Predicting the effective thermal conductivities of composite materials and porous media by machine learning methods

Wei, Han; Zhao, Shanshan; Rong, Qingyuan; Bao, Hua

doi:10.1016/j.ijheatmasstransfer.2018.08.082

Cited by 231 publications

(109 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This paradigm change is further promoted by projects like the materials genome initiative (Materials genome initiative) that aim to bridge the gap between experiment and theory and promote a more data-intensive and systematic research approach. A multitude of already successful machine learning applications in materials science can be found, e.g., the prediction of new stable materials, [27][28][29][30][31][32][33][34][35] the calculation of numerous material properties, [36][37][38][39][40][41][42][43][44][45][46][47][48][49][50][51] and the speeding up of firstprinciple calculations. 52 Machine learning algorithms have already revolutionized other fields, such as image recognition.…”

Section: Introductionmentioning

confidence: 99%

Recent advances and applications of machine learning in solid-state materials science

et al. 2019

View full text Add to dashboard Cite

One of the most exciting tools that have entered the material science toolbox in recent years is machine learning. This collection of statistical methods has already proved to be capable of considerably speeding up both fundamental and applied research. At present, we are witnessing an explosion of works that develop and apply machine learning to solid-state systems. We provide a comprehensive overview and analysis of the most recent research in this topic. As a starting point, we introduce machine learning principles, algorithms, descriptors, and databases in materials science. We continue with the description of different machine learning approaches for the discovery of stable materials and the prediction of their crystal structure. Then we discuss research in numerous quantitative structure-property relationships and various approaches for the replacement of first-principle methods by machine learning. We review how active learning and surrogate-based optimization can be applied to improve the rational design process and related examples of applications. Two major questions are always the interpretability of and the physical understanding gained from machine learning models. We consider therefore the different facets of interpretability and their importance in materials science. Finally, we propose solutions and future research paths for various challenges in computational materials science.

show abstract

Section: Introductionmentioning

confidence: 99%

Recent advances and applications of machine learning in solid-state materials science

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Besides, MD simulation is computationally expensive and time-consuming, which limits its applications as screening tools for specific materials. Lately, machine learning methods have been applied to predict composite thermal conductivity, ITR between graphene and boron nitride, and thermoelectric conversion efficiency [30][31][32][33][34][35][36][37][38] . Specifically, Xu group 8 applied machine learning algorithms as regression tree ensembles of LSBoost, support vector machines, and Gaussian regress processes to build ITR prediction models.…”

Section: Xiaojuan Tian 1* and Mingguang Chen 2*mentioning

confidence: 99%

Descriptor selection for predicting interfacial thermal resistance by machine learning methods

Tian

Chen

2021

Sci Rep

View full text Add to dashboard Cite

Interfacial thermal resistance (ITR) is a critical property for the performance of nanostructured devices where phonon mean free paths are larger than the characteristic length scales. The affordable, accurate and reliable prediction of ITR is essential for material selection in thermal management. In this work, the state-of-the-art machine learning methods were employed to realize this. Descriptor selection was conducted to build robust models and provide guidelines on determining the most important characteristics for targets. Firstly, decision tree (DT) was adopted to calculate the descriptor importances. And descriptor subsets with topX highest importances were chosen (topX-DT, X = 20, 15, 10, 5) to build models. To verify the transferability of the descriptors picked by decision tree, models based on kernel ridge regression, Gaussian process regression and K-nearest neighbors were also evaluated. Afterwards, univariate selection (UV) was utilized to sort descriptors. Finally, the top5 common descriptors selected by DT and UV were used to build concise models. The performance of these refined models is comparable to models using all descriptors, which indicates the high accuracy and reliability of these selection methods. Our strategy results in concise machine learning models for a fast prediction of ITR for thermal management applications.

show abstract

Section: Property Predictions Using Supervised Algorithmsmentioning

confidence: 99%

“…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 . As to GAN models, the text‐based representations are being replaced by molecular graphs and 3D chemical structures.…”

Section: Concluding Remarks and Future Directionsmentioning

confidence: 99%

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

Yang

Hou

Jiang

et al. 2019

WIREs Comput Mol Sci

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

Predicting the effective thermal conductivities of composite materials and porous media by machine learning methods

Cited by 231 publications

References 23 publications

Recent advances and applications of machine learning in solid-state materials science

Recent advances and applications of machine learning in solid-state materials science

Descriptor selection for predicting interfacial thermal resistance by machine learning methods

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

Contact Info

Product

Resources

About