Prediction of California bearing ratio and modified proctor parameters using deep neural networks and multiple linear regression: A case study of granular soils
Source abstract
Abstract
The California Bearing Ratio (CBR) and modified proctor parameters belong to the soil geotechnical properties used to assess soil behaviour. Direct measurement of these properties can be quite time-consuming in large-scale applications or when immediate results are required. Therefore, significant research efforts have been made in the literature to develop indirect methods for their estimation. However, some gaps in the state-of-the-art can be highlighted in these topics, such as the deficiency in computational models to calculate the maximum dry unit weight (γd(max)), optimum moisture content (wopt) and CBR, and the lack of methods that consider their intrinsic influence on each other. Hence, in this investigation, mathematical and computational models were created to obtain the above-mentioned variables from the soil grain size distribution. The mathematical model was based on Multiple Linear Regression (MLR) correlations. Meanwhile, the computational model was constructed from a custom-made Deep Neural Networks (DNNs) architecture. Subsequently, the accuracy of these models was validated with an experimental case study. The results demonstrated that the proposed methods in this study are more precise than previous approaches in the literature. Accordingly, the main contribution of this manuscript to the industry is the formation of models with high exactness to predict the γd(max), wopt and CBR of granular soils.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Soil and Unsaturated Flow · Landslides and related hazards · Geotechnical Engineering and Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (100+)
Show source-provided references
1. The effect of overconsolidation on monotonic and cyclic behaviours of frozen subgrade soil
2. Study of the bearing capacity of closely spaced square foundations on granular soils10.1007/s10706-018-0694-5 ↗
3. Implementation of deep neural networks and statistical methods to predict the resilient modulus of soils10.1080/10298436.2023.2257852 ↗
4. Chapter 7: advanced modelling approaches
5. Soil behavior and characterization: effect of improvement in CBR characteristics of soil subgrade on design of bituminous pavements10.1007/s40098-021-00533-8 ↗
6. Experimental investigation on design of thickness for flexible pavement subgrade soils using CBR approach
7. A new approach for determining resilient moduli of marginal pavement base materials using the staged repeated load CBR test method10.1080/14680629.2017.1352532 ↗
8. Procedural uncertainties of proctor compaction tests applied on MSWI bottom ash10.1016/j.jhazmat.2010.12.045 ↗
9. Comparative analysis of gyratory and proctor compaction processes of unbound granular materials10.1080/14680629.2011.9695251 ↗
10. Requirements for pavement base layers with unbound granular material10.2478/sjce-2019-0018 ↗
11. Unveiling the effect of transport infrastructure and technological innovation on economic growth, energy consumption and CO2 emissions
12. The role of transport infrastructure in economic growth: empirical evidence in the UK10.1016/j.tranpol.2023.01.017 ↗
13. Re-appraising ‘in-process’ benefits of strategic infrastructure improvements: capturing the unexpected socio-economic impacts for lagging regions10.1016/j.tranpol.2023.02.012 ↗
14. Guide for mechanistic-empirical design of new and rehabilitated pavement structures - appendix CC-1: correlation of CBR values with soil index properties
15. Effect of grain size distribution on California bearing ratio (CBR) and modified proctor parameters for granular materials10.1007/s13369-020-04673-6 ↗
16. Prediction of California Bearing Ratio (CBR) and compaction characteristics of granular soils
17. State-of-the-art review of geotechnical-driven artificial intelligence techniques in underground soil-structure interaction
18. A survey on applications of artificial intelligence for pre-parametric project cost and soil shear-strength estimation in construction and geotechnical engineering
19. Application of artificial intelligence in geotechnical engineering: a state-of-the-art review
20. Practice of artificial intelligence in geotechnical engineering10.1631/jzus.A20AIGE1 ↗
21. Applications of artificial intelligence and machine learning in geotechnical engineering
22. A systematic review and meta-analysis of artificial neural network application in geotechnical engineering: theory and applications10.1007/s00521-019-04109-9 ↗
23. Application of deep learning algorithms in geotechnical engineering: a short critical review10.1007/s10462-021-09967-1 ↗
24. A maximum entropy method using fractional moments and deep learning for geotechnical reliability analysis10.1007/s11440-021-01326-2 ↗
25. Use of neural networks for the prediction of the CBR value of some Aegean sands10.1007/s00521-015-1943-7 ↗
26. Regression and neural network models for California bearing ratio prediction of typical granular materials in Egypt10.1007/s13369-019-03803-z ↗
27. Prediction of California bearing ratio (CBR) of fine grained soils by AI methods10.1016/j.advengsoft.2010.01.003 ↗
28. Explainable artificial intelligence: a comprehensive review10.1007/s10462-021-10088-y ↗
29. Machine learning in subsurface geothermal energy: two decades in review
30. A survey on machine learning-based routing for VLSI physical design10.1016/j.vlsi.2022.05.003 ↗
31. On removing conflicts for machine learning
32. A review of feature selection methods for machine learning-based disease risk prediction
33. Chapter 5: machine learning
34. Traffic flow prediction models – a review of deep learning techniques10.1080/23311916.2021.2010510 ↗
35. Deep learning based recommender system: a survey and new perspectives10.1145/3158369 ↗
36. Financial time series forecasting with deep learning: a systematic literature review: 2005–2019
37. A survey on deep learning: algorithms, techniques, and applications10.1145/3234150 ↗
38. Automatic segmentation of mandible from conventional methods to deep learning - a review
39. Deep learning10.1038/nature14539 ↗
40. A federated calibration scheme for convolutional neural networks: models, applications and challenges10.1016/j.comcom.2022.05.035 ↗
41. Deep learning in neural networks: an overview10.1016/j.neunet.2014.09.003 ↗
42. Guaranteed approximation error estimation of neural networks and model modification10.1016/j.neunet.2022.03.023 ↗
43. An efficient improved photovoltaic irrigation system with artificial neural network based modeling of soil moisture distribution - a case study in Turkey10.1016/j.compag.2014.01.008 ↗
44. Predicting effective thermal conductivity in sands using an artificial neural network with multiscale microstructural parameters
45. Spatial soil erosion estimation using an artificial neural network (ANN) and field plot data10.1016/j.catena.2017.12.027 ↗
46. Results of application of artificial neural networks in predicting geo-mechanical properties of stabilised clays - a review10.3390/geotechnics1010008 ↗
47. Load-settlement behavior modeling of single piles using artificial neural networks and CPT data10.1016/j.compgeo.2017.04.003 ↗
48. Prediction of unconfined compressive strength of geopolymer stabilized clayey soil using artificial neural network10.1016/j.compgeo.2015.05.021 ↗
49. Surrogate models to predict maximum dry unit weight, optimum moisture content and California bearing ratio form grain size distribution curve
50. Prediction of strength and CBR characteristics of chemically stabilized coal gangue: ANN and random forest tree approach
51. Prediction of bearing capacity of stone columns placed in soft clay using ANN model10.1007/s10706-017-0436-0 ↗
52. Prediction of CBR and resilient modulus of crushed waste rocks using machine learning models10.1007/s11440-022-01472-1 ↗
53. Prediction of the California bearing ratio (CBR) of compacted soils by using GMDH-type neural network
54. Failure assessment of strength and bearing capacity on marine stabilized subgrade soil10.1007/s11668-021-01232-5 ↗
55. Application of genetic expression programming and artificial neural network for prediction of CBR10.1080/14680629.2018.1544924 ↗
56. On random subspace optimization-based hybrid computing models predicting the California bearing ratio of soils
57. Estimation of California bearing ratio by using soft computing systems10.1016/j.eswa.2010.12.054 ↗
58. Correlation of California bearing ratio (CBR) value with soil properties of road subgrade soil10.1007/s10706-018-0604-x ↗
59. Compaction behaviour and prediction of its characteristics of fine grained soils with particular reference to compaction energy10.3208/sandf.44.5_27 ↗
60. Empirical models to predict compaction parameters for soils in the State of Ceará, Northeastern Brazil
61. Correlation between gradational parameters and compaction characteristics of sandy soils10.1179/1938636213Z.00000000045 ↗
62. Correlation of maximum laboratory dry density and optimum moisture content of soil with soil parameters
63. Multiple criteria optimization (MCO): a gene selection deterministic tool in RStudio10.1371/journal.pone.0262890 ↗
64. RStudio: a platform-independent IDE for R and sweave10.1002/jae.1278 ↗
65. Data parsing in mass spectrometry imaging using R studio and cardinal: a tutorial10.1016/j.jmsacl.2021.12.007 ↗
66. Eco-friendly design of warm mix asphalt (WMA) with recycled concrete aggregate (RCA): a case study from a developing country
67. Why we need to report more than ’data were analyzed by t-tests or ANOVA’
68. Resolution of students t-tests, ANOVA and analysis of variance components from intermediary data10.11613/BM.2017.026 ↗
69. Application of student’s t-test, analysis of variance, and covariance10.4103/aca.ACA_94_19 ↗
70. Effect of grain size distribution on the maximum and minimum void ratios of granular soils10.18690/actageotechslov.17.2.26-33.2020 ↗
71. The application of Student’s t-test in internal quality control of clinical laboratory10.1016/j.flm.2017.09.002 ↗
72. Attach importance of the bootstrap t-test against Student’s t-test in clinical epidemiology: a demonstrative comparison using COVID-19 as an example
73. t-Test feature selection approach based on term frequency for text categorization10.1016/j.patrec.2014.02.013 ↗
74. An ANOVA test for parameter estimability using data cloning with application to statistical inference for dynamic systems10.1016/j.csda.2013.09.013 ↗
75. Parametric boostrap and objective Bayesian testing for heteroscedastic one-way ANOVA
76. Develop 24 dissimilar ANNs by suitable architectures & training algorithms via sensitivity analysis to better statistical presentation: measure MSEs between targets & ANN for Fe–CuO/Eg–Water nanofluid10.1016/j.physa.2018.12.031 ↗
77. A survey of deep neural network architectures and their applications10.1016/j.neucom.2016.12.038 ↗
78. Environmental optimization of warm mix asphalt (WMA) design with recycled concrete aggregates (RCA) inclusion through artificial intelligence (AI) techniques
79. Applications of artificial neural networks for refrigeration, air-conditioning and heat pump systems - a review10.1016/j.rser.2011.10.015 ↗
80. Device-independent cellular-based indoor location tracking using deep learning10.1016/j.pmcj.2021.101420 ↗
81. ANN architecture specifications for modelling of open-cell aluminum under compression10.1155/2020/2834317 ↗
82. A review on neural networks with random weights10.1016/j.neucom.2017.08.040 ↗
83. Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks10.1016/j.jsv.2016.10.043 ↗
84. Overfitting effect of artificial neural network based nonlinear equalizer: from mathematical origin to transmission evolution
85. A comparison of methods to avoid overfitting in neural networks training in the case of catchment runoff modelling10.1016/j.jhydrol.2012.10.019 ↗
86. A convergent smoothing algorithm for training max-min fuzzy neural networks10.1016/j.neucom.2017.04.046 ↗
87. Investigation of ANN architecture for predicting the compressive strength of concrete containing GGBFS10.1371/journal.pone.0260847 ↗
88. A comprehensive evaluation of random vector functional link networks10.1016/j.ins.2015.09.025 ↗
89. Kearns · 1994
90. Rethinking statistical learning theory: learning using statistical invariants10.1007/s10994-018-5742-0 ↗
91. Statistical learning theory for high dimensional prediction: application to criterion-keyed scale development10.1037/met0000088 ↗
92. Deep learning in spiking neural networks10.1016/j.neunet.2018.12.002 ↗
93. Neural network models and deep learning10.1016/j.cub.2019.02.034 ↗
94. Forecasting PM2.5 levels in Santiago de Chile using deep learning neural networks10.1016/j.uclim.2021.100906 ↗
95. Deep neural networks for texture classification - a theoretical analysis10.1016/j.neunet.2017.10.001 ↗
96. Learning viscoelasticity models from indirect data using deep neural networks10.1016/j.cma.2021.114124 ↗
97. Solving high-dimensional partial differential equations using deep learning10.1073/pnas.1718942115 ↗
98. Prediction of the local buckling strength and load‐displacement behaviour of SHS and RHS members using deep neural networks (DNN) – introduction to the deep neural network direct stiffness method (DNN‐DSM)10.1002/stco.202100047 ↗
99. Representation learning: a review and new perspectives10.1109/TPAMI.2013.50 ↗
100. An analysis of the influence of deep neural network (DNN) topology in bottleneck feature based language recognition10.1371/journal.pone.0182580 ↗