Multi-objective optimization in machine learning assisted materials design and discovery

Abstract

Over the past decades, machine learning has kept playing an important role in materials design and discovery. In practical applications, materials usually need to fulfill the requirements of multiple target properties. Therefore, multi-objective optimization of materials based on machine learning has become one of the most promising directions. This review aims to provide a detailed discussion on machine learning-assisted multi-objective optimization in materials design and discovery combined with the recent research progress. First, we briefly introduce the workflow of materials machine learning. Then, the Pareto fronts in multi-objective optimization and the corresponding algorithms are summarized. Next, multi-objective optimization strategies are demonstrated, including Pareto front-based strategy, scalarization function, and constraint method. Subsequently, the research progress of multi-objective optimization in materials machine learning is summarized and different Pareto front-based strategies are discussed. Finally, we propose future directions for machine learning-based multi-objective optimization of materials.

Keywords

Machine learning / multi-objective optimization / materials design / Pareto front

References

[1] Qiu J,Ding G,Feng S.A survey of machine learning for big data processing.EURASIP J Adv Signal Process2016;2016:67

[2] Butler KT,Cartwright H,Walsh A.Machine learning for molecular and materials science.Nature2018;559:547-55

[3] Xu P,Li M.Small data machine learning in materials science.npj Comput Mater2023;9:1000

[4] Kumari J,Kumar D.A structured analysis to study the role of machine learning and deep learning in the healthcare sector with big data analytics.Arch Comput Methods Eng2023;30:3673-701 PMCID:PMC10064607

[5] An Q,Zhou J.A comprehensive review on machine learning in healthcare industry: classification, restrictions, opportunities and challenges.Sensors2023;23:4178 PMCID:PMC10180678

[6] Nazareth N.Financial applications of machine learning: a literature review.Expert Syst Appl2023;219:119640

[7] Ghoddusi H,Rafizadeh N.Machine learning in energy economics and finance: a review.Energy Econ2019;81:709-27

[8] Kim DH,Wang X.Smart machining process using machine learning: a review and perspective on machining industry.Int J Precis Eng Manuf Green Technol2018;5:555-68

[9] Mccoy J.Machine learning applications in minerals processing: a review.Min Eng2019;132:95-109

[10] Kadulkar S,Ganesan V.Machine learning-assisted design of material properties.Annu Rev Chem Biomol Eng2022;13:235-54

[11] Cai J,Xu K,Wei J.Machine learning-driven new material discovery.Nanoscale Adv2020;2:3115-30 PMCID:PMC9419423

[12] Si Z,Yang J.Review: 2D material property characterizations by machine-learning-assisted microscopies.Appl Phys A2023;129:6543

[13] Wei J,Sun X.Machine learning in materials science.InfoMat2019;1:338-58

[14] Liu Y,Wang Z.Machine learning in materials genome initiative: a review.J Mater Sci Technol2020;57:113-22

[15] Wang X,Li H.Discovery and design of lithium battery materials via high-throughput modeling.Chinese Phys B2018;27:128801

[16] Hu W.First-principles, machine learning and symbolic regression modelling for organic molecule adsorption on two-dimensional CaO surface.J Mol Graph Model2023;124:108530

[17] Mai J,Xu P,Li M.Predicting the maximum absorption wavelength of azo dyes using an interpretable machine learning strategy.Dyes Pigments2022;206:110647

[18] Tao Q,Li M.Machine learning for perovskite materials design and discovery.npj Comput Mater2021;7:495

[19] Wang J,Ji X,Lu W.Feature selection in machine learning for perovskite materials design and discovery.Materials2023;16:3134 PMCID:PMC10146176

[20] Bhat N,Birbilis N.Unsupervised machine learning discovers classes in aluminium alloys.R Soc Open Sci2023;10:220360 PMCID:PMC9890099

[21] Yang Z.Applications of machine learning in alloy catalysts: rational selection and future development of descriptors.Adv Sci2022;9:e2106043 PMCID:PMC9036033

[22] Sha W,Tang S.Machine learning in polymer informatics.InfoMat2021;3:353-61

[23] Xu P,Li M.New opportunity: machine learning for polymer materials design and discovery.Adv Theory Simul2022;5:2100565

[24] Startt J,Wood MA,Dingreville R.Bayesian blacksmithing: discovering thermomechanical properties and deformation mechanisms in high-entropy refractory alloys.npj Comput Mater2024;10:1353

[25] Zhang Q,Li S.Recent advances in supported acid/base ionic liquids as catalysts for biodiesel production.Front Chem2022;10:999607 PMCID:PMC9520055

[26] Zheng M,Teng H.A new “intersection” method for multi-objective optimization in material selection.Teh glas2021;15:562-8

[27] Al Ani, Z.; Gujarathi, A. M.; Al-Muhtaseb, A. H. A state of art review on applications of multi-objective evolutionary algorithms in chemicals production reactors.Artif Intell Rev2023;56:2435-96

[28] Takagi T,Sato H.Directional pareto front and its estimation to encourage multi-objective decision-making.IEEE Access2023;11:20619-34

[29] Lee J,Ahn J.Pareto front generation with knee-point based pruning for mixed discrete multi-objective optimization.Struct Multidisc Optim2018;58:823-30

[30] Shi L,Ji X.Using data mining to search for perovskite materials with higher specific surface area.J Chem Inf Model2018;58:2420-7

[31] Chen H,Lu W,Tan F.A property-driven stepwise design strategy for multiple low-melting alloys via machine learning.Adv Eng Mater2021;23:2100612

[32] Zhang S,Xu P,Li M.Predicting the formability of hybrid organic-inorganic perovskites via an interpretable machine learning strategy.J Phys Chem Lett2021;12:7423-30

[33] Bartel CJ,Goldsmith BR.New tolerance factor to predict the stability of perovskite oxides and halides.Sci Adv2019;5:eaav0693 PMCID:PMC6368436

[34] Wang T,Ouyang R.Nature of metal-support interaction for metal catalysts on oxide supports.Science2024;386:915-20

[35] Xu P,Li M.Virtual sample generation in machine learning assisted materials design and discovery.J Mater Inf2023;3:16

[36] Li Y,Liu H.Recent advances in feature selection and its applications.Knowl Inf Syst2017;53:551-77

[37] Xie J,Zhao YF.Feature selection and feature learning in machine learning applications for gas turbines: a review.Eng Appl Artif Intell2023;117:105591

[38] Borchers A.Programming pluripotent precursor cells derived from Xenopus embryos to generate specific tissues and organs.Genes2010;1:413-26 PMCID:PMC3966229

[39] Zheng W,Fu Z,Yan H.Feature selection boosted by unselected features.IEEE Trans Neural Netw Learn Syst2022;33:4562-74

[40] Yang C,Jia Y,Li M.A machine learning-based alloy design system to facilitate the rational design of high entropy alloys with enhanced hardness.Acta Mater2022;222:117431

[41] Wang J,Ji X,Lu W.MIC-SHAP: an ensemble feature selection method for materials machine learning.Mater Today Commun2023;37:106910

[42] Ordillo VZ,Putungan DB.Two-stage feature selection for machine learning-aided DFT-based surface reactivity study on single-atom alloys.Modelling Simul Mater Sci Eng2024;32:065003

[43] Lu K,Ji X,Lu W.Machine learning aided discovery of the layered double hydroxides with the largest basal spacing for super-capacitors.International J Electrochem Sci2021;16:211146

[44] Zhao Y,Xu Z.Discovery of temperature-induced stability reversal in perovskites using high-throughput robotic learning.Nat Commun2021;12:2191 PMCID:PMC8044090

[45] Wong TT.Reliable accuracy estimates from k-fold cross validation.IEEE Trans Knowl Data Eng2020;32:1586-94

[46] Zhang J.A fast leave-one-out cross-validation for SVM-like family.Neural Comput Appl2016;27:1717-30

[47] Meiyazhagan J,Venkatesan A.Prediction of occurrence of extreme events using machine learning.Eur Phys J Plus2022;137:2249

[48] Novello P,Lugato D.Goal-oriented sensitivity analysis of hyperparameters in deep learning.J Sci Comput2023;94:2083

[49] Li Z.Extracting spatial effects from machine learning model using local interpretation method: an example of SHAP and XGBoost.Comput Environ Urban Syst2022;96:101845

[50] Szepannaek G.How much do we see? On the explainability of partial dependence plots for credit risk scoring.Argum Oeconom2023;2023:137-50

[51] Feng W,Yu Z.Multi-objective evolutionary optimization based on online perceiving Pareto front characteristics.Inform Sci2021;581:912-31

[52] Khorram E,Khaledyan M.A numerical method for constructing the Pareto front of multi-objective optimization problems.J Comput Appl Math2014;261:158-71

[53] Bejarano LA,Montenegro CE.Clustering analysis for the Pareto optimal front in multi-objective optimization.Computation2022;10:37

[54] Gomes GF,da Silva Lopes Alexandrino P,de Sousa BS.A multiobjective sensor placement optimization for SHM systems considering Fisher information matrix and mode shape interpolation.Eng Comput2019;35:519-35

[55] Boţ RI,Wanka G.A general approach for studying duality in multiobjective optimization.Math Meth Oper Res2007;65:417-44

[56] Jiménez B,Vílchez A.A set scalarization function based on the oriented distance and relations with other set scalarizations.Optimization2018;67:2091-116

[57] Bazgan C,Thielen C.The power of the weighted sum scalarization for approximating multiobjective optimization problems.Theory Comput Syst2022;66:395-415

[58] Hanaoka K.Comparison of conceptually different multi-objective Bayesian optimization methods for material design problems.Mater Today Commun2022;31:103440

[59] Qu BY.Constrained multi-objective optimization algorithm with an ensemble of constraint handling methods.Eng Optim2011;43:403-16

[60] Kazemzadeh Azad, S.; Aminbakhsh, S. ε-constraint guided stochastic search with successive seeding for multi-objective optimization of large-scale steel double-layer grids.J Build Eng2022;46:103767

[61] Li X,Zhang J.Accelerated design for magnetic high entropy alloys using data-driven multi-objective optimization.J Mater Chem C2022;10:17291-302

[62] Ma Y,Mu Y,Lu W.Accelerated design for high-entropy alloys based on machine learning and multiobjective optimization.J Chem Inf Model2023;63:6029-42

[63] Chen Y,Zhou Y.Machine learning assisted multi-objective optimization for materials processing parameters: a case study in Mg alloy.J Alloys Compd2020;844:156159

[64] Deng Y,Gong X.An intelligent design for Ni-based superalloy based on machine learning and multi-objective optimization.Mater Design2022;221:110935

[65] Banerjee T,Sekhar AP,Das D.Design of alumina reinforced aluminium alloy composites with improved tribo-mechanical properties: a machine learning approach.Trans Indian Inst Met2020;73:3059-69

[66] Wu S,Yang S,Volinsky AA.Data-driven optimization of hardness and toughness of high-entropy nitride coatings.Ceram Int2023;49:21561-9

[67] Zhang Y,Guo W,Poh LH.Multi-objective optimization for high-performance Fe-based metallic glasses via machine learning approach.J Alloys Compd2023;960:170793

[68] Gao W,Gu Q.Accelerated discovery of high-performance 3D printing materials using multi-objective active optimization method.J Mater Sci2024;59:2390-402

[69] Morales-Hernández A,Van Nieuwenhuyse I.Bayesian multi-objective optimization of process design parameters in constrained settings with noise: an engineering design application.Eng Comput2024;40:2497-511

[70] Fang J,Zhang J.Optimized design of composition and brazing process for Cu-Ag-Zn-Mn-Ni-Si-B-P alloy brazing material based on machine learning strategy to improve brazing properties.Mater Today Commun2024;39:109317

[71] Tao Q,Lu T.Multiobjective stepwise design strategy-assisted design of high-performance perovskite oxide photocatalysts.J Phys Chem C2021;125:21141-50

[72] Cai X,Shi Z.Discovery of lead-free perovskites for high-performance solar cells via machine learning: ultrabroadband absorption, low radiative combination, and enhanced thermal conductivities.Adv Sci2022;9:e2103648 PMCID:PMC8811845

[73] Gao T,Yang S.Data-driven design of novel lightweight refractory high-entropy alloys with superb hardness and corrosion resistance.npj Comput Mater2024;10:1457

[74] Hu X,Lu J.Three-step learning strategy for designing 15Cr ferritic steels with enhanced strength and plasticity at elevated temperature.J Mater Sci Technol2023;164:79-94

[75] Wei Q,Sun S.Multi-objective machine learning of four mechanical properties of steels.Sci Sin Tech2021;51:722-36

[76] Zhou X,Lu T.Interpretable machine learning assisted multi-objective optimization design for small molecule hole transport materials.J Alloys Compd2023;966:171440

[77] Liu P,Wen C,Su Y.The γ/γ′ microstructure in CoNiAlCr-based superalloys using triple-objective optimization.npj Comput Mater2023;9:1090

[78] Wang X,Ji J,Yang J.A multi-objective, multi-interpretable machine learning demonstration verified by domain knowledge for ductile thermoelectric materials.J Materiomics2025;11:100886

[79] Li Z,O’brien S,Gupta R.cardiGAN: a generative adversarial network model for design and discovery of multi principal element alloys.J Mater Sci Technol2022;125:81-96

[80] Iyer RS,P RA.Harnessing machine learning and virtual sample generation for corrosion studies of 2-alkyl benzimidazole scaffold small dataset with an experimental validation.J Mol Struct2024;1306:137767