Neural Network-Based Prediction of Amplification Factors for Nonlinear Soil Behaviour: Insights into Site Proxies
Abstract
:Featured Application
Abstract
1. Introduction
2. Derivation of Amplification Factors (AFs)
2.1. Introduction
2.2. Input Waveforms
2.3. Site Model, Wave Propagation Solution, and Transfer Function T(f)
- with:
2.4. Database
2.4.1. Descriptions of Soil Profiles Studied
2.4.2. Selection of Site Parameters Studied
2.4.3. Correlation Between Site Parameters
3. Computed Amplification Factors: Main Statistical Characteristics
3.1. Validation of Adopted Methodology for Computation of AFs
3.2. General Background of Computed AFs
- is introduced to identify the soil profile, ;
- for clay (using the shear modulus degradation curve of clay) and for sand (using the shear modulus degradation curve of sand);
- , is the ith structural period, and AF values are systematically computed for 100 values, equally spaced between 0.01 and 10 s on a logarithmic period axis;
- , for the identification of the PGA level, and lo, vary from 1 (for PGA = 0.01 g) to 11 (for PGA = 1.05 g).
3.3. Means and Variability of AFs
- For each profile set, we compute the , the average amplification factors (AFm), to constitute, for each soil type, a database of 3564 values and their associated variability , the mean amplification factor , and the associated initial variability . The results are displayed in Figure 6a,b for the clay and sand sets, respectively. The following main observations are derived:
- The peak period, i.e., the period with the peak amplification factor, covers a very broad range from 0.08 s to about 6–7 s for clay and sand soil profiles, which explains the richness of the database.
- As shown in Figure 4 and Figure 5, the corresponding peak amplification ranges from less than 1.0 to 4.0 and up to 5.0 for low levels of PGA (0.01 g to 0.05 g). However, increasing the PGA level results in a decrease in the peak amplification factors to values of around 2.0 to 2.5 for a PGA ranging from 0.75 g to 1.05 g. The average amplification factors for clay are generally higher than those for sand at the mean (2 Hz ≤ f < 5 Hz) and high (f ≥ 5 Hz) frequency ranges.
- Some amplification factors exhibit a short period of de-amplification. A careful look at the corresponding soil profiles indicates that they correspond to deep soft soils, with low velocity, which act as seismic isolators.
- The overall average amplification factor (Figure 6a,b) is higher than unity for periods greater than 0.5 s for clay soil profiles, but it is greater than 0.9 s for sand soil profiles. The lowest overall average amplification factor is observed in the 0.05 to 0.15 s period range for clay and sand soil profiles. In this period range, the overall average amplification factor is less than 0.7 and 0.6 for clay and sand, respectively. The overall average amplification factors are significantly smaller than the peak values for individual profiles, which highlights the need to identify relevant site parameters that may explain this site-to-site variability.
- The “initial variability” associated with the average AFs (Table 3) has a maximum value at low to intermediate periods (0.01 to 0.4 s), reaching up to 0.39 for clay and 0.47 for sand soil. It then gradually vanishes with the period’s increase, reaching a value of around 0.065 at T = 10 s.
3.4. The Division of the Period Range: Short, Intermediate, and Long Periods
4. Description and Implementation of Neural Network Method
5. Results
5.1. Determination of Site Proxies Using GRNN
- The PGA is common to all input parameter combinations. The model did not converge when not considering the PGA nor when considering only a single parameter. This means that the PGA is a predominant input parameter, and at the very least, a couple of PGAs with another parameter are needed to achieve convergence.
- The PGA and f0 constitute the best couple for the prediction of the amplification factor, producing 64% to 65% reductions in the standard deviation for clay and sand soil profiles, respectively. The PGA performs well for all periods and soil types. In comparison, all other couples of parameters offer a lower reduction in variability, capped at 33%.
- The triplet (PGA, Cv, f0) is the most pertinent triplet for predicting the AF, with a standard deviation reduction of more than 71% for clay and 73% for sand profiles. The other triplets (PGA, Cv2, f0), (PGA, Vsm, f0), and (PGA, Vs30, f0), which present interesting but slightly lower performances, are also worthy of consideration. However, because parameters such as Cv and Cv2 are difficult to measure in practice and have less physical meaning, the triplet (PGA, Vs30, f0) is the triplet retained for predicting the AF. Considering more than three parameters will lead to better predictions, but for practical reasons, we decided not to go further.
- The largest root mean square errors are systematically found in short to intermediate period ranges (see Figure 7).
5.2. Variation in Amplification Factors for Specific Period Ranges Using RBF
- Generally, the amplification factors Fa, Fv, and Fl, are higher for clay-type soil than for sand-type soil. This is particularly true for the range of low frequencies f0 up to 1 Hz. However, for f0 values higher than 3 Hz and for relatively stiff soils, with a value exceeding 350 m/s, Fa and Fv values are slightly higher for sand than for clay.
- The amplification factors are higher for low PGA values. This holds true for the factor Fl and soft soils with low values.
- -
- Some combinations are not possible in real cases, such as having a soil profile with a fundamental frequency f0 greater than 10 Hz while its Vs30 value is lower than 500 m/s. In such situations, the predictions of Equation (26) are somehow extrapolations that are very likely erroneous and meaningless.
- -
- The predictions of Equation (26) shall be considered for explaining the global tendency regarding the interactions between different parameters such as the change in the amplification factors with the PGA level, Vs30 (about 600 m/s). We can observe, for instance, that stiff soils with high Vs30 values have higher Fa but lower Fl than soft soils with low values of Vs30 (about 150 m/s). Similarly, the tendencies of Fv and Fl with Vs30 and PGA can be deduced from the results shown in Figure 10 and Figure 11, respectively.
6. Conclusions
- The pair (PGA, f0) was identified as effective for predicting AFs, achieving reductions in the standard deviation of 64% and 65% for clay and sand profiles, respectively.
- The triplet (PGA, Cv, f0) proved to be particularly powerful in predicting actual AFs, resulting in standard deviation reductions of over 71% for both clay and sand. Other combinations, such as (PGA, Cv2, f0), (PGA, Vsm, f0), and (PGA, Vs30, f0), also yielded promising results and can be utilized.
- Because parameters Cv and Cv2 are often difficult and costly to measure in engineering practices, we recommend using the combination (PGA, Vs30, f0), which, while offering slightly lower performance, still provides a significant reduction in the standard deviation, making it a practical alternative for field applications.
- The Inclusion of the Fundamental Frequency: The fundamental frequency (f0) should be considered alongside the peak ground acceleration (PGA) and shear wave velocity (Vs30) to improve predictions of amplification factors.
- The Distinction of Period Ranges: It is crucial to differentiate between amplification factors for short (Fa), medium (Fv), and long (Fl) period ranges. The long-period amplification (Fl) is particularly significant, often exceeding Fa and Fv values for soil profiles with low Vs30 values, which typically correspond to site classes C, D, and E in Eurocode 8 (EC8) and site classes D and E in UBC/CNBC codes.
Supplementary Materials
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Bard, P.-Y.; Campillo, M.; Chavez-Garcia, F.J.; Sanchez-Sesma, F.J. The Mexico Earthquake of September 19, 1985—A Theoretical Investigation of Large- and Small-scale Amplification Effects in the Mexico City Valley. Earthq. Spectra 1988, 4, 609–633. [Google Scholar] [CrossRef]
- Kawase, H.; Aki, K. A study on the response of a soft soil basin for incident S, P, and Rayleigh waves with special reference to the long duration observed in Mexico City. Bull. Seismol. Soc. Am. 1989, 79, 1361–1382. [Google Scholar]
- Chávez-García, F.J.; Bard, P.Y. Site effects in Mexico City eight years after the September 1985 Michoacan earthquakes. Soil Dyn. Earthq. Eng. 1994, 13, 229–247. [Google Scholar]
- Del Gaudio, V.; Pierri, P.; Rajabi, A.M. An approach to identify site response directivity of accelerometer sites and application to the Iranian Area. Pure Appl. Geophys. 2015, 172, 1471–1490. [Google Scholar] [CrossRef]
- Cherid, D.; Hammoutene, M.; Tiliouine, B.; Berrah, M.K. Local seismic site amplification: Effects of obliquely incident antiplane motions. J. Seismol. 2017, 21, 509–524. [Google Scholar] [CrossRef]
- Sandıkkaya, M.A.; Akkar, S. Cumulative absolute velocity, Arias intensity and significant duration predictive model from a pan-European strong-motion dataset. Bull. Earthq. Eng. 2017, 15, 1881–1898. [Google Scholar] [CrossRef]
- Boudghene Stambouli, A.; Zendagui, D.; Bard, P.Y.; Dif, H. Influence of site parameters on fourier amplification application for 1D linear viscoelastic method. Period. Polytech. Civ. Eng. 2021, 65, 229–241. [Google Scholar] [CrossRef]
- Dif, H.; Boudghene Stambouli, A. Impact of site condition on Arias intensity and Cumulative absolute velocity: Application for low seismicity areas. Asian J. Civ. Eng. 2023, 24, 1411–1424. [Google Scholar] [CrossRef]
- Buckle, I.G.; Friedland, I.; Mander, J.; Martin, G.; Nutt, R.; Power, M. Seismic Retrofitting Manual for Highway Structures. Part 1, Bridges (No. FHWA-HRT-06-032); Turner-Fairbank Highway Research Center: McLean, VA, USA, 2006.
- Borcherdt, R.D. Estimates of site dependent response spectra for design (methodology and justification). Earthq. Spectra 1994, 10, 617–653. [Google Scholar] [CrossRef]
- Martin, G.R.; Dobry, R. Earthquake site response and seismic code provisions. NCEER Bull. 1994, 8, 1–6. [Google Scholar]
- Dickenson, S.E.; Seed, R.B. Nonlinear Dynamic Response of Soft and Deep Cohesive Soil Deposits. In Proceedings of the International Workshop on Site Response Subjected to Strong Earthquake Motions, Yokosuka, Japan, 16–17 January 1996; Volume 2, pp. 67–81. [Google Scholar]
- Dobry, R.; Borcherdt, R.D.; Crouse, C.B.; Idriss, I.M.; Joyner, W.N.; Martin, G.R.; Power, M.S.; Rinne, E.E.; Seed, R.B. New Site coefficients and site classification system used in recent building seismic code provisions. Earthq. Spectra 2000, 16, 41–67. [Google Scholar] [CrossRef]
- Steidl, J.H. Site response in southern California for probabilistic seismic hazard analysis. Bull. Seismol. Soc. Am. 2000, 90, S149–S169. [Google Scholar] [CrossRef]
- Rodriguez-Marek, A.; Bray, J.D.; Abrahamson, N.A. An empirical geotechnical seismic site response procedure. Earthq. Spectra 2001, 17, 65–87. [Google Scholar] [CrossRef]
- Pitilakis, K.D.; Makra, K.A.; Raptakis, D.G. 2D vs 3D Site Effects with Potential Applications to Seismic Norms: The case of EUROSEISTEST and Thessaloniki. In Proceedings of the XVth ICSMGE, Istanbul, Turkey, 27–31 August 2001; pp. 123–133. [Google Scholar]
- Stewart, J.P.; Liu, A.H.; Choi, Y. Amplification Factors for Spectral Acceleration in Tectonically Active Regions. Bull. Seismol. Soc. Am. 2003, 93, 332–352. [Google Scholar] [CrossRef]
- Choi, Y.; Stewart, J.P. Nonlinear site amplification as function of 30 m shear wave velocity. Earthq. Spectra 2005, 21, 1–30. [Google Scholar] [CrossRef]
- Castellaro, S.; Mulargia, F.; Rossi, P.M. Vs30: Proxy for seismic amplification? Seismol. Res. Lett. 2008, 79, 540–543. [Google Scholar] [CrossRef]
- Lee, V.W.; Trifunac, M.D. Should average shear-wave velocity in the top 30m of soil be used to describe seismic amplification? Soil Dyn. Earthq. Eng. 2010, 30, 1250–1258. [Google Scholar] [CrossRef]
- Abrahamson, N.; Atkinson, G.; Boore, D.; Bozorgnia, Y.; Campbell, K.; Chiou, B.; Idriss, I.; Silva, W.; Youngs, R. Comparisons of the NGA ground-motion relations. Earthq. Spectra 2008, 24, 45–66. [Google Scholar] [CrossRef]
- Gregor, N.; Abrahamson, N.A.; Atkinson, G.M.; Boore, D.M.; Bozorgnia, Y.; Campbell, K.W.; Chiou, B.S.-J.; Idriss, I.M.; Kamai, R.; Seyhan, E.; et al. Comparison of NGA-West2 GMPEs. Earthq. Spectra 2014, 30, 1179–1197. [Google Scholar] [CrossRef]
- Ancheta, T.D.; Darragh, R.B.; Stewart, J.P.; Seyhan, E.; Silva, W.J.; Chiou, B.S.-J.; Wooddell, K.E.; Graves, R.W.; Kottke, A.R.; Boore, D.M.; et al. NGA-West 2 database. Earthq. Spectra 2014, 30, 989–1005. [Google Scholar] [CrossRef]
- Douglas, J.; Akkar, S.; Ameri, G.; Bard, P.-Y.; Bindi, D.; Bommer, J.J.; Singh Bora, S.; Cotton, F.; Derras, B.; Hermkes, M.; et al. Comparisons among the five ground-motion models developed using RESORCE for the prediction of response spectral accelerations due to earthquakes in Europe and the Middle East. Bull. Earthq. Eng. 2014, 12, 341–358. [Google Scholar] [CrossRef]
- Luzi, L.; Puglia, R.; Pacor, F.; Gallipoli, M.; Bindi, D.; Mucciarelli, M. Proposal for a soil classification based on parameters alternative or complementary to Vs, 30. Bull. Earthq. Eng. 2011, 9, 1877–1898. [Google Scholar] [CrossRef]
- Cadet, H.; Bard, P.-Y.; Duval, A.-M.; Bertrand, E. Site effect assessment using KiK-net data—Part 2—Site amplification prediction equation (SAPE) based on f0 and Vsz. Bull. Earthq. Eng. 2012, 10, 451–489. [Google Scholar] [CrossRef]
- Pitilakis, K.; Riga, E.; Anastasiadis, A. Design spectra and amplification factors for Eurocode 8. Bull. Earthq. Eng. 2012, 10, 1377–1400. [Google Scholar] [CrossRef]
- Pitilakis, K.; Riga, E.; Anastasiadis, A. New code site classification, amplification factors and normalized response spectra based on a worldwide ground-motion database. Bull. Earthq. Eng. 2013, 11, 925–966. [Google Scholar] [CrossRef]
- NEHRP Guidelines for the Seismic Rehabilitation of Buildings; FEMA-273; Federal Emergency Management Agency: Washington, DC, USA, 1997. Available online: https://courses.washington.edu/cee518/fema273.pdf (accessed on 10 March 2025).
- Uniform Building Code. Structural engineering design provisions. In Proceedings of the International Conference of Building Officials, Whittier, CA, USA, 14 July 1997; Volume 2. [Google Scholar]
- EN 1998-1; EC8 Eurocode 8. Design of Structures for Earthquake Resistance—Part 1: General Rules, Seismic Actions and Rules for Buildings. European Committee for Standardization (CEN): Brussels, Belgium, 2004. Available online: https://eurocodes.jrc.ec.europa.eu (accessed on 1 February 2016).
- IBC2012. International Building Code, 2012 ed.; International Code Council: Washington, DC, USA, 2012; ISBN 978-1-60983-039-7. Available online: https://archive.org/details/gov.law.icc.ibc.2012 (accessed on 1 November 2016).
- Canadian Commission on Building and Fire Codes, National Research Council of Canada. National Building Code of Canada (NBC) (2015) National Building Code of Canada; Canadian Commission on Building and Fire Codes, National Research Council of Canada: Ottawa, ON, Canada, 2015. [Google Scholar]
- Canadian Commission on Building and Fire Codes, National Research Council of Canada. National Building Code of Canada (NBC) (2015b) User’s Guide—NBC 2015 Structural Commentaries (Part 4 of Division B); Canadian Commission on Building and Fire Codes, National Research Council of Canada: Ottawa, ON, Canada, 2015. [Google Scholar]
- Boudghene Stambouli, A.; Zendagui, D.; Bard, P.-Y.; Derras, B. Deriving amplification factors from simple site parameters using generalized regression neural networks: Implications for relevant site proxies. Earth Planets Space 2017, 69, 99. [Google Scholar] [CrossRef]
- Ghaboussi, J.; Garrett, J., Jr.; Wu, X. Knowledge-based modeling of material behavior with neural networks. J. Eng. Mech. 1991, 117, 132–153. [Google Scholar] [CrossRef]
- Ghaboussi, J.; Sidarta, D. New nested adaptive neural networks (NANN) for constitutive modeling. Comput. Geotech. 1998, 22, 29–52. [Google Scholar] [CrossRef]
- Paolucci, R.; Colli, P.; Giacinto, G. Assessment of seismic site effect in 2-D alluvial Valleys Using Neural Networks. Earthq. Spectra 2000, 16, 661–680. [Google Scholar] [CrossRef]
- Hurtado, J.; Londono, J.; Meza, M. On the applicability of neural networks for soil dynamic amplification analysis. Soil Dyn. Earthq. Eng. 2001, 21, 579–591. [Google Scholar] [CrossRef]
- Derras, B.; Bard, P.Y.; Cotton, F.; Bekkouche, A. Adapting the neural network approach to PGA prediction: An example based on the KiK-net data. Bull. Seismol. Soc. Am. 2012, 102, 1446–1461. [Google Scholar] [CrossRef]
- Poggio, T.; Girosi, F. Networks for approximation and learning. Proc. IEEE 1990, 78, 1481–1497. [Google Scholar] [CrossRef]
- Liu, S.; Wang, L.; Zhang, W.; Sun, W.; Wang, Y.; Liu, J. Physics-informed optimization for a data-driven approach in landslide susceptibility evaluation. J. Rock Mech. Geotech. Eng. 2024, 16, 3192–3205. [Google Scholar] [CrossRef]
- Zhang, Z.; Pan, Q.; Yang, Z.; Yang, X. Physics-informed deep learning method for predicting tunnelling-induced ground deformations. Acta Geotechnica 2023, 18, 4957–4972. [Google Scholar] [CrossRef]
- Constantopoulos, I.V.; Roesset, J.M.; Christian, J.T. A comparison of linear and exact nonlinear analysis of soil amplification. In Proceedings of the 5th WCEE, Rome, Italy, 25–29 June 1973; pp. 1806–1815. [Google Scholar]
- Yoshida, N.; Kobayashi, S.; Suetomi, I.; Miura, K. Equivalent linear method considering frequency dependent characteristics of stiffness and damping. Soil Dyn. Earthq. Eng. 2002, 22, 205–222. [Google Scholar] [CrossRef]
- Assimaki, D.; Kausel, E. An equivalent linear algorithm with frequency-and pressure-dependent moduli and damping for the seismic analysis of deep sites. Soil Dyn. Earthq. Eng. 2002, 22, 959–965. [Google Scholar] [CrossRef]
- Johari, A.; Momeni, M. Stochastic analysis of ground response using non-recursive algorithm. Soil Dyn. Earthq. Eng. 2015, 69, 57–82. [Google Scholar] [CrossRef]
- Trifunac, M.D.; Todorovska, M.I. Can aftershock studies predict site amplification factors? Northridge, CA, earthquake of 17 January 1994. Soil Dyn. Earthq. Eng. 2000, 19, 233–251. [Google Scholar] [CrossRef]
- Nguyen, X.D.; Guizani, L. On the application limits and performance of the single-mode spectral analysis for seismic analysis of isolated bridges in Canada. Can. J. Civ. Eng. 2022, 49, 1747–1763. [Google Scholar] [CrossRef]
- Boudghene Stambouli, A.; Bard, P.Y.; Chaljub, E.; Moczo, P.; Kristek, J.; Stripajova, S.; Durand, C.; Zendagui, D.; Derras, B. 2D/1D aggravation factors: From a comprehensive study to estimation with a neural network model. In Proceedings of the 16Ith European Conference of Earthquake Engineering, Thessaloniki, Greece, 18–21 June 2018. [Google Scholar]
- Paolucci, R.; Morstabilini, L. Non-dimensional site amplification functions for basin edge effects on seismic ground motion. In Proceedings of the Third International Symposium on the Effects of Surface Geology on Seismic Motion, Grenoble, France, 30 August–1 September 2006; Volume 30, pp. 823–831. [Google Scholar]
- Seed, H.B.; Idriss, I.M. Soil Moduli and Damping Factors for Dynamic Response Analyses; EERC-70-10; University of California Berkeley Structural Engineers and Mechanics: Berkeley, CA, USA, 1970. [Google Scholar]
- Vucetic, M.; Dobry, R. Cyclic triaxial strain-controlled testing of liquefiable sands. In Advanced Triaxial Testing of Soil and Rock, ASTM STP 977; ASTM International: West Conshohocken, PA, USA, 1988. [Google Scholar]
- Vucetic, M.; Dobry, R. Effect of soil plasticity on cyclic response. J. Geotech. Eng. 1991, 117, 89–107. [Google Scholar] [CrossRef]
- Ishibashi, I.; Zhang, X. Unified dynamic shear moduli and damping ratios of sand and clay. Soils Found. 1993, 33, 182–191. [Google Scholar] [CrossRef]
- EPRI. Guidelines for Determining Design Basis Ground Motions; EPRI Tr-102293; Electric Power Research Institute: Palo Alto, CA, USA, 1993. [Google Scholar]
- Darendeli, M.B. Development of a New Family of Normalized Modulus Reduction and Material Damping Curves; The University of Texas at Austin: Austin, TX, USA, 2001. [Google Scholar]
- Sun, J.I.; Golesorkhi, R.; Seed, H.B. Dynamic Moduli and Damping Ratios for Cohesive Soils; Report No. UCB/EERC-88/15, EERC; College of Engineering, University of California: Berkeley, CA, USA, 1988. [Google Scholar]
- Idriss, I. Response of soft soil sites during earthquakes. In Proc. H. Bolton Seed Memorial Symposium; BiTech Publishers: Berkeley, CA, USA, 1990; pp. 273–289. [Google Scholar]
- Jacobsen, L.S. Steady forced vibration as influenced by damping: An approximate solution of the steady forced vibration of a system of one degree of freedom under the influence of various types of damping. Trans. Am. Soc. Mech. Eng. 1930, 52, 169–178. [Google Scholar] [CrossRef]
- Hudson, D.E. Equivalent Viscous Friction for Hysteretic Systems with Earthquake-Like Excitations. In Proceedings of the 3rd World Conference on Earthquake Engineering, Auckland, New Zealand, 22 January–1 February 1965; pp. II-185/II-201. [Google Scholar]
- Kanai, K. Relation Between the Nature of Surface Layer and the Amplitude of Earthquake Motions; Bulletin, Tokyo Earthquake Research Institute: Tokyo, Japan, 1951. [Google Scholar]
- Matthiesen, R.B.; Duke, C.M.; Leeds, D.J.; Fraser, J.C. Site Characteristics of Southern California Strong-Motion Earthquake Stations, Part Two; Report No. 64-15; Department of Engineering, University of California: Los Angeles, CA, USA, 1964. [Google Scholar]
- Roesset, J.M.; Whitman, R.V. Theoretical Background for Amplification Studies; Massachusetts Institute of Technology: Cambridge, MA, USA, 1969. [Google Scholar]
- Tsai, N.; Housner, G. Calculation of surface motions of a layered half-space. Bull. Seismol. Soc. Am. 1970, 60, 1625–1651. [Google Scholar] [CrossRef]
- Lysmer, J.; Seed, H.B.; Schnabel, P.B. Influence of base-rock characteristics on ground response. Bull. Seismol. Soc. Am. 1971, 61, 1213–1231. [Google Scholar] [CrossRef]
- Schnabel, P.B.; Lysmer, J.L.; Seed, H.B. SHAKE: A Computer Program for Earthquake Response Analysis of Horizontally Layered Sites; Report EERC-72-12; University of California: Berkeley, CA, USA, 1972. [Google Scholar]
- Kramer, S.L.; Stewart, J.P. Geotechnical Earthquake Engineering; CRC Press: Boca Raton, FL, USA, 2024. [Google Scholar]
- Akkar, S.; Sandıkkaya, M.A.; Şenyurt, M.; Azari Sisi, A.; Ay, B.Ö.; Traversa, P.; Douglas, J.; Cotton, F.; Luzi, L.; Hernandez, B.; et al. Reference Database for Seismic Ground-Motion in Europe (RESORCE). Bull. Earthq. Eng. 2014, 12, 311–339. [Google Scholar] [CrossRef]
- Hashash, Y.M.A.; Groholski, D.R.; Phillips, C.A.; Park, D.; Musgrove, M. DEEPSOIL 5.1, User Manual and Tutorial; Department of Civil and Environmental Engineering, University of Illinois at Urbana-Champaign: Urbana, IL, USA, 2012. [Google Scholar]
- Bardet, J.P.; Ichii, K.; Lin, C.H. EERA: A Computer Program for Equivalent-Linear Earthquake Site Response Analyses of Layered Soil Deposits; Department of Civil Engineering, University of Southern California: Los Angeles, USA, USA, 2000. [Google Scholar]
- Seed, H.B.; Romo, M.P.; Sun, J.I.; Jaime, A.; Lysmer, J. Relationships between soil conditions and earthquake ground motions. Earthq. Spectra 1988, 4, 687–729. [Google Scholar] [CrossRef]
- Seed, R.B.; Dickenson, S.E.; Mok, C.M. Seismic response analysis of soft and deep cohesive sites: A brief summary of recent findings. In Proceedings of the CALTRANS First Annual Seismic Response Workshop, Sacramento, CA, USA, 3–4 December 1991. [Google Scholar]
- Chang, S.W.; Bray, J.D.; Gookin, W.B. Seismic Response of Deep Stiff Soil Deposits in the Los Angeles, California Area During the 1994 Northridge Earthquake; University of California at Berkeley: Barkeley, CA, USA, 1997. [Google Scholar]
- Dobry, R.; Oweis, I.; Urzua, A. Simplified Procedures for Estimating the Fundamental Period of a Soil Profile. Bull. Seismol. Soc. Am. 1976, 66, 1293–1321. [Google Scholar]
- Borcherdt, R.D.; Glassmoyer, G. On the Characteristics of Local Geology and Their Influence on Ground Motions Generated by the Loma Prieta Earthquake in the San Francisco Bay Region, California. Bull. Seismol. Soc. Am. 1992, 82, 603–641. [Google Scholar] [CrossRef]
- Salameh, C.; Bard, P.-Y.; Guillier, B.; Harb, J.; Cornou, C.; Almakari, M. Using ambient vibration measurements for risk assessment at an urban scale: From numerical proof of concept to a case study in Beirut (Lebanon). In Proceedings of the 5th IAEE International Symposium: Effects of Surface Geology on Seismic Motion, Taipei, Taiwan, 15–17 August 2016. [Google Scholar]
- Yilmaz, A.S.; Özer, Z. Pitch angle control in wind turbines above the rated wind speed by multi-layer perceptron and radial basis function neural networks. Expert Syst. Appl. 2009, 36, 9767–9775. [Google Scholar] [CrossRef]
- Barrile, V.; Cacciola, M.; D’Amico, S.; Greco, A.; Morabito, F.C.; Parrillo, F. Radial basis function neural networks to foresee aftershocks in seismic sequences related to large earthquakes. In Neural Information Processing, Proceedings of the 13th International Conference, ICONIP 2006, Hong Kong, China, 3–6 October 2006; Proceedings, Part II 13, 909-916; Springer: Berlin/Heidelberg, Germany, 2006. [Google Scholar]
- Baddari, K.; Aïfa, T.; Djarfour, N.; Ferahtia, J. Application of a radial basis function artificial neural network to seismic data inversion. Comput. Geosci. 2009, 35, 2338–2344. [Google Scholar] [CrossRef]
- Günaydın, K.; Günaydın, A. Peak ground acceleration prediction by artificial neural networks for northwestern Turkey. Math. Probl. Eng. 2008, 2008, 919420. [Google Scholar] [CrossRef]
- Broomhead, D.S.; Lowe, D. Radial basis functions, multi-variable functional interpolation and adaptive networks: Royal Signals and Radar Establishment Malvern (United Kingdom). Complex Syst. 1988, 2, 321–355. [Google Scholar]
- Moody, J.; Darken, C.J. Fast learning in networks of locally-tuned processing units. Neural Comput. 1988, 1, 281–294. [Google Scholar] [CrossRef]
- Borgi, A. Apprentissage Supervisé par Génération de Règles: Le Système SUCRAGE. Ph.D. Thesis, Université de Paris, Paris, France, 1999. (In French). [Google Scholar]
- Seghouane, A.K.; Fleury, G. Apprentissage de réseaux de neurones à fonctions radiales de base avec un jeu de données à entrée-sortie bruitées. Trait. Signal 2003, 20, 414. [Google Scholar]
- Chen, S.; Cowan, C.F.; Grant, P.M. Orthogonal least squares learning algorithm for radial basis function networks. IEEE Trans. Neural Netw. 1991, 2, 302–309. [Google Scholar] [CrossRef]
- Specht, D.F. A general regression neural network. IEEE Trans. Neural Netw. 1991, 2, 568–576. [Google Scholar] [CrossRef]
- Cigizoglu, H.K.; Alp, M. Generalized regression neural network in modelling river sediment yield. Adv. Eng. Softw. 2005, 37, 63–68. [Google Scholar] [CrossRef]
- Hannan, S.A.; Manza, R.R.; Ramteke, R.J. Generalized regression neural network and radial basis function for heart disease diagnosis. Int. J. Comput. Appl. 2010, 7, 7–13. [Google Scholar] [CrossRef]
- Wasserman, P.D. Advanced Methods in Neural Computing; John Wiley & Sons Inc.: Hoboken, NJ, USA, 1993. [Google Scholar]
- Kim, B.; Lee, D.W.; Parka, K.Y.; Choi, S.R.; Choi, S. Prediction of plasma etching using a randomized generalized regression neural network. Vacuum 2004, 76, 37–43. [Google Scholar] [CrossRef]
- Kohonen, T. Learning vector quantization. Self-Organ. Maps 1997, 203–217. [Google Scholar]
- Haykin, S. Neural Networks: A Comprehensive Foundation, 2nd ed.; Prentice Hall: Hoboken, NJ, USA, 1999; p. 842. [Google Scholar]
10% Fractile | 50% Fractile | 90% Fractile | ||
---|---|---|---|---|
(m) | 5 | 50 | 200 | |
(m/s) | (m/s) | 100 | 250 | 600 |
(m/s) | 100 | 300 | 642 | |
Cv | 1.66 | 4 | 10 | |
Cv2 | 1.33 | 3 | 8 | |
(Hz) | 0.31 | 1.64 | 12.73 |
Depth | f0 | Cv | Cv2 | Vsm | Vs30 | |
Depth | 1 | 0.5119 | 0.0001 | 0.2584 | 0.0001 | 0.3311 |
f0 | 1 | 0.2926 | 0.4445 | 0.3744 | 0.7496 | |
Cv | 1 | 0.8493 | 0.7815 | 0.6208 | ||
Cv2 | 1 | 0.6638 | 0.7529 | |||
Vsm | 1 | 0.7954 | ||||
Vs30 | 1 |
Total Initial Variability (Soil Type: Clay) | 0.2631 | Total Initial Variability (Soil Type: Sand) | 0.3241 |
---|---|---|---|
0.3905 | 0.4696 | ||
σ (θ = 0, T = 0.01 s) | 0.3061 | σ (θ = 1, T = 0.01 s) | 0.3794 |
σ (θ = 0, T = 0.02 s) | 0.3045 | σ (θ = 1, T = 0.02 s) | 0.3766 |
σ (θ = 0, T = 0.04 s) | 0.3236 | σ (θ = 1, T = 0.04 s) | 0.3954 |
σ (θ = 0, T = 0.07 s) | 0.3649 | σ (θ = 1, T = 0.07 s) | 0.4384 |
σ (θ = 0, T = 0.1 s) | 0.3828 | σ (θ = 1, T = 0.1 s) | 0.4577 |
σ (θ = 0, T = 0.2 s) | 0.3555 | σ (θ = 1, T = 0.2 s) | 0.4369 |
σ (θ = 0, T = 0.4 s) | 0.273 | σ (θ = 1, T = 0.4 s) | 0.3509 |
σ (θ = 0, T = 0.7 s) | 0.2071 | σ (θ = 1, T = 0.7 s) | 0.2783 |
σ (θ = 0, T = 1.0 s) | 0.1768 | σ (θ = 1, T = 1.0 s) | 0.2385 |
σ (θ = 0, T = 2.0 s) | 0.1106 | σ (θ = 1, T = 2.0 s) | 0.1387 |
σ (θ = 1, T = 4.0 s) | 0.0961 | σ (θ = 1, T = 4.0 s) | 0.0998 |
σ (θ = 1, T = 7.0 s) | 0.0804 | σ (θ = 1, T = 7.0 s) | 0.081 |
σ (θ = 0, T = 10.0 s) | 0.0652 | σ (θ = 1, T = 10.0 s) | 0.067 |
Combination of Parameters | Standard Deviation for Clay | Reduction in Standard Deviation | Standard Deviation for Sand | Reduction in Standard Deviation |
---|---|---|---|---|
PGA + Vs30 + f0 + Cv | 0.0695 | 0.73 | 0.0772 | 0.76 |
PGA + Vs30 + depth + Cv | 0.0919 | 0.65 | 0.1047 | 0.68 |
PGA + Vs30 + f0 + Cv2 | 0.0774 | 0.70 | 0.0859 | 0.73 |
PGA + Vs30 + depth + Cv2 | 0.0987 | 0.62 | 0.1129 | 0.65 |
PGA + Vs30 + f0 | 0.0882 | 0.66 | 0.0998 | 0.69 |
PGA + Vsm + f0 | 0.0877 | 0.67 | 0.0997 | 0.69 |
PGA + Cv + f0 | 0.0767 | 0.71 | 0.0881 | 0.73 |
PGA + Cv2 + f0 | 0.0842 | 0.68 | 0.0964 | 0.70 |
PGA + Vs30 + Cv | 0.2013 | 0.23 | 0.2313 | 0.29 |
PGA + Vs30 + Cv2 | 0.1927 | 0.27 | 0.2197 | 0.32 |
PGA + Cv2 + Cv | 0.1867 | 0.29 | 0.2097 | 0.35 |
PGA + Vs30 + depth | 0.1086 | 0.59 | 0.1265 | 0.61 |
PGA + Cv + depth | 0.1197 | 0.54 | 0.1414 | 0.56 |
PGA + Cv2 + depth | 0.1255 | 0.52 | 0.1482 | 0.54 |
PGA + Vs30 | 0.2112 | 0.20 | 0.2470 | 0.24 |
PGA + Vsm | 0.2204 | 0.16 | 0.2554 | 0.21 |
PGA + f0 | 0.0939 | 0.64 | 0.1140 | 0.65 |
PGA + Cv | 0.2242 | 0.15 | 0.2609 | 0.19 |
PGA + Cv2 | 0.1921 | 0.27 | 0.2173 | 0.33 |
PGA + depth | 0.1770 | 0.33 | 0.2192 | 0.32 |
0.2631 | 0.3241 |
Statistical Summary for Amplification at Specific Period Ranges | Fa | Fv | Fl |
---|---|---|---|
(Clay, θ = 0) | 0.0441 | 0.0436 | 0.0363 |
0.3759 | 0.1632 | 0.0917 | |
0.9931 | 0.9637 | 0.9184 | |
Number of key neurons | 16 | 10 | 10 |
Standard deviation for all databases (soil type: sand) | 0.0504 | 0.0437 | 0.0341 |
0.4551 | 0.2228 | 0.0967 | |
0.9939 | 0.9805 | 0.9358 | |
12 | 10 | 9 |
Main Result for Amplification at Specific Period (Test Database) | Fa | Fv | Fl |
---|---|---|---|
Standard deviation for database (50% test database) (soil type: clay) | 0.0479 | 0.004 | 0.0369 |
0.9914 | 0.9667 | 0.9142 | |
Standard deviation for database (50% test database) (soil type: sand) | 0.0514 | 0.0436 | 0.0365 |
0.9933 | 0.9794 | 0.9227 |
Participation of Synaptic Weights | (%) PGA | (%) f0 | (%) Vs30 |
---|---|---|---|
(soil type: clay) | 30.51 | 46.82 | 22.67 |
(soil type: clay) | 32.73 | 45.81 | 21.45 |
(soil type: clay) | 33.44 | 45.26 | 21.30 |
(soil type: sand) | 30.76 | 51.10 | 18.14 |
(soil type: sand) | 31.75 | 47.11 | 21.14 |
(soil type: sand) | 41.52 | 37.62 | 20.86 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Boudghene Stambouli, A.; Guizani, L. Neural Network-Based Prediction of Amplification Factors for Nonlinear Soil Behaviour: Insights into Site Proxies. Appl. Sci. 2025, 15, 3618. https://doi.org/10.3390/app15073618
Boudghene Stambouli A, Guizani L. Neural Network-Based Prediction of Amplification Factors for Nonlinear Soil Behaviour: Insights into Site Proxies. Applied Sciences. 2025; 15(7):3618. https://doi.org/10.3390/app15073618
Chicago/Turabian StyleBoudghene Stambouli, Ahmed, and Lotfi Guizani. 2025. "Neural Network-Based Prediction of Amplification Factors for Nonlinear Soil Behaviour: Insights into Site Proxies" Applied Sciences 15, no. 7: 3618. https://doi.org/10.3390/app15073618
APA StyleBoudghene Stambouli, A., & Guizani, L. (2025). Neural Network-Based Prediction of Amplification Factors for Nonlinear Soil Behaviour: Insights into Site Proxies. Applied Sciences, 15(7), 3618. https://doi.org/10.3390/app15073618