Accelerated discoveries of mechanical properties of graphene using machine learning and high-throughput computation

Zhang, Zesheng; Yang, Hong; Hou, Bo; Zhang, Zhongtao; Negahban, Mehrdad; Zhang, Jingchao

doi:10.1016/j.carbon.2019.03.046

Cited by 79 publications

(51 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given enough data, proper ML and ANN models can be trained to directly predict the material properties with only the knowledge of initial conditions without repetitive experiments or simulations. The predictions using ML and ANN only take a fraction of second for a single case compared to hundreds to thousands of CPU hours using the traditional approach . For proper training of any model, a dataset on the scales of thousands of data points is desired.…”

Section: Property Predictions Using Supervised Algorithmsmentioning

confidence: 99%

“…Aside from various thermal properties mentioned above, different ML models have also been employed to predict the mechanical properties of several 2D materials such as graphene, MoSe 2 , and WS 2 under impact factors of system temperature, strain rate, vacancy defect, and chirality. Unlike the thermal conductivity predictions, the mechanical property predictions have multiple outputs, such as fracture strain, fracture strength, and Young's modulus.…”

Section: Property Predictions Using Supervised Algorithmsmentioning

confidence: 99%

“…In many cases, traditional algorithms such as kNN, DT, RF, and SVM can provide desirable prediction accuracies with fewer hyperparameters to tune. The kNN model even outperformed the ANN model in the prediction of graphene's mechanical properties . On the other hand, in those cases where ANNs are used to construct predictions Nevertheless, neural networks such as CNN still have the edge over traditional algorithms on image‐based regressions .…”

Section: Concluding Remarks and Future Directionsmentioning

confidence: 99%

See 2 more Smart Citations

Machine learning and artificial neural network accelerated computational discoveries in materials science

Yang

Hou

Jiang

et al. 2019

WIREs Comput Mol Sci

Self Cite

View full text Add to dashboard Cite

Artificial intelligence (AI) has been referred to as the "fourth paradigm of science," and as part of a coherent toolbox of data-driven approaches, machine learning (ML) dramatically accelerates the computational discoveries. As the machinery for ML algorithms matures, significant advances have been made not only by the mainstream AI researchers, but also those work in computational materials science. The number of ML and artificial neural network (ANN) applications in the computational materials science is growing at an astounding rate. This perspective briefly reviews the state-of-the-art progress in some supervised and unsupervised methods with their respective applications. The characteristics of primary ML and ANN algorithms are first described. Then, the most critical applications of AI in computational materials science such as empirical interatomic potential development, ML-based potential, property predictions, and molecular discoveries using generative adversarial networks (GAN) are comprehensively reviewed. The central ideas underlying these ML applications are discussed, and future directions for integrating ML with computational materials science are given. Finally, a discussion on the applicability and limitations of current ML techniques and the remaining challenges are summarized.

show abstract

Section: Property Predictions Using Supervised Algorithmsmentioning

confidence: 99%

Section: Property Predictions Using Supervised Algorithmsmentioning

confidence: 99%

Section: Concluding Remarks and Future Directionsmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning and artificial neural network accelerated computational discoveries in materials science

Yang

Hou

Jiang

et al. 2019

WIREs Comput Mol Sci

Self Cite

View full text Add to dashboard Cite

show abstract

“…Structural damage diagnosis and prediction are of utmost importance in various scientific and engineering applications (Cha, Choi, Suh, Mahmoudkhani, & Büyüköztürk, 2018;Chen et al, 2019;Finotti, Cury, & Barbosa, 2019). Second paragraph on general damage detection methods and drawback to those methods (Hong et al, 2019;Huang & Wang, 2018;Jang, Lee, Park, & Baek, 2018;Kan et al, 2017;Krummenacher, Ong, Koller, Kobayashi, & Buhmann, 2018;Wang, Hu, & Zhai, 2018;. Third paragraph on machine learning suitability and importance of machine learning and deep learning methods on this application (H. Li et al, 2019;Y.…”

Section: Introductionmentioning

confidence: 99%

Structural Damage Diagnosis and Prediction Using Machine Learning and Deep Learning Models: Comprehensive Review of Advances<strong> </strong>

Mosavi¹

2019

Preprint

View full text Add to dashboard Cite

The loss of integrity and adverse effect on mechanical properties can be concluded as attributing miro/macro-mechanics damage in structures, especially in composite structures. Damage as a progressive degradation of material continuity in engineering predictions for any aspects of initiation and propagation requires to be identified by a trustworthy mechanism to guarantee the safety of structures. Besides the materials design, structural integrity and health are usually prone to be monitored clearly. One of the most powerful methods for the detection of damage is machine learning (ML). This paper presents the state of the art of ML methods and their applications in structural damage and prediction. Popular ML methods are identified and the performance and future trends are discussed.

show abstract

“…However, in combination with their numerous processing steps, 7xxx alloys are extremely complex and thus hard to optimize via intuition and trial-and-error. Recently, machinelearning-assisted design of multicomponent materials has attracted special interests [25][26][27][28][29][30][31] . We believe that machine learning could play an important role in composition optimization of multicomponent 7xxx alloys, although related publications are limited 32 .…”

mentioning

confidence: 99%

Accelerated discovery of high-strength aluminum alloys by machine learning

Zhang

Cao

et al. 2020

Commun Mater

View full text Add to dashboard Cite

Aluminum alloys are attractive for a number of applications due to their high specific strength, and developing new compositions is a major goal in the structural materials community. Here, we investigate the Al-Zn-Mg-Cu alloy system (7xxx series) by machine learning-based composition and process optimization. The discovered optimized alloy is compositionally lean with a high ultimate tensile strength of 952 MPa and 6.3% elongation following a cost-effective processing route. We find that the Al8Cu4Y phase in wrought 7xxx-T6 alloys exists in the form of a nanoscale network structure along sub-grain boundaries besides the common irregular-shaped particles. Our study demonstrates the feasibility of using machine learning to search for 7xxx alloys with good mechanical performance.

show abstract

Accelerated discoveries of mechanical properties of graphene using machine learning and high-throughput computation

Cited by 79 publications

References 50 publications

Machine learning and artificial neural network accelerated computational discoveries in materials science

Machine learning and artificial neural network accelerated computational discoveries in materials science

Structural Damage Diagnosis and Prediction Using Machine Learning and Deep Learning Models: Comprehensive Review of Advances<strong> </strong>

Accelerated discovery of high-strength aluminum alloys by machine learning

Contact Info

Product

Resources

About