Abstract: Materials informatics promotes the development of materials science by using data centric method.It extracts material features from existing material databases and uses machine learning to predict and research new materials.From the perspective of machine learning methods (supervised learning,unsupervised learning,active learning and semi supervised learning),the related research progress of various learning methods in performance prediction,structure prediction and algorithm optimization was summarized.The unsolved problems and possible future development hotspots of machine learning in materials science were analyzed and prospected.
刘霏凝, 石竞琛, 王文杰, 赵瑞. 材料科学中机器学习算法的应用综述[J]. 化工新型材料, 2022, 50(9): 42-46.
Liu Feining, Shi Jingchen, Wang Wenjie, Zhao Rui. Review of machine learning algorithm applied in materials science. New Chemical Materials, 2022, 50(9): 42-46.
[1] 牛程程,李少波,胡建军,等.机器学习在材料信息学中的应用综述[J].材料导报,2020,34(23):9. [2] Hehemann J H,Correc G,Barbeyron T,et al.Transfer of carbohydrate-active enzymes from marine bacteria to Japanese gut microbiota[J].Nature,2010,464(7290):908-912. [3] Vinayagam A,Hu Y H,Kulkarni M,et al.Protein complex-based analysis framework for high-throughput data sets[J].Science Signaling,2013,6(264):rs5. [4] Yvonnet J,Auffray N,Monchiet V.Computational second-order homogenization of materials with effective anisotropic strain-gradient behavior[J].International Journal of Solids and Structures,2020,191-192:434-448. [5] Carrete J,Mingo N,Wang S D,et al.Nanograined half-heusler semiconductors as advanced thermoelectrics:an Ab initio high-throughput statistical study[J].Advanced Functional Materials,2014,24(47):7427-7432. [6] Im J,Lee S,Ko T W,et al.Identifying Pb-free perovskites for solar cells by machine learning[J].NPJ Computational Materials,2019,5:37. [7] Wang J Q,Nobakht A Y,Blanks J D,et al.Machine learning for thermal transport analysis of aluminum alloys with precipitate morphology[J].Advanced Theory and Simulations,2019,2(4):1800196. [8] Choi H,Venkiteela G,Gregori A,et al.Advanced quality control models for concrete admixtures[J].Journal of Materials in Civil Engineering,2020,32(2):04019349. [9] Schulz K,Kreis S,Trittenbach H,et al.Data-driven crack assessment based on surface measurements[J].Engineering Fracture Mechanics,2019,218:106552. [10] Ulissi Z W,Tang M T,Xiao J P,et al.Machine-learning methods enable exhaustive searches for active bimetallic facets and reveal active site motifs for CO2 reduction[J].ACS Catalysis,2017,7(10):6600-6608. [11] Yu T Y,Li Z X,Wu D Z.Predictive modeling of material removal rate in chemical mechanical planarization with physics-informed machine learning[J].Wear,2019,426:1430-1438. [12] Davies D W,Butler K T,Walsh.Data-driven discovery of photoactive quaternary oxides using first-principles machine learning[J].Chemistry of Materials,2019,31(18):7221-7230. [13] Hautier G,Fischer C C,Jain A,et al.Finding nature's missing ternary oxide compounds using machine learning and density functional theory[J].Chemistry of Materials,2010,22(12):3762-3767. [14] Fischer C C,Tibbetts K J,Morgan D,et al.Predicting crystal structure by merging data mining with quantum mechanics[J].Nature Materials,2006,5(8):641-646. [15] Meredig B,Agrawal A,Kirklin S,et al.Combinatorial screening for new materials in unconstrained composition space with machine learning[J].Physical Review B,2014,89(9):094104. [16] Borjali A,Monson K,Raeymaekers B.Predicting the polyethylene wear rate in pin-on-disc experiments in the context of prosthetic hip implants:deriving a data-driven model using machine learning methods[J].Tribology International,2019,133:101-110. [17] Umegaki T,Watanabe Y,Nukui N,et al.Optimization of catalyst for methanol synthesis by a combinatorial approach using a parallel activity test and genetic algorithm assisted by a neural network[J].Energy & Fuels,2003,17(4):850-856. [18] Kang H H,Kaya M,Hajimirza S.A data driven artificial neural network model for predicting radiative properties of metallic packed beds[J].Journal of Quantitative Spectroscopy and Radiative Transfer,2019,226:66-72. [19] Zhang J X,Liu X L,Bi S R,et al.Robust data-driven approach for predicting the configurational energy of high entropy alloys[J].Materials & Design,2020,185:108247. [20] Liu Y,Wu J M,Acdeev M,et al.Multi-layer feature selection incorporating weighted score-based expert knowledge toward modeling materials with targeted properties[J].Advanced Theory and Simulations,2020,3(2):1900215. [21] Pruksawan S,Lambard G,Samitsu S,et al.Prediction and optimization of epoxy adhesive strength from a small dataset through active learning[J].Science and Technology of Advanced Materials,2019,20(1):1010-1021. [22] Faber F,Lindmaa A,von Lilienfeld O A,et al.Crystal structure representations for machine learning models of formation energies[J].International Journal of Quantum Chemistry,2015,115(16):1094-1101. [23] Yosipof A,Khalemsky A,Grlbard R,et al.Dynamic classification for materials-informatics:mining the solar cell space[J].Molecular Informatics,2022,41(1):2000173. [24] Wang Y F,Yu C F,Xing L L,et al.A data-driven scheme for quantitative analysis of texture[J].Metallurgical and Materials Transactions A,2019,51(2):940-950. [25] Kautz E,Ma W F,Jana S,et al.An image-driven machine learning approach to kinetic modeling of a discontinuous precipitation reaction[J].Materials Characterization,2020,166:110379. [26] 韩嵩,韩秋弘,半监督学习研究的述评[J].计算机工程与应用,2020,56(6):19-27. [27] 刘康,钱旭,王自强.主动学习算法综述[J].计算机工程与应用,2012,48(34):1-4. [28] Townsend J,Micucci C P,Hymel J H,et al.Representation of molecular structures with persistent homology for machine learning applications in chemistry[J].Nature Communications,2020,11(1):3579. [29] Gubaev K,Podryabinkin E V,Hart G,et al.Accelerating high-throughput searches for new alloys with active learning of interatomic potentials[J].Computational Materials Science,2019,156:148-156. [30] 陈武锦.半监督学习研究综述[J].电脑知识与技术,2011,07(16):3887-3889. [31] Al-Jarrah O Y,Al-Hammdi Y,Yoo P D,et al,Semi-supervised multi-layered clustering model for intrusion detection[J].Digital Communications and Networks,2018,4(4):277-286. [32] Konstantopoulos G,Koumoulos E P,Charitidis C A.Testing novel portland cement formulations with carbon nanotubes and intrinsic properties revelation:nanoindentation analysis with machine learning on microstructure identification[J].Nanomaterials,2020,10(4):645. [33] Kunselman C,Attari V,McClenny L,et al.Semi-supervised learning approaches to class assignment in ambiguous microstructures[J].Acta Materialia,2020,188:49-62. [34] 米晓希,汤爱涛,朱雨晨,等.机器学习技术在材料科学研究中的应用进展[J].材料导报,2021(15):1-18. [35] Hong Y,Hou B,Jiang H L,et al.Machine learning and artificial neural network accelerated computational discoveries in materials science[J].WIREs Computational Molecular Science,2019,10(3):e1450. [36] Rossi K,Cumby J.Representations and descriptors unifying the study of molecular and bulk systems[J].International Journal of Quantum Chemistry,2019,120(8):e26151. [37] Childs C M,Washburn N R.Embedding domain knowledge for machine learning of complex material systems[J].MRS Communications,2019,9(3):806-820.