Predicting the compressive strength of clay solid masonry using optimized machine learning algorithms and partial dependence plot analysis

Abstract

Due to its low cost and its thermal and acoustic insulation properties, clay masonry is widely used in construction. Its compressive strength is the main mechanical property and is critical for structural design. This study aims to predict it using machine learning (ML) techniques. An experimental database was compiled from uniaxial compression tests on solid clay masonry specimens. First, the performance of 18 empirical models from the literature was evaluated. Then, several ML algorithms were developed, including least absolute shrinkage and selection operator regression, decision tree regression, support vector regression, bagging tree, gradient boosting, random forest regression, artificial neural networks, and Gaussian process regression (GPR). The models were trained on 80% of the data and tested on the remaining 20%, with hyperparameter optimisation and 10-fold cross-validation. The findings highlight the lower performance of traditional empirical models compared to ML methods. They also show the superior predictive ability of GPR over other ML algorithms for estimating the compressive strength of clay solid masonry. Sensitivity analysis confirms that masonry unit strength is the most influential factor, with notable nonlinear interactions involving mortar strength and geometric ratios, while joint thickness primarily acts as a regime modulator.

Graphical abstract

Keywords

ML / clay solid masonry / compressive strength / partial dependence plot analysis / bayesian optimisation

References

[1] Lourenço P J B B. Computational strategies for masonry structures. Dissertation for the Doctoral Degree. Delft: Delft University of Technology, 1997, 1369–1369

[2] Huang H , Burton H V , Sattar S . Development and utilization of a database of infilled frame experiments for numerical modeling. Journal of Structural Engineering, 2020, 146(6): 04020079

[3] De Risi M T , Di Domenico M , Ricci P , Verderame G M , Manfredi G . Experimental investigation on the influence of the aspect ratio on the in-plane/out-of-plane interaction for masonry infills in RC frames. Engineering Structures, 2019, 189: 523–540

[4] Roberts J J . The effect of different test procedures upon the indicated strength of concrete blocks in compression. Magazine of Concrete Research, 1973, 25(83): 87–98

[5] Kaushik H B , Rai D C , Jain S K . Stress–strain characteristics of clay brick masonry under uniaxial compression. Journal of Materials in Civil Engineering, 2007, 19(9): 728–739

[6] Thamboo J A , Dhanasekar M . Correlation between the performance of solid masonry prisms and wallettes under compression. Journal of Building Engineering, 2019, 22: 429–438

[7] Khalaf F M . Factors influencing compressive strength of concrete masonry prisms. Magazine of Concrete Research, 1996, 48(175): 95–101

[8] Bennett R M , Boyd K A , Flanagan R D . Compressive properties of structural clay tile prisms. Journal of Structural Engineering, 1997, 123(7): 920–926

[9] Gumaste K S , Nanjunda Rao K S , Venkatarama Reddy B V , Jagadish K S . Strength and elasticity of brick masonry prisms and wallettes under compression. Materials and Structures, 2007, 40(2): 241–253

[10] Freeda Christy C , Tensing D , Mercy Shanthi R . Experimental study on axial compressive strength and elastic modulus of the clay and fly ash brick masonry. Journal of Civil Engineering and Construction Technology, 2013, 4(4): 134–141

[11] Sarhat S R , Sherwood E G . The prediction of compressive strength of ungrouted hollow concrete block masonry. Construction and Building Materials, 2014, 58: 111–121

[12] Sarangapani G , Venkatarama Reddy B V , Jagadish K S . Brick-mortar bond and masonry compressive strength. Journal of Materials in Civil Engineering, 2005, 17(2): 229–237

[13] Murthi P , Bhavani M , Musthaq M S , Jauhar M O , Rama Devi V . Development of relationship between compressive strength of brick masonry and brick strength. Materials Today: Proceedings, 2021, 39: 258–262

[14] Monteagudo S M , Casat M J , Gálvez J C . Influence of the bed joint thickness on the bearing capacity of the brick masonry under compression loading: an ultrasound assessment. Revista de la Construcción. Journal of Construction, 2015, 14(1): 9–15

[15] Uday Vyas C V , Venkatarama Reddy B V . Prediction of solid block masonry prism compressive strength using FE model. Materials and Structures, 2010, 43(5): 719–735

[16] Thamboo J A , Dhanasekar M , Yan C . Effects of joint thickness, adhesion and web shells to the face shell bedded concrete masonry loaded in compression. Australian Journal of Structural Engineering, 2013, 14(3): 291–302

[17] Caldeira F E , Nalon G H , Oliveira D S , Pedroti L G , Ribeiro J C L , Ferreira F A , Carvalho J M F . Influence of joint thickness and strength of mortars on the compressive behavior of prisms made of normal and high-strength concrete blocks. Construction and Building Materials, 2020, 234: 117419

[18] Asteris P G , Mokos V G . Concrete compressive strength using artificial neural networks. Neural Computing and Applications, 2020, 32(15): 11807–11826

[19] Asteris P G , Skentou A D , Bardhan A , Samui P , Pilakoutas K . Predicting concrete compressive strength using hybrid ensembling of surrogate machine learning models. Cement and Concrete Research, 2021, 145: 106449

[20] Chopra P , Sharma R K , Kumar M , Chopra T . Comparison of machine learning techniques for the prediction of compressive strength of concrete. Advances in Civil Engineering, 2018, 2018(1): 5481705

[21] Armaghani D J , Asteris P G . A comparative study of ANN and ANFIS models for the prediction of cement-based mortar materials compressive strength. Neural Computing and Applications, 2021, 33(9): 4501–4532

[22] Eskandari-Naddaf H , Kazemi R . ANN prediction of cement mortar compressive strength, influence of cement strength class. Construction and Building Materials, 2017, 138: 1–11

[23] Asteris P G , Tsaris A K , Cavaleri L , Repapis C C , Papalou A , Di Trapani F , Karypidis D F . Prediction of the fundamental period of infilled RC frame structures using artificial neural networks. Computational Intelligence and Neuroscience, 2016, 2016(1): 5104907

[24] Đorđević F , Marinković M . Advanced ANN regularization-based algorithm for prediction of the fundamental period of masonry infilled RC frames. Journal of Big Data, 2024, 11(1): 169

[25] Garzón-Roca J , Marco C O , Adam J M . Compressive strength of masonry made of clay bricks and cement mortar: estimation based on neural networks and fuzzy logic. Engineering Structures, 2013, 48: 21–27

[26] Zhou Q , Wang F , Zhu F . Estimation of compressive strength of hollow concrete masonry prisms using artificial neural networks and adaptive neuro-fuzzy inference systems. Construction and Building Materials, 2016, 125: 417–426

[27] Asteris P GArgyropoulos ICavaleri LRodrigues HVarum HThomas JLourenço P B. Masonry compressive strength prediction using artificial neural networks. In: Transdisciplinary Multispectral Modeling and Cooperation for the Preservation of Cultural Heritage: First International Conference, TMM_CH 2018, Athens, Greece, October 10–13, 2018, Revised Selected Papers, Part II—1. Cham: Springer International Publishing, 2019, 200–224

[28] Lan G , Wang Y , Zeng G , Zhang J . Compressive strength of earth block masonry: estimation based on neural networks and adaptive network-based fuzzy inference system. Composite Structures, 2020, 235: 111731

[29] Asteris P G , Lourenço P B , Hajihassani M , Adami C E N , Lemonis M E , Skentou A D , Marques R , Nguyen H , Rodrigues H , Varum H . Soft computing-based models for the prediction of masonry compressive strength. Engineering Structures, 2021, 248: 113276

[30] Sathiparan N , Jeyananthan P . Prediction of masonry prism strength using machine learning technique: Effect of dimension and strength parameters. Materials Today. Communications, 2023, 35: 106282

[31] Fakharian P , Rezazadeh Eidgahee D , Akbari M , Jahangir H , Ali Taeb A . Compressive strength prediction of hollow concrete masonry blocks using artificial intelligence algorithms. Structures, 2023, 47: 1790–1802

[32] Sathiparan N . Predicting compressive strength of grouted masonry using machine learning models with feature importance analysis. Materials Today. Communications, 2024, 41: 110487

[33] Ho L S , Tran V Q . Evaluation and estimation of compressive strength of concrete masonry prism using gradient boosting algorithm. PLoS One, 2024, 19(3): e0297364

[34] Bin Inqiad W , Dumitrascu E V , Dobre R A , Khan N M , Hammood A H , Henedy S N , Khan R M A . Predicting compressive strength of hollow concrete prisms using machine learning techniques and explainable artificial intelligence (XAI). Heliyon, 2024, 10(17): e36841

[35] Gholami M , Ranjbargol M , Yousefzadeh R , Ghorbani Z . Integrating three smart predictive models using a power-law committee machine for the prediction of compressive strength in masonry made of clay bricks and cement mortar. Structures, 2023, 55: 951–964

[36] Baraldi D , Reccia E , Bello C B D C , Cecchi A . Laboratory and numerical experimentation for masonry in compression. International Journal of Masonry Research and Innovation, 2021, 6(1): 1–20

[37] Bompa D V , Elghazouli A Y . Compressive behaviour of fired-clay brick and lime mortar masonry components in dry and wet conditions. Materials and Structures, 2020, 53(3): 60

[38] Budiwati I A M. Experimental compressive strength and modulus of elasticity of masonry. Jurnal Ilmiah Teknik Sipil, 2009, 13(1)

[39] Bustos-García A , Moreno-Fernández E , Zavalis R , Valivonis J . Diagonal compression tests on masonry wallets coated with mortars reinforced with glass fibers. Materials and Structures, 2019, 52(3): 1–13

[40] Dehghan S M , Najafgholipour M A , Baneshi V , Rowshanzamir M . Mechanical and bond properties of solid clay brick masonry with different sand grading. Construction and Building Materials, 2018, 174: 1–10

[41] Ewing B D , Kowalsky M J . Compressive behavior of unconfined and confined clay brick masonry. Journal of Structural Engineering, 2004, 130(4): 650–661

[42] Foytong P , Boonpichetvong M , Areemit N , Teerawong J . Effect of brick types on compressive strength of masonry prisms. International Journal of Technology, 2016, 7(7): 1171–1178

[43] Jafari SEsposito R. Material tests for the characterisation of replicated solid clay brick masonry. Delft University of Technology, Report C31B67WP1–12, 2017

[44] Joshi D A , Jain R K . Evaluation of compressive strength and basic compressive stress of clay brick unreinforced masonry by prism test. International Journal of Scientific Research, 2013, 5(4): 913–916

[45] Khan N A , Aloisio A , Monti G , Nuti C , Briseghella B . Experimental characterization and empirical strength prediction of Pakistani brick masonry walls. Journal of Building Engineering, 2023, 71: 106451

[46] Liang B , Zhang H , Liu Z , Hou J . The influence of different types of mortar on the compressive strength of masonry. Journal of Building Engineering, 2023, 65: 105635

[47] Lumantarna R , Biggs D T , Ingham J M . Uniaxial compressive strength and stiffness of field-extracted and laboratory-constructed masonry prisms. Journal of Materials in Civil Engineering, 2014, 26(4): 567–575

[48] Mahmood H , Ingham J M . Diagonal compression testing of FRP-retrofitted unreinforced clay brick masonry wallettes. Journal of Composites for Construction, 2011, 15(5): 810–820

[49] McNary W S , Abrams D P . Mechanics of masonry in compression. Journal of Structural Engineering, 1985, 111(4): 857–870

[50] Mishra M , Bhatia A S , Maity D . A comparative study of regression, neural network and neuro-fuzzy inference system for determining the compressive strength of brick–mortar masonry by fusing nondestructive testing data. Engineering with Computers, 2021, 37(1): 77–91

[51] Moayedian S M , Hejazi M . Effect of scale on compressive strength of brick masonry with gypsum mortar. Measurement, 2021, 172: 108932

[52] Nowak R , Kania T , Derkach V , Orłowicz R , Halaliuk A , Ekiert E , Jaworski R . Strength parameters of clay brick walls with various directions of force. Materials, 2021, 14(21): 6461

[53] Nazimi KCastro J JOmi SStanikzai M A. Investigating the compressive strength of clay brick masonry: A case study of Nangarhar, Afghanistan. Buildings, 2024, 14(12)

[54] Padalu P K V R , Singh Y . Variation in compressive properties of Indian brick masonry and its assessment using empirical models. Structures, 2021, 33: 1734–1753

[55] Soundar Rajan M , Jegatheeswaran D . Influence of strength behavior in brick masonry prism and wallette under compression. Materials (Rio de Janeiro), 2023, 28(1): e20220260

[56] San Bartholome A. Tests for evaluation of slenderness correction factor for masonry prisms. In: 10th North American Masonry Conference. St. Louis, MO: The Masonry Society, 2007

[57] Sassoni E , Mazzotti C , Pagliai G . Comparison between experimental methods for evaluating the compressive strength of existing masonry buildings. Construction and Building Materials, 2014, 68: 206–219

[58] Sathiparan N , Rumeshkumar U . Effect of moisture condition on mechanical behavior of low strength brick masonry. Journal of Building Engineering, 2018, 17: 23–31

[59] Saviano F , Lignola G P , Parisi F . Experimental compressive and shear behaviour of clay brick masonry with degraded joints. Construction and Building Materials, 2024, 452: 138880

[60] Segura J , Pelà L , Roca P . Monotonic and cyclic testing of clay brick and lime mortar masonry in compression. Construction and Building Materials, 2018, 193: 453–466

[61] Singhal V , Rai D C . Suitability of half-scale burnt clay bricks for shake table tests on masonry walls. Journal of Materials in Civil Engineering, 2014, 26(4): 644–657

[62] Singh S B , Munjal P . Bond strength and compressive stress–strain characteristics of brick masonry. Journal of Building Engineering, 2017, 9: 10–16

[63] Soleymani A , Najafgholipour M A , Johari A . An experimental study on the mechanical properties of solid clay brick masonry with traditional mortars. Journal of Building Engineering, 2022, 58: 105057

[64] Susila I G A. Experimental and numerical studies of masonry wall panels and timber frames of low-rise structures under seismic loadings in Indonesia. Dissertation for the Doctoral Degree. Manchester: The University of Manchester, 2014

[65] Thaickavil N N , Thomas J . Behaviour and strength assessment of masonry prisms. Case Studies in Construction Materials, 2018, 8: 23–38

[66] Thamboo J A . Material characterisation of thin layer mortared clay masonry. Construction and Building Materials, 2020, 230: 116932

[67] Wang X , Lam C C , Iu V P . Characterization of mechanical behaviour of grey clay brick masonry in China. Construction and Building Materials, 2020, 262: 119964

[68] Tibshirani R . Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society. Series B, Statistical Methodology, 1996, 58(1): 267–288

[69] Kump P , Bai E W , Chan K S , Eichinger B , Li K . Variable selection via RIVAL (removing irrelevant variables amidst Lasso iterations) and its application to nuclear material detection. Automatica, 2012, 48(9): 2107–2115

[70] Azencott C A. Introduction au Machine Learning, 2nd ed. Paris: Dunod, 2022

[71] Breiman LFriedman J HOlshen R AStone C J. Classification and Regression Trees. New York: Chapman and Hall/CRC, 1984

[72] Vapnik V , Lerner A . Pattern recognition using generalized portrait method. Automation and Remote Control, 1963, 24: 774–780

[73] Awad MKhanna R. Efficient learning machines: Theories, concepts, and applications for engineers and system designers. London: Springer Nature, 2015, 268

[74] Breiman L . Bagging predictors. Machine Learning, 1996, 24(2): 123–140

[75] Breiman L . Random forests. Machine Learning, 2001, 45(1): 5–32

[76] Epelbaum T. Deep learning: Technical introduction. 2017, arXiv:1709.01412

[77] Williams C KRasmussen C E. Gaussian Processes for Machine Learning. Cambridge, MA: MIT Press, 2006, 4

[78] Ly H B , Nguyen T A , Pham B T . Investigation on factors affecting early strength of high-performance concrete by Gaussian Process Regression. PLoS One, 2022, 17(1): e0262930

[79] Shahriari B , Swersky K , Wang Z , Adams R P , De Freitas N . Taking the human out of the loop: A review of Bayesian optimization. Proceedings of the IEEE, 2016, 104(1): 148–175

[80] Bousquet Ovon Luxburg URätsch G. Advanced lectures on machine learning: ML Summer Schools 2003, Canberra, Australia, February 2–14, 2003, Tübingen, Germany, August 4–16, 2003, revised lectures. Lecture Notes in Computer Science, 2004, 3176: 1–504

[81] Basha S H , Kaushik H B . Evaluation of nonlinear material properties of fly ash brick masonry under compression and shear. Journal of Materials in Civil Engineering, 2015, 27(8): 04014227

[82] Bröcker O . Evaluation of load-bearing capacity tests on masonry walls. Concrete Block Journal, 1963, 19–21

[83] Calderón S , Sandoval C , Araya-Letelier G , Aguilar V . A detailed experimental mechanical characterization of multi-perforated clay brick masonry. Journal of Building Engineering, 2023, 63: 105505

[84] Dayaratnam P. Brick and Reinforced Brick Structures. New Delhi: South Asia Books, 1987

[85] Dymiotis C , Gutlederer B M . Allowing for uncertainties in the modelling of masonry compressive strength. Construction and Building Materials, 2002, 16(8): 443–452

[86] Engesser F . On long-span arch bridges. Journal of Architecture and Engineering, 1907, 53: 403–440

[87] British Standards Institution. Eurocode 6: design of masonry structures: Part 1–1: General rules for reinforced and unreinforced masonry structures. British Standards Institution, 2013

[88] Hendry A W , Malek M H . Characteristic compressive strength of brickwork walls from collected test results. Masonry International, 1986, 7: 15

[89] Kumavat H R . An experimental investigation of mechanical properties in clay brick masonry by partial replacement of fine aggregate with clay brick waste. Journal of The Institution of Engineers: Series A, 2016, 97: 199–204

[90] Mann W. Statistical evaluation of tests on masonry by potential functions. In: Sixth International Brick Masonry Conference. Rome: Andil, 1982

[91] Nazimi K , Castro J J , Omi S , Ali B S . Proposal of empirical equations for masonry compressive strength: Considering the compressive strength difference between bricks and mortar. Buildings, 2024, 14(4): 1138

[92] Taylor K E . Summarizing multiple aspects of model performance in a single diagram. Journal of Geophysical Research, 2001, 106(D7): 7183–7192

[93] Kashem A , Karim R , Malo S C , Das P , Datta S D , Alharthai M . Hybrid data-driven approaches to predicting the compressive strength of ultra-high-performance concrete using SHAP and PDP analyses. Case Studies in Construction Materials, 2024, 20: e02991

[94] Roy T , Das P , Jagirdar R , Shhabat M , Abdullah M S , Kashem A , Rahman R . Prediction of mechanical properties of eco-friendly concrete using machine learning algorithms and partial dependence plot analysis. Smart Construction and Sustainable Cities, 2025, 3(1): 2

[95] Maze G. Taylor diagram. MATLAB Central File Exchange, 2025

[96] Friedman J H . Greedy function approximation: A gradient boosting machine. Annals of Statistics, 2001, 29(5): 1189–1232

[97] Goldstein A , Kapelner A , Bleich J , Pitkin E . Peeking inside the black box: visualizing statistical learning with plots of individual conditional expectation. Journal of Computational and Graphical Statistics, 2015, 24(1): 44–65

[98] Bile H M , Güler K . Data-driven modeling of lateral and cracking loads in confined masonry walls using machine learning. Buildings, 2024, 14(12): 4016

[99] Peng Y , Unluer C . Modeling the mechanical properties of recycled aggregate concrete using hybrid machine learning algorithms. Resources, Conservation and Recycling, 2023, 190: 106812

[100] Molnar C. Interpretable Machine Learning. Raleigh, NC: Lulu Press, 2020

[101] Saltelli A . Making best use of model evaluations to compute sensitivity indices. Computer Physics Communications, 2002, 145(2): 280–297

[102] Jansen M J . Analysis of variance designs for model output. Computer Physics Communications, 1999, 117(1–2): 35–43

[103] Samaniego E , Anitescu C , Goswami S , Nguyen-Thanh V M , Guo H , Hamdia K , Zhuang X , Rabczuk T . An energy approach to the solution of partial differential equations in computational mechanics via machine learning: Concepts, implementation and applications. Computer Methods in Applied Mechanics and Engineering, 2020, 362: 112790

[104] Mojahedin A , Salavati M , Rabczuk T . A deep energy method for functionally graded porous beams. Journal of Zhejiang University. Science A, 2021, 22(6): 492–498

[105] Eshaghi M S , Anitescu C , Thombre M , Wang Y , Zhuang X , Rabczuk T . Variational physics-informed neural operator (VINO) for solving partial differential equations. Computer Methods in Applied Mechanics and Engineering, 2025, 437: 117785

RIGHTS & PERMISSIONS

Higher Education Press