Prediction of Coefficient of Restitution of Limestone in Rockfall Dynamics Using Adaptive Neuro-Fuzzy Inference System and Multivariate Adaptive Regression Splines

Document Type : Regular Paper

Authors

1 Assistant Professor, Faculty of Civil Engineering and Architecture, Shahid Chamran University of Ahvaz, Ahvaz, Iran

2 Assistant Professor, Department of Civil Engineering, Dariun Branch, Islamic Azad University, Dariun, Iran

Abstract

Rockfalls are a type of landslide that poses significant risks to roads and infrastructure in mountainous regions worldwide. The main objective of this study is to predict the coefficient of restitution (COR) for limestone in rockfall dynamics using an adaptive neuro-fuzzy inference system (ANFIS) and Multivariate Adaptive Regression Splines (MARS). A total of 931 field tests were conducted to measure kinematic, tangential, and normal CORs on three surfaces: asphalt, concrete, and rock. The ANFIS model was trained using five input variables: impact angle, incident velocity, block mass, Schmidt hammer rebound value, and angular velocity. The model demonstrated strong predictive capability, achieving root mean square errors (RMSEs) of 0.134, 0.193, and 0.217 for kinematic, tangential, and normal CORs, respectively. These results highlight the potential of ANFIS to handle the complexities and uncertainties inherent in rockfall dynamics. The analysis was also extended by fitting a MARS model (degree 2, 8 basis functions) to the same dataset. The MARS model achieved MAE ≈ 0.095 and RMSE ≈ 0.118—marginally improving over ANFIS—while delivering a fully explicit algebraic form and an intrinsic ranking of variable importance.

Highlights

  • A novel application of ANFIS was employed to predict the coefficients of restitution for rockfall events, using parameters such as impact angle, incident velocity, block mass, surface hardness, and angular velocity.
  • A comprehensive dataset of 931 field tests was collected, with 571 tests deemed suitable for determining coefficients of restitution on various surfaces (asphalt, concrete, rock) under different seasonal conditions.
  • The study identified a decreasing trend of kinematic and normal coefficients of restitution with increasing impact angle and incident velocity, providing insights into rockfall dynamics and behavior.
  • The ANFIS model demonstrated robust predictive capabilities, effectively handling the inherent uncertainties in field data and offering a reliable method for predicting rockfall behavior and mitigating hazards.

Keywords

Main Subjects


[1]      Matsukura Y. Rockfall at Toyohama Tunnel, Japan, in 1996: effect of notch growth on instability of a coastal cliff. Bull Eng Geol Environ 2001;60:285–9.
[2]      Sarro R, Mateos RM, García-Moreno I, Herrera G, Reichenbach P, Laín L, et al. The Son Poc rockfall (Mallorca, Spain) on the 6th of March 2013: 3D simulation. Landslides 2014;11:493–503.
[3]      Geniş M, Sakız U, Çolak Aydıner B. A stability assessment of the rockfall problem around the Gökgöl Tunnel (Zonguldak, Turkey). Bull Eng Geol Environ 2017;76:1237–48.
[4]      Hu J, Li S, Li L, Shi S, Zhou Z, Liu H, et al. Field, experimental, and numerical investigation of a rockfall above a tunnel portal in southwestern China. Bull Eng Geol Environ 2018;77:1365–82.
[5]      Shafiee AH, Falamaki A, Shafiee A, Arjmand F. Probabilistic analysis of an 80,000 m2 landslide in Shiraz, Iran. Landslides 2022;19:659–71.
[6]      Thakur T, Singh K, Sharma A. A Review on Analysis and Mitigation Strategies for Landslide Risk Management: Case studies of Nainital, Satluj Valley, Pipalkoti, Jhakri, Panjpiri in Himalayan Region, India. J Min Environ 2024;15:1255–70.
[7]      Romana M. New adjustment ratings for application of Bieniawski classification to slopes. Proc. Int. Symp. role rock Mech. Zacatecas, Mex., 1985, p. 49–53.
[8]      Qazi A, Singh K. Rock Mass Classification Techniques and Parameters: a Review. J Min Environ 2023;14:155–78.
[9]      Stevens WD. RocFall, a tool for probabilistic analysis, design of remedial measures and prediction of rockfalls. 1998.
[10]     PFEIFFER TJ, BOWEN TD. Computer simulation of rockfalls. Bull Assoc Eng Geol 1989;26:135–46.
[11]     Meriam JL, Kraige LG, Bolton JN. Engineering mechanics: dynamics. John Wiley & Sons; 2020.
[12]     Buzzi O, Giacomini A, Spadari M. Laboratory investigation on high values of restitution coefficients. Rock Mech Rock Eng 2012;45:35–43.
[13]     Ansari MK, Ahmad M, Singh R, Singh TN. Correlation between Schmidt hardness and coefficient of restitution of rocks. J African Earth Sci 2015;104:1–5.
[14]     Li L, Sun S, Li S, Zhang Q, Hu C, Shi S. Coefficient of restitution and kinetic energy loss of rockfall impacts. KSCE J Civ Eng 2016;20:2297–307.
[15]     Asteriou P, Tsiambaos G. Effect of impact velocity, block mass and hardness on the coefficients of restitution for rockfall analysis. Int J Rock Mech Min Sci 2018;106:41–50.
[16]     Asteriou P. Effect of impact angle and rotational motion of spherical blocks on the coefficients of restitution for rockfalls. Geotech Geol Eng 2019;37:2523–33.
[17]     Ji Z-M, Chen Z-J, Niu Q-H, Wang T-J, Song H, Wang T-H. Laboratory study on the influencing factors and their control for the coefficient of restitution during rockfall impacts. Landslides 2019;16:1939–63.
[18]     Ji Z-M, Chen Z-J, Niu Q-H, Wang T-H, Wang T-J, Chen T-L. A calculation model of the normal coefficient of restitution based on multi-factor interaction experiments. Landslides 2021;18:1531–53.
[19]     Tang J, Zhou X, Liang K, Lai Y, Zhou G, Tan J. Experimental study on the coefficient of restitution for the rotational sphere rockfall. Environ Earth Sci 2021;80:419.
[20]     Asteriou P, Saroglou H, Tsiambaos G. Geotechnical and kinematic parameters affecting the coefficients of restitution for rock fall analysis. Int J Rock Mech Min Sci 2012;54:103–13.
[21]     Spadari M, Giacomini A, Buzzi O, Fityus S, Giani GP. In situ rockfall testing in new south wales, australia. Int J Rock Mech Min Sci 2012;49:84–93.
[22]     Ferrari F, Giani GP, Apuani T. Why can rockfall normal restitution coefficient be higher than one? Rend Online Della Soc Geol Ital 2013;24:122–4.
[23]     Ji Z-M, Hu S-M, Chen Z-J, Niu Q-H, Wang T-H, Wu F-Q. Laboratory investigation of the effect of the rotational speed on the coefficient of restitution. Eng Geol 2021;292:106196.
[24]     Zadeh LA. Fuzzy sets. Inf Control 1965;8:338–53.
[25]     Ross TJ. Fuzzy logic with engineering applications. John Wiley & Sons; 2009.
[26]     Mamdani EH. Advances in the linguistic synthesis of fuzzy controllers. Int J Man Mach Stud 1976;8:669–78.
[27]     Takagi T, Sugeno M. Derivation of fuzzy control rules from human operator’s control actions. IFAC Proc Vol 1983;16:55–60.
[28]     Jang J-S. ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans Syst Man Cybern 1993;23:665–85.
[29]     Khajeh A, Mousavi SR, RAKHSHANI MM. Adaptive neural fuzzy inference system models for predicting the shear strength of reinforced concrete deep beams 2015.
[30]     Ghorbani A, Ghasemi MR. Reliability and sensitivity analysis of structures using adaptive neuro-fuzzy systems. J Rehabil Civ Eng 2020;8:75–86.
[31]     Polykretis C, Chalkias C, Ferentinou M. Adaptive neuro-fuzzy inference system (ANFIS) modeling for landslide susceptibility assessment in a Mediterranean hilly area. Bull Eng Geol Environ 2019;78:1173–87.
[32]     Razavi-Termeh SV, Shirani K, Pasandi M. Mapping of landslide susceptibility using the combination of neuro-fuzzy inference system (ANFIS), ant colony (ANFIS-ACOR), and differential evolution (ANFIS-DE) models. Bull Eng Geol Environ 2021;80:2045–67.
[33]     Shafiee AH, Oulapour M, Abdlkadhim MAA. Stability of subsea circular tunnels using finite element limit analysis and adaptive neuro-fuzzy inference system. Earth Sci Informatics 2024;17:2417–27.
[34]     Friedman JH. Multivariate adaptive regression splines. Ann Stat 1991;19:1–67.
[35]     Gan Y, Duan Q, Gong W, Tong C, Sun Y, Chu W, et al. A comprehensive evaluation of various sensitivity analysis methods: A case study with a hydrological model. Environ Model \& Softw 2014;51:269–85.
[36]     Shafiee AH, Neamani AR, Eskandarinejad A, Hosseini R, Gholami A. Undrained stability of wide rectangular subsea tunnels using finite element limit analysis and multivariate adaptive regression splines. Earth Sci Informatics 2025;18:60.
[37]     Eskandarinejad A, Shiau J, Lai VQ, Keawsawasvong S. Predicting uplift capacity of group anchors in sand using 3D FELA and MARS. Mar Georesources \& Geotechnol 2025;43:607–21.
[38]     Nouri Y, Ghanizadeh AR, Safi Jahanshahi F, Fakharian P. Data-driven prediction of axial compression capacity of GFRP-reinforced concrete column using soft computing methods. J Build Eng 2025;101:111831. https://doi.org/10.1016/J.JOBE.2025.111831.
[39]     Ghanizadeh AR, Safi Jahanshahi F, Ziayi A. Presenting a Model for Predicting CBR and UCS of Expensive Soil Stabilized with Hydrated Lime Activated with Rice Husk Ash Using the Hybrid MARS-EBS Method. Road 2025;33:45–66.
[40]     Ghanizadeh AR, Ghanizadeh A, Asteris PG, Fakharian P, Armaghani DJ. Developing bearing capacity model for geogrid-reinforced stone columns improved soft clay utilizing MARS-EBS hybrid method. Transp Geotech 2023;38:100906.
[41]     Ghanizadeh AR, Safi Jahanshahi F, Khalifeh V, Jalali F. Predicting flow number of asphalt mixtures based on the marshall mix design parameters using multivariate adaptive regression spline (MARS). Int J Transp Eng 2020;7:433–48.
[42]     Ghanizadeh AR, Fakhri M. Prediction of frequency for simulation of asphalt mix fatigue tests using MARS and ANN. Sci World J 2014;2014:515467.
[43]     Fakharian P, Nouri Y, Ghanizadeh AR, Jahanshahi FS, Naderpour H, Kheyroddin A. Bond strength prediction of externally bonded reinforcement on groove method (EBROG) using MARS-POA. Compos Struct 2024;349:118532.
[44]     D-14 A. Standard Test Methods for Determination of Rock Hardness by Rebound Hammer Method, American Society for Testing and Materials West Conshohocken, PA, USA; 2014.
[45]     Robotham ME, Wang H, Walton G. Assessment of risk from rockfall from active and abandoned quarry slopes. Trans Inst Min Metall Sect A Min Ind 1995;104.
[46]     Gili JA, Ruiz-Carulla R, Matas G, Moya J, Prades A, Corominas J, et al. Rockfalls: Analysis of the block fragmentation through field experiments. Landslides 2022;19:1009–29.
[47]     Chiu SL. Fuzzy model identification based on cluster estimation. J Intell Fuzzy Syst 1994;2:267–78.
[48]     Jang J-SR, Sun C-T, Mizutani E. Neuro-fuzzy and soft computing-a computational approach to learning and machine intelligence [Book Review]. IEEE Trans Automat Contr 1997;42:1482–4.