) kirigami structures consisting of 8 and 10 cuts from a search space of billion candidates as zero-shot predictions.},
doi = {10.1038/s41524-021-00572-y},
journal = {npj Computational Materials},
number = 1,
volume = 7,
place = {United Kingdom},
year = {Fri Jul 09 00:00:00 EDT 2021},
month = {Fri Jul 09 00:00:00 EDT 2021}
}

Works referenced in this record:

Kirigami metamaterials for reconfigurable toroidal circular dichroism
journal, September 2018


Tunable Mechanical Metamaterials through Hybrid Kirigami Structures
journal, February 2018


Role of strain on electronic and mechanical response of semiconducting transition-metal dichalcogenide monolayers: An ab-initio study
journal, June 2014

  • Guzman, David M.; Strachan, Alejandro
  • Journal of Applied Physics, Vol. 115, Issue 24
  • DOI: 10.1063/1.4883995

Chalcogenide glass-on-graphene photonics
journal, October 2017


Deep reinforcement learning for de novo drug design
journal, July 2018

  • Popova, Mariya; Isayev, Olexandr; Tropsha, Alexander
  • Science Advances, Vol. 4, Issue 7
  • DOI: 10.1126/sciadv.aap7885

Structural Phase Transformation in Strained Monolayer MoWSe 2 Alloy
journal, February 2018


Structural phase transitions in a MoWSe 2 monolayer: Molecular dynamics simulations and variational autoencoder analysis
journal, July 2019


Nature’s Way: Hierarchical Strengthening through Weakness
journal, August 2019


De novo composite design based on machine learning algorithm
journal, January 2018


Modeling the Phase-Change Memory Material, Ge 2 Sb 2 Te 5 , with a Machine-Learned Interatomic Potential
journal, September 2018

  • Mocanu, Felix C.; Konstantinou, Konstantinos; Lee, Tae Hoon
  • The Journal of Physical Chemistry B, Vol. 122, Issue 38
  • DOI: 10.1021/acs.jpcb.8b06476

Buckling-Induced Kirigami
journal, February 2017


Nanoindentation on Monolayer MoS 2 Kirigami
journal, June 2019


Machine learning in materials informatics: recent applications and prospects
journal, December 2017

  • Ramprasad, Rampi; Batra, Rohit; Pilania, Ghanshyam
  • npj Computational Materials, Vol. 3, Issue 1
  • DOI: 10.1038/s41524-017-0056-5

Graphene kirigami
journal, July 2015

  • Blees, Melina K.; Barnard, Arthur W.; Rose, Peter A.
  • Nature, Vol. 524, Issue 7564
  • DOI: 10.1038/nature14588

Bandgap Engineering of Strained Monolayer and Bilayer MoS2
journal, July 2013

  • Conley, Hiram J.; Wang, Bin; Ziegler, Jed I.
  • Nano Letters, Vol. 13, Issue 8, p. 3626-3630
  • DOI: 10.1021/nl4014748

Optimizing Chemical Reactions with Deep Reinforcement Learning
journal, November 2017


Single-Layer MoS 2 with Sulfur Vacancies: Structure and Catalytic Application
journal, March 2014

  • Le, Duy; Rawal, Takat B.; Rahman, Talat S.
  • The Journal of Physical Chemistry C, Vol. 118, Issue 10
  • DOI: 10.1021/jp411256g

Atomically Sharp Crack Tips in Monolayer MoS 2 and Their Enhanced Toughness by Vacancy Defects
journal, September 2016


Active learning for accelerated design of layered materials
journal, December 2018

  • Bassman, Lindsay; Rajak, Pankaj; Kalia, Rajiv K.
  • npj Computational Materials, Vol. 4, Issue 1
  • DOI: 10.1038/s41524-018-0129-0

Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules
journal, January 2018

  • Gómez-Bombarelli, Rafael; Wei, Jennifer N.; Duvenaud, David
  • ACS Central Science, Vol. 4, Issue 2
  • DOI: 10.1021/acscentsci.7b00572

2-Dimensional Transition Metal Dichalcogenides with Tunable Direct Band Gaps: MoS 2(1-x) Se 2x Monolayers
journal, December 2013


Mechanical metamaterials with negative compressibility transitions
journal, May 2012

  • Nicolaou, Zachary G.; Motter, Adilson E.
  • Nature Materials, Vol. 11, Issue 7
  • DOI: 10.1038/nmat3331

Structure-property relationships from universal signatures of plasticity in disordered solids
journal, November 2017


Stretching and Breaking of Ultrathin MoS 2
journal, November 2011

  • Bertolazzi, Simone; Brivio, Jacopo; Kis, Andras
  • ACS Nano, Vol. 5, Issue 12
  • DOI: 10.1021/nn203879f

A cellular metastructure incorporating coupled negative thermal expansion and negative Poisson's ratio
journal, October 2018


A kirigami approach to engineering elasticity in nanocomposites through patterned defects
journal, June 2015

  • Shyu, Terry C.; Damasceno, Pablo F.; Dodd, Paul M.
  • Nature Materials, Vol. 14, Issue 8
  • DOI: 10.1038/nmat4327

Accelerated discovery of metallic glasses through iteration of machine learning and high-throughput experiments
journal, April 2018


2D Electrets of Ultrathin MoO 2 with Apparent Piezoelectricity
journal, May 2020

  • Apte, Amey; Mozaffari, Kosar; Samghabadi, Farnaz Safi
  • Advanced Materials, Vol. 32, Issue 24
  • DOI: 10.1002/adma.202000006

Two-Dimensional Transition Metal Dichalcogenide Alloys: Stability and Electronic Properties
journal, November 2012

  • Komsa, Hannu-Pekka; Krasheninnikov, Arkady V.
  • The Journal of Physical Chemistry Letters, Vol. 3, Issue 23, p. 3652-3656
  • DOI: 10.1021/jz301673x

A universal strategy for the creation of machine learning-based atomistic force fields
journal, September 2017


Flexible and Transparent MoS 2 Field-Effect Transistors on Hexagonal Boron Nitride-Graphene Heterostructures
journal, August 2013

  • Lee, Gwan-Hyoung; Yu, Young-Jun; Cui, Xu
  • ACS Nano, Vol. 7, Issue 9
  • DOI: 10.1021/nn402954e

High-performance stretchable conductive nanocomposites: materials, processes, and device applications
journal, January 2019

  • Choi, Suji; Han, Sang Ihn; Kim, Dokyoon
  • Chemical Society Reviews, Vol. 48, Issue 6
  • DOI: 10.1039/C8CS00706C

Inverse molecular design using machine learning: Generative models for matter engineering
journal, July 2018


Growth of Polypyrrole Ultrathin Films on MoS 2 Monolayers as High-Performance Supercapacitor Electrodes
journal, December 2014


Quantifying Chemical Structure and Machine-Learned Atomic Energies in Amorphous and Liquid Silicon
journal, April 2019

  • Bernstein, Noam; Bhattarai, Bishal; Csányi, Gábor
  • Angewandte Chemie International Edition, Vol. 58, Issue 21
  • DOI: 10.1002/anie.201902625

Origami and Kirigami Nanocomposites
journal, August 2017


Human-level control through deep reinforcement learning
journal, February 2015

  • Mnih, Volodymyr; Kavukcuoglu, Koray; Silver, David
  • Nature, Vol. 518, Issue 7540
  • DOI: 10.1038/nature14236

Vertical and in-plane heterostructures from WS2/MoS2 monolayers
journal, September 2014

  • Gong, Yongji; Lin, Junhao; Wang, Xingli
  • Nature Materials, Vol. 13, Issue 12, p. 1135-1142
  • DOI: 10.1038/nmat4091

Taking the Human Out of the Loop: A Review of Bayesian Optimization
journal, January 2016


Highly stretchable MoS 2 kirigami
journal, January 2016

  • Hanakata, Paul Z.; Qi, Zenan; Campbell, David K.
  • Nanoscale, Vol. 8, Issue 1
  • DOI: 10.1039/C5NR06431G

A fast neural network approach for direct covariant forces prediction in complex multi-element extended systems
journal, September 2019

  • Mailoa, Jonathan P.; Kornbluth, Mordechai; Batzner, Simon
  • Nature Machine Intelligence, Vol. 1, Issue 10
  • DOI: 10.1038/s42256-019-0098-0

LASEC: Instant Fabrication of Stretchable Circuits Using a Laser Cutter
conference, May 2019

  • Groeger, Daniel; Steimle, Jürgen
  • CHI '19: CHI Conference on Human Factors in Computing Systems, Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems
  • DOI: 10.1145/3290605.3300929

Manipulating spin-polarized photocurrents in 2D transition metal dichalcogenides
journal, March 2016

  • Xie, Lu; Cui, Xiaodong
  • Proceedings of the National Academy of Sciences, Vol. 113, Issue 14
  • DOI: 10.1073/pnas.1523012113

Fracture toughness of graphene
journal, April 2014

  • Zhang, Peng; Ma, Lulu; Fan, Feifei
  • Nature Communications, Vol. 5, Issue 1
  • DOI: 10.1038/ncomms4782

Extremely compliant and highly stretchable patterned graphene
journal, April 2014

  • Zhu, Shuze; Huang, Yinjun; Li, Teng
  • Applied Physics Letters, Vol. 104, Issue 17
  • DOI: 10.1063/1.4874337

Commentary: The Materials Project: A materials genome approach to accelerating materials innovation
journal, July 2013

  • Jain, Anubhav; Ong, Shyue Ping; Hautier, Geoffroy
  • APL Materials, Vol. 1, Issue 1
  • DOI: 10.1063/1.4812323

Recent Strategies for Improving the Catalytic Activity of 2D TMD Nanosheets Toward the Hydrogen Evolution Reaction
journal, February 2016

  • Voiry, Damien; Yang, Jieun; Chhowalla, Manish
  • Advanced Materials, Vol. 28, Issue 29
  • DOI: 10.1002/adma.201505597

Initial rigid response and softening transition of highly stretchable kirigami sheet materials
journal, April 2016

  • Isobe, Midori; Okumura, Ko
  • Scientific Reports, Vol. 6, Issue 1
  • DOI: 10.1038/srep24758

Reversible MoS 2 Origami with Spatially Resolved and Reconfigurable Photosensitivity
journal, September 2019


Impact of Interfacial Defects on the Properties of Monolayer Transition Metal Dichalcogenide Lateral Heterojunctions
journal, March 2017

  • Cao, Zhen; Harb, Moussab; Lardhi, Sheikha
  • The Journal of Physical Chemistry Letters, Vol. 8, Issue 7
  • DOI: 10.1021/acs.jpclett.7b00518

Constructing high-dimensional neural network potentials: A tutorial review
journal, March 2015

  • Behler, Jörg
  • International Journal of Quantum Chemistry, Vol. 115, Issue 16
  • DOI: 10.1002/qua.24890

Machine Learning Strategy for Accelerated Design of Polymer Dielectrics
journal, February 2016

  • Mannodi-Kanakkithodi, Arun; Pilania, Ghanshyam; Huan, Tran Doan
  • Scientific Reports, Vol. 6, Issue 1
  • DOI: 10.1038/srep20952

Closed-loop optimization of fast-charging protocols for batteries with machine learning
journal, February 2020


Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons
journal, April 2010


Nano-kirigami with giant optical chirality
journal, July 2018


Formation enthalpies for transition metal alloys using machine learning
journal, June 2017


Artificial intelligence design algorithm for nanocomposites optimized for shear crack resistance
journal, August 2019


Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
journal, April 2018


Single-layer MoS2 transistors
journal, January 2011

  • Radisavljevic, B.; Radenovic, A.; Brivio, J.
  • Nature Nanotechnology, Vol. 6, Issue 3, p. 147-150
  • DOI: 10.1038/nnano.2010.279

Machine learning for molecular and materials science
journal, July 2018


Planning chemical syntheses with deep neural networks and symbolic AI
journal, March 2018

  • Segler, Marwin H. S.; Preuss, Mike; Waller, Mark P.
  • Nature, Vol. 555, Issue 7698
  • DOI: 10.1038/nature25978

Materials and Structures toward Soft Electronics
journal, August 2018

  • Wang, Chunfeng; Wang, Chonghe; Huang, Zhenlong
  • Advanced Materials, Vol. 30, Issue 50
  • DOI: 10.1002/adma.201801368

Using Deep Learning to Predict Fracture Patterns in Crystalline Solids
journal, July 2020