传统的理论研究、实验研究及计算仿真已无法满足科学家对新材料的探索与设计。数据驱动的机器学习算法对材料的筛选与性能预测有着推动作用。将机器学习算法应用到材料信息学,基于现有材料热导率数据集,建立机器学习热导率预测模型,通过交叉验证来对机器学习回归模型进行评估。利用机器学习算法建立描述符与热导率属性之间的映射模型,可用于大规模的材料筛选,从而指导实验研究。
Traditional theoretical research,experimental research and computational simulation have failed to satisfy scientists' exploration and design of new materials.Data-driven machine learning algorithms have a driving role in material screening and performance prediction.The machine learning was applied to material informatics.Based on the existing material thermal conductivity data set,a machine learning thermal conductivity prediction model was developed and evaluated by cross-validation.Machine learning was used to establish a mapping model between descriptors and thermal conductivity properties,which can be used for large-scale material screening to guide experimental research.
[1] Toberer E S,Zevalkink A,Snyder G J.Phonon engineering through crystal chemistry[J].Journal of Materials Chemistry,2011,21(40):15843-15852.
[2] Giardino D,Bettio D,Simoni G.Ab initio calculation of the linewidth of various phonon modes in germanium and silicon[J].Physical Review B,2003,67(14):1393-1406.
[3] Broido D A,Malorny M,Birner G,et al.Intrinsic lattice thermal conductivity of semiconductors from first principles[J].Applied Physics Letters,2007,91(23):231922.
[4] Li W,Mingo N,Lindsay L,et al.Thermal conductivity of diamond nanowires from first principles[J].Physical Review B,2012,85(19):195436.
[5] Allen P B.Zero-point and isotope shifts:relation to thermal shifts[J].Philosophical Magazine Part B,1994,70(3):527-534.
[6] Callaway J.Model for lattice thermal conductivity at low temperatures[J].Physical Review,1959,113(4):436-441.
[7] Rowley R L,Painter M M.Diffusion and viscosity equations of state for a Lennard-Jones fluid obtained from molecular dynamics simulations[J].International Journal of Thermophysics,1997,18(5):1109-1121.
[8] Seko A,Togo A,Hayashi H,et al.Prediction of low-thermal-conductivity compounds with first-principles anharmonic lattice-dynamics calculations and bayesian optimization[J].Physical Review Letters,2015,115(20):205901.
[9] Madsen G K H,Katre A,Bera C.Calculating the thermal conductivity of the silicon clathrates using the quasi-harmonic approximation[J].Physica Status Solidi,2016,213(3):802-807.
[10] Toher C,Plata J J,Levy O,et al.High-throughput computational screening of thermal conductivity,Debye temperature,and Gruneisen parameter using a quasiharmonic Debye model[J].Physical Review B,2014,90(17):174107.
[11] De J M,Chen W,Notestine R,et al.A statistical learning framework for materials science:application to elastic moduli of k-nary inorganic polycrystalline compounds[J].Sci Rep,2016,6:34256.
[12] Medasani B,Gamst A,Ding H,et al.Predicting defect behavior in B2 intermetallics by merging ab initio modeling and machine learning[J].npj Computational Materials,20162(1):1.
[13] Ma X,Li Z,Achenie L E,et al.Machine-learning-augmented chemisorption model for CO2 electroreduction catalyst screening[J].Journal of Physical Chemistry Letters,2015,6(18):3528.
[14] Oliynyk A O,Antono E,Sparks T D,et al.High-throughput machine-learning-driven synthesis of full-heusler compounds[J].Chemistry of Materials,2016,28(20):7324-7331.
[15] Sendek A D,Yang Q,Cubuk E D,et al.Holistic computational structure screening of more than 12000 candidates for solid lithium-ion conductor materials[J].Energy & Environmental Science,2016,10(1):306-320.
[16] Dey P,Bible J,Datta S,et al.Informatics-aided bandgap engineering for solar materials[J].Computational Materials Science,2014,83:185-195.
[17] Xue D,Balachandran P V,Hogden J,et al.Accelerated search for materials with targeted properties by adaptive design[J].Nature Communications,2016,7:11241.
[18] Ghanshyam P,Wang C,Jiang X,et al.Accelerating materials property predictions using machine learning[J].Scientific Reports,2013,3(9):2810.
[19] Mannodikanakkithodi A,Pilania G,Huan T D,et al.Machine learning strategy for accelerated design of polymer dielectrics[J].Scientific Reports,2016,6:20952.
[20] Stanev V,Oses C,Kusne A G,et al.Machine learning modeling of superconducting critical temperature[J].npj Computational Materials,2018,4(1):29.
[21] Conduit B D,Jones N G,Stone H J,et al.Design of a nickel-base superalloy using a neural network[J].Materials & Designm,2017,131:358-365.
[22] Schmidt J,Shi J M,Borlido P,et al.Predicting the thermodynamic stability of solids combining Density functional theory and machine learning[J].Chemistry of Materials,2017,29(12):5090-5103.
[23] Ju S,Shiga T,Feng L,et al.Designing nanostructures for interfacial phonon transport via Bayesian optimization[J].Physical Review X,2017,7(2):021024.
[24] Faber F A,Lindmaa A,von Lilienfeld O A,et al.Machine learning energies of 2 million elpasolite (ABC2D6) crystals[J].Phys Rev Lett,2016,117(13):135502.
[25] Gómez-Bombarelli R,Aguilera-Lparraguirre J,Hirzel T D,et al.Design of efficient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach[J].Nature Materials,2016,15(10):1120.
[26] Meredig B,Agrawal A,Kirklin S,et al.Combinatorial screening for new materials in unconstrained composition space with machine learning[J].Phys Rev B,2014,89(9):82-84.
[27] Pedregosa F,Gramfort A,Michel V,et al.Scikit-learn:machine learning in python[J].Journal of Machine Learning Research,2013,12(10):2825-2830.
[28] Dzbor M,Domingue J,Motta E.Magpie-towards a semantic web browser[J].Lecture Notes in Computer Science,2003,2870:690-705.
[29] Ward L,Agrawal A,Choudhary A,et al.A general-purpose machine learning framework for predicting properties of inorganic materials[J].npj Computational Materials,2016,2:16028.
[30] Zhou Q,Tang P,Liu S,et al.Learning atoms for materials discovery[J].Proceedings of the National Academy of Sciences of the United States of America,2018,115(28):E6411-E6417.
[31] Ma J,Li W,Luo X.Examining the Callaway model for lattice thermal conductivity[J].Physical Review B,2014,90(3):035203.
基金资助
国家自然科学基金(51741101)
PDF
(1172KB)
