Hybrid Models for Basalt Building Stones Assessment: Combining Regression and LSTM Techniques

Rababah, Samer; Khasawneh, Mohammad; Mewada, Hiren; Aldeeky, Hussien

doi:10.22115/scce.2025.2017

Hybrid Models for Basalt Building Stones Assessment: Combining Regression and LSTM Techniques

Document Type : Regular Article

Authors

Samer Rababah ¹

Mohammad Khasawneh ²

Hiren Mewada ³

Hussien aldeeky ⁴

¹ Dept. of Civil Engineering, Jordan University of Science &Technology, P.O. Box 3030, Irbid 2210, Jordan

² Civil Engineering Department, Prince Mohammad Bin Fahd University, P.O. Box 1664, 31952 Al Khobar, Kingdom of Saudi Arabia

³ Electrical Engineering Department, Prince Mohammad Bin Fahd University, P.O. Box 1664, 31952 Al Khobar, Kingdom of Saudi Arabia

⁴ Department of Civil Engineering, Faculty of Engineering, The Hashemite University, P.O. Box 330127, Zarqa 13133, Jordan

10.22115/scce.2025.2017

Abstract

Because basalt rock is durable, abundant, hard and visually appealing, it has been widely used in the construction of many historical buildings in Jordan. Over time, these structures quite often require routine maintenance to preserve their structural integrity. Key parameters for assessing its mechanical behavior are uniaxial compressive strength (UCS) and the tangent modulus of elasticity (Et). However, direct laboratory tests to measure both UCS and Et require a specific core sample with certain dimensions, which is expensive, time-consuming, and prohibited in historic buildings. For this reason, developing novel models to predict both UCS and Et of basalt rock based on simple nondestructive tests is required. A laboratory of 134 datasets has been tested and used as input data, including Leeb rebound hardness (LRH), Schmidt hammer (Rn), Dry Density (DD), and ultrasonic pulse velocity (UPV). The study compares three approaches: simple regression models, multiple linear regression (MLR), and nonlinear regression (NLR), alongside advanced machine learning models, such as Long Short-Term Memory (LSTM) networks. A low Durbin-Watson (DW) value indicated significant positive autocorrelation in the residuals, suggesting temporal or sequential dependency in the data. This finding makes LSTM networks particularly well suited for modeling UCS and Et. Results show that although MLR and NLR are effective in prediction, LSTM models outperform them in accuracy, with R2 values of 0.9815 and 0.9644 for predicting UCS and Et, respectively, and lower RMSE values of 5.3135 and 0.7229 for predicting UCS and Et, respectively. The findings demonstrate the potential of combining traditional statistical methods with advanced machine learning approaches to estimate the mechanical properties of basalt rock accurately.

Graphical Abstract

Hybrid Models for Basalt Building Stones Assessment: Combining Regression and LSTM Techniques

Highlights

Developing cost-effective, nondestructive methods for evaluating rock mechanics, crucial for preserving historical basalt structures
Demonstrating the superior predictive capabilities of LSTM models with R² values of 0.98 and 0.96 for UCS and Et, respectively
Bridging traditional engineering techniques with cutting-edge machine learning methodologies to enhance analytical precision

Keywords

Uniaxial compressive strength

Tangent modulus of elasticity

Long short term memory (LSTM)

Leeb rebound hardness

Schmidt hammer

Dry density

Ultrasonic pulse velocity

Subjects

Artificial Neural Networks

[1] Umrao RK, Singh R, Singh TN. Stability evaluation of hill cut slopes along national highway-13 near Hospet, Karnataka, India. Georisk Assess Manag Risk Eng Syst Geohazards 2015;9:158–70. https://doi.org/10.1080/17499518.2015.1053494.

[2] ISRM (2007) The complete ISRM suggested methods for rock characterization, testing and monitoring. In: Ulusay R, Hudson JA (eds) Suggested methods prepared by the commission on testing methods. International Society for Rock Mechanics, ISRM Turkish Nation n.d.

[3] Heidari M, Khanlari GR, Torabi Kaveh M, Kargarian S. Predicting the Uniaxial Compressive and Tensile Strengths of Gypsum Rock by Point Load Testing. Rock Mech Rock Eng 2012;45:265–73. https://doi.org/10.1007/s00603-011-0196-8.

[4] Fakir M, Ferentinou M, Misra S. An Investigation into the Rock Properties Influencing the Strength in Some Granitoid Rocks of KwaZulu-Natal, South Africa. Geotech Geol Eng 2017;35:1119–40. https://doi.org/10.1007/s10706-017-0168-1.

[5] Umrao RK, Sharma LK, Singh R, Singh TN. Determination of strength and modulus of elasticity of heterogenous sedimentary rocks: An ANFIS predictive technique. Measurement 2018;126:194–201. https://doi.org/10.1016/J.MEASUREMENT.2018.05.064.

[6] Aldeeky H, Al Hattamleh O. Prediction of Engineering Properties of Basalt Rock in Jordan Using Ultrasonic Pulse Velocity Test. Geotech Geol Eng 2018;36:3511–25. https://doi.org/10.1007/s10706-018-0551-6.

[7] Yagiz S. Correlation between slake durability and rock properties for some carbonate rocks. Bull Eng Geol Environ 2011;70:377–83. https://doi.org/10.1007/S10064-010-0317-8/TABLES/4.

[8] Fereidooni D, Karimi Z, Ghasemi F. Non-destructive test-based assessment of uniaxial compressive strength and elasticity modulus of intact carbonate rocks using stacking ensemble models. PLoS One 2024;19:e0302944. https://doi.org/10.1371/JOURNAL.PONE.0302944.

[9] Shahani NM, Zheng X, Liu C, Li P, Hassan FU. Application of soft computing methods to estimate uniaxial compressive strength and elastic modulus of soft sedimentary rocks. Arab J Geosci 2022 155 2022;15:1–19. https://doi.org/10.1007/S12517-022-09671-6.

[10] Malkawi DA, Rabab’ah SR, Sharo AA, Aldeeky H, Al-Souliman GK, Saleh HO. Enhancing of uniaxial compressive strength of travertine rock prediction through machine learning and multivariate analysis. Results Eng 2023;20:101593. https://doi.org/10.1016/J.RINENG.2023.101593.

[11] Barham WS, Rabab’ah SR, Aldeeky HH, Al Hattamleh OH. Mechanical and Physical Based Artificial Neural Network Models for the Prediction of the Unconfined Compressive Strength of Rock. Geotech Geol Eng 2020;38:4779–92. https://doi.org/10.1007/s10706-020-01327-0.

[12] Ling X, Wang M, Yi W, Xia Q, Sun H. Predicting Rock Unconfined Compressive Strength Based on Tunnel Face Boreholes Measurement-While-Drilling Data. KSCE J Civ Eng 2024;28:5946–62. https://doi.org/10.1007/S12205-024-2742-4/METRICS.

[13] Asteris PG, Karoglou M, Skentou AD, Vasconcelos G, He M, Bakolas A, et al. Predicting uniaxial compressive strength of rocks using ANN models: Incorporating porosity, compressional wave velocity, and schmidt hammer data. Ultrasonics 2024;141:107347. https://doi.org/10.1016/J.ULTRAS.2024.107347.

[14] Ghasemi E, Kalhori H, Bagherpour R, Yagiz S. Model tree approach for predicting uniaxial compressive strength and Young’s modulus of carbonate rocks. Bull Eng Geol Environ 2018;77:331–43. https://doi.org/10.1007/S10064-016-0931-1/TABLES/7.

[15] Mahmoodzadeh A, Mohammadi M, Ghafoor Salim S, Farid Hama Ali H, Hashim Ibrahim H, Nariman Abdulhamid S, et al. Machine Learning Techniques to Predict Rock Strength Parameters. Rock Mech Rock Eng 2022;55:1721–41. https://doi.org/10.1007/s00603-021-02747-x.

[16] Sabri MS, Jaiswal A, Verma AK, Singh TN. Advanced machine learning approaches for uniaxial compressive strength prediction of Indian rocks using petrographic properties. Multiscale Multidiscip Model Exp Des 2024;7:5265–86. https://doi.org/10.1007/S41939-024-00513-4/FIGURES/18.

[17] Wen T, Li D, Wang Y, Hu M, Tang R. Machine learning methods for predicting the uniaxial compressive strength of the rocks: a comparative study. Front Earth Sci 2024;18:400–11. https://doi.org/10.1007/S11707-024-1101-6/METRICS.

[18] Çanakcı H, Baykasoğlu A, Güllü H. Prediction of compressive and tensile strength of Gaziantep basalts via neural networks and gene expression programming. Neural Comput Appl 2009;18:1031–41. https://doi.org/10.1007/s00521-008-0208-0.

[19] Yagiz S. Assessment of brittleness using rock strength and density with punch penetration test. Tunn Undergr Sp Technol 2009;24:66–74. https://doi.org/10.1016/J.TUST.2008.04.002.

[20] DEHGHAN S, SATTARI G, CHEHREH CHELGANI S, ALIABADI M. Prediction of uniaxial compressive strength and modulus of elasticity for Travertine samples using regression and artificial neural networks. Min Sci Technol 2010;20:41–6. https://doi.org/10.1016/S1674-5264(09)60158-7.

[21] Yagiz S, Karahan H. Prediction of hard rock TBM penetration rate using particle swarm optimization. Int J Rock Mech Min Sci 2011;48:427–33. https://doi.org/10.1016/J.IJRMMS.2011.02.013.

[22] Yagiz S, Sezer EA, Gokceoglu C. Artificial neural networks and nonlinear regression techniques to assess the influence of slake durability cycles on the prediction of uniaxial compressive strength and modulus of elasticity for carbonate rocks. Int J Numer Anal Methods Geomech 2012;36:1636–50. https://doi.org/10.1002/nag.1066.

[23] Beiki M, Majdi A, Dadi Givshad A. Application of genetic programming to predict the uniaxial compressive strength and elastic modulus of carbonate rocks. Int J Rock Mech Min Sci 2013;63:159–69. https://doi.org/10.1016/j.ijrmms.2013.08.004.

[24] Yesiloglu-Gultekin N, Gokceoglu C, Sezer EA. Prediction of uniaxial compressive strength of granitic rocks by various nonlinear tools and comparison of their performances. Int J Rock Mech Min Sci 2013;62:113–22. https://doi.org/10.1016/j.ijrmms.2013.05.005.

[25] Armaghani DJ, Tonnizam Mohamad E, Momeni E, Monjezi M, Sundaram Narayanasamy M. Prediction of the strength and elasticity modulus of granite through an expert artificial neural network. Arab J Geosci 2016;9:48. https://doi.org/10.1007/s12517-015-2057-3.

[26] Singh PK, Tripathy A, Kainthola A, Mahanta B, Singh V, Singh TN. Indirect estimation of compressive and shear strength from simple index tests. Eng Comput 2017;33:1–11. https://doi.org/10.1007/s00366-016-0451-4.

[27] Esmaeili-Falak M, Katebi H, Vadiati M, Adamowski J. Predicting Triaxial Compressive Strength and Young’s Modulus of Frozen Sand Using Artificial Intelligence Methods. J Cold Reg Eng 2019;33:04019007. https://doi.org/10.1061/(ASCE)CR.1943-5495.0000188.

[28] Mahdiabadi N, Khanlari G. Prediction of Uniaxial Compressive Strength and Modulus of Elasticity in Calcareous Mudstones Using Neural Networks, Fuzzy Systems, and Regression Analysis. Period Polytech Civ Eng 2019;63:104–14. https://doi.org/10.3311/PPCI.13035.

[29] Teymen A, Mengüç EC. Comparative evaluation of different statistical tools for the prediction of uniaxial compressive strength of rocks. Int J Min Sci Technol 2020;30:785–97. https://doi.org/10.1016/J.IJMST.2020.06.008.

[30] Fang Q, Yazdani Bejarbaneh B, Vatandoust M, Jahed Armaghani D, Ramesh Murlidhar B, Tonnizam Mohamad E. Strength evaluation of granite block samples with different predictive models. Eng Comput 2021;37:891–908. https://doi.org/10.1007/S00366-019-00872-4/FIGURES/14.

[31] Gül E, Ozdemir E, Eren Sarıcı D. Modeling uniaxial compressive strength of some rocks from turkey using soft computing techniques. Measurement 2021;171:108781. https://doi.org/10.1016/j.measurement.2020.108781.

[32] Mahmoodzadeh A, Mohammadi M, Hashim Ibrahim H, Nariman Abdulhamid S, Ghafoor Salim S, Farid Hama Ali H, et al. Artificial intelligence forecasting models of uniaxial compressive strength. Transp Geotech 2021;27:100499. https://doi.org/10.1016/J.TRGEO.2020.100499.

[33] Jin X, Zhao R, Ma Y. Application of a Hybrid Machine Learning Model for the Prediction of Compressive Strength and Elastic Modulus of Rocks. Miner 2022, Vol 12, Page 1506 2022;12:1506. https://doi.org/10.3390/MIN12121506.

[34] Abdi Y, Momeni E, Armaghani DJ. Elastic modulus estimation of weak rock samples using random forest technique. Bull Eng Geol Environ 2023;82:1–20. https://doi.org/10.1007/S10064-023-03154-Y/FIGURES/16.

[35] Benemaran RS, Esmaeili-Falak M. Predicting the Young’s modulus of frozen sand using machine learning approaches: State-of-the-art review. Geomech Eng 2023;34:507. https://doi.org/10.12989/GAE.2023.34.5.507.

[36] Taheri-Garavand A, Abdi Y, Momeni E. Smart Estimation of Sandstones Mechanical Properties Based on Thin Section Image Processing Techniques. J Nondestruct Eval 2024;43:1–15. https://doi.org/10.1007/S10921-024-01056-X/TABLES/5.

[37] Chen K, Zhou Y, Dai F. A LSTM-based method for stock returns prediction: A case study of China stock market. Proc - 2015 IEEE Int Conf Big Data, IEEE Big Data 2015 2015:2823–4. https://doi.org/10.1109/BIGDATA.2015.7364089.

[38] Wang J, Li J, Wang X, Wang J, Huang M. Air quality prediction using CT-LSTM. Neural Comput Appl 2021;33:4779–92. https://doi.org/10.1007/S00521-020-05535-W/FIGURES/8.

[39] ISRM. The ISRM Suggested Methods for Rock Characterization, Testing and Monitoring: 2007-2014. Cham, Switzerland: Springer International Publishing; 2015. https://doi.org/10.1007/978-3-319-07713-0.

[40] ASTM D2845. Standard test method for laboratory determination of pulse velocities and ultrasonic elastic constants of rock. ASTM Int 2008:West Conshohocken, PA, USA.

[41] Daniels G, McPhee C, McCurdy P, Sorrentino Y. Non-destructive strength index testing applications for sand failure evaluation. SPE Asia Pacific Oil Gas Conf. Exhib., SPE; 2012, p. SPE-158326.

[42] Corkum AG, Asiri Y, El Naggar H, Kinakin D. The Leeb Hardness Test for Rock: An Updated Methodology and UCS Correlation. Rock Mech Rock Eng 2018;51:665–75. https://doi.org/10.1007/s00603-017-1372-2.

[43] ASTM D5873. Standard Test Methods for Determination of Rock Hardness by Rebound Hammer Method. ASTM Int., West Conshohocken, PA, USA: American Society for Testing and Materials West Conshohocken, PA, USA; 2014.

[44] ASTM D7012. Standard test method for compressive strength and elastic moduli of intact rock core specimens under varying states of stress and temperatures. ASTM Int 2017;10:West Conshohocken, PA, USA.

[45] Bejarbaneh BY, Bejarbaneh EY, Amin MFM, Fahimifar A, Jahed Armaghani D, Majid MZA. Intelligent modelling of sandstone deformation behaviour using fuzzy logic and neural network systems. Bull Eng Geol Environ 2018;77:345–61. https://doi.org/10.1007/S10064-016-0983-2/TABLES/11.

[46] Aldeeky H, Al Hattamleh O, Rababah S. Assessing the uniaxial compressive strength and tangent Young’s modulus of basalt rock using the Leeb rebound hardness test. Mater Construcción 2020;70:230. https://doi.org/10.3989/mc.2020.15119.

[47] Aladejare AE, Alofe ED, Onifade M, Lawal AI, Ozoji TM, Zhang Z-X. Empirical Estimation of Uniaxial Compressive Strength of Rock: Database of Simple, Multiple, and Artificial Intelligence-Based Regressions. Geotech Geol Eng 2021;39:4427–55. https://doi.org/10.1007/s10706-021-01772-5.

[48] EN ISO 14689. Geotechnical investigation and testing. Identification, description and classification of rock 2018. https://doi.org/10.3403/BSENISO14689.

[49] Deere D V, Miller RP. Engineering classification and index properties for intact rock 1966.

[50] Kochukrishnan S, Krishnamurthy P, D Y, Kaliappan N. Comprehensive study on the Python-based regression machine learning models for prediction of uniaxial compressive strength using multiple parameters in Charnockite rocks. Sci Reports 2024 141 2024;14:1–12. https://doi.org/10.1038/s41598-024-58001-1.

[51] Tang Z, Li S, Huang S, Huang F, Wan F. Indirect Estimation of Rock Uniaxial Compressive Strength from Simple Index Tests: Review and Improved Least Squares Regression Tree Predictive Model. Geotech Geol Eng 2021;39:3843–62. https://doi.org/10.1007/S10706-021-01731-0/FIGURES/2.

[52] Li C, Zhou J, Dias D, Du K, Khandelwal M. Comparative Evaluation of Empirical Approaches and Artificial Intelligence Techniques for Predicting Uniaxial Compressive Strength of Rock. Geosci 2023, Vol 13, Page 294 2023;13:294. https://doi.org/10.3390/GEOSCIENCES13100294.

[53] Esmaeili-Falak M, Benemaran RS. Ensemble Extreme Gradient Boosting based models to predict the bearing capacity of micropile group. Appl Ocean Res 2024;151:104149. https://doi.org/10.1016/J.APOR.2024.104149.

[54] Zhu Y, Huang L, Zhang Z, Bayrami B. Estimation of splitting tensile strength of modified recycled aggregate concrete using hybrid algorithms. Steel Compos Struct 2022;44:389. https://doi.org/10.12989/SCS.2022.44.3.389.

[55] Kou H, Quan J, Guo S, Hassankhani E. Light and normal weight concretes shear strength estimation using tree-based tunned frameworks. Constr Build Mater 2024;452:138955. https://doi.org/10.1016/J.CONBUILDMAT.2024.138955.

[56] Yaychi BM, Esmaeili-Falak M. Estimating Axial Bearing Capacity of Driven Piles Using Tuned Random Forest Frameworks. Geotech Geol Eng 2024;42:7813–34. https://doi.org/10.1007/S10706-024-02952-9/FIGURES/8.

[57] Esmaeili-Falak M, Sarkhani Benemaran R. Application of optimization-based regression analysis for evaluation of frost durability of recycled aggregate concrete. Struct Concr 2024;25:716–37. https://doi.org/10.1002/SUCO.202300566;WGROUP:STRING:PUBLICATION.