Abstract
This article introduces a novel method using the K-nearest neighbors (KNN) model to predict the unconfined compressive strength (UCS) of soil-stabilizer combinations. To ensure accurate UCS estimation, customized KNN prediction models are created. The research combines two meta-heuristic algorithms, the giant trevally optimizer (GTO) and the tunicate swarm algorithm (TSA), for improved accuracy. These algorithms examine UCS samples made from various soil types and validate the models using the results of previous stabilization tests. The study’s findings point to three distinct models: KNGT, KNTS, and an independent KNN model. Each of these models offers insightful information that helps with the precise prediction of UCS. As a result, the KNGT model performs best by displaying suitable statistics like a high R2 value of 0.995 and a low RMSE value of 84.5 (kN/m2). In addition, KNTS obtained the second suitable performance with R2 and RMSE equal to 0.989 and 121.2 (kN/m2), alternatively. These results highlight the accuracy, dependability, and prognostication capabilities of the KNGT model. This study describes a unique machine-learning approach for the exact prediction of critical soil parameters, with an emphasis on UCS in civil engineering. In order to overcome data difficulties, it leverages the KNN model and presents a novel dual-algorithm technique that combines the GTO and TSA. This integration improves KNN’s accuracy and efficiency while also easing UCS structure planning in civil engineering. The work not only improves UCS prediction accuracy but also opens up a viable route for future research and practical applications in civil engineering undertakings, giving significant insights and a fresh method for UCS performance prediction.
Similar content being viewed by others
Abbreviations
- UCS:
-
Unconfined compressive strength
- LL:
-
Liquid limit
- KNN:
-
K-nearest neighbors
- TSA:
-
Tunicate swarm algorithm
- RMSE:
-
Root mean square error
- MDAPE:
-
Median absolute percentage error
- R2:
-
Coefficient of determination
- PL:
-
Plastic limit
- PI:
-
Plasticity index
- GTO:
-
Giant trevally optimizer
- ML:
-
Machine learning
- SI:
-
Scatter index
- MSE:
-
Mean square error
References
Zhang F, O’Donnell LJ (2020) Support vector regression In: Machine learning, Elsevier, 2020, pp. 123–140
Akbulut S, Kalkan E, Celik S (2003) Artificial Neural Networks to estimate the shear strength of compacted soil samples. Int Conf New Dev Soil Mech Geotech Eng 1:285–290
Lee SJ, Lee SR, Kim YS (2003) An approach to estimate unsaturated shear strength using artificial neural network and hyperbolic formulation. Comput Geotech 30(6):489–503
Sivrikaya O, Togrol E, Komur M (2004) Determination of unconfined compressive strength by Artificial Neural Network. In: 10th national congress of soil mechanics and foundation engineering, Istanbul, Turkey
Majdi A, Rezaei M (2013) Prediction of unconfined compressive strength of rock surrounding a roadway using artificial neural network. Neural Comput Appl 23:381–389
Sathyapriya S, Arumairaj PD, Ranjini D (2017) Prediction of unconfined compressive strength of a stabilised expansive clay soil using ANN and regression analysis (SPSS). Asian J Res Soc Sci Humanit 7(2):109–123
Shah HA et al (2022) Application of machine learning techniques for predicting compressive, splitting tensile, and flexural strengths of concrete with metakaolin. Materials (Basel) 15(15):5435. https://doi.org/10.3390/ma15155435
Wang H, Lei Z, Zhang X, Zhou B, Peng J (2016) Machine learning basics. Deep Learn., pp. 98–164
Pham BT (2018) A novel classifier based on composite hyper-cubes on iterated random projections for assessment of landslide susceptibility. J Geol Soc India 91(3):355–362
Pham BT, Hoang T-A, Nguyen D-M, Bui DT (2018) Prediction of shear strength of soft soil using machine learning methods. CATENA 166:181–191
Suman S, Mahamaya M, Das SK (2016) Prediction of maximum dry density and unconfined compressive strength of cement stabilised soil using artificial intelligence techniques. Int J Geosynth Gr Eng 2:1–11
Nazir R, Momeni E, Armaghani DJ, Amin MFM (2013) Correlation between unconfined compressive strength and indirect tensile strength of limestone rock samples. Electron J Geotech Eng 18(1):1737–1746
Ceryan N, Okkan U, Kesimal A (2013) Prediction of unconfined compressive strength of carbonate rocks using artificial neural networks. Environ earth Sci 68:807–819
Ruffolo RM, Shakoor A (2009) Variability of unconfined compressive strength in relation to number of test samples. Eng Geol 108(1–2):16–23
Grima MA, Babuška R (1999) Fuzzy model for the prediction of unconfined compressive strength of rock samples. Int J rock Mech Min Sci 36(3):339–349
Yılmaz I, Sendır H (2002) Correlation of Schmidt hardness with unconfined compressive strength and Young’s modulus in gypsum from Sivas (Turkey). Eng Geol 66(3–4):211–219
Naeini SA, Naderinia B, Izadi E (2012) Unconfined compressive strength of clayey soils stabilized with waterborne polymer. KSCE J Civ Eng 16:943–949
Park S-S (2011) Unconfined compressive strength and ductility of fiber-reinforced cemented sand. Constr Build Mater 25(2):1134–1138
Ghazavi M, Roustaie M (2010) The influence of freeze–thaw cycles on the unconfined compressive strength of fiber-reinforced clay. Cold Reg Sci Technol 61(2–3):125–131
Nwaiwu CMO, Mezie EO (2021) Prediction of maximum dry unit weight and optimum moisture content for coarse-grained lateritic soils. Soils and Rocks 44:e2021054120
Kumar M, Biswas R, Kumar DR, Samui P, Kaloop MR, Eldessouki M (2023) Soft computing-based prediction models for compressive strength of concrete. Case Stud Constr Mater 19:e02321
Khajeh A, Ebrahimi SA, MolaAbasi H, Jamshidi Chenari R, Payan M (2021) Effect of EPS beads in lightening a typical zeolite and cement-treated sand. Bull Eng Geol Environ 80(11):8615–8632. https://doi.org/10.1007/s10064-021-02458-1
Kumar M, Kumar V, Rajagopal BG, Samui P, Burman A (2023) State of art soft computing based simulation models for bearing capacity of pile foundation: a comparative study of hybrid ANNs and conventional models. Model Earth Syst Environ 9(2):2533–2551. https://doi.org/10.1007/s40808-022-01637-7
Tavana Amlashi A, Mohammadi Golafshani E, Ebrahimi SA, Behnood A (2023) Estimation of the compressive strength of green concretes containing rice husk ash: a comparison of different machine learning approaches. Eur J Environ Civ Eng 27(2):961–983. https://doi.org/10.1080/19648189.2022.2068657
Behnam Sedaghat, Tejani GG, Kumar S (2023) Predict the maximum dry density of soil based on individual and hybrid methods of machine learning. Adv Eng Intell Syst 2(3) https://doi.org/10.22034/aeis.2023.414188.1129.
Farooq K, Khalid U, Mujtaba H (2016) Prediction of compaction characteristics of fine-grained soils using consistency limits. Arab J Sci Eng 41:1319–1328
Riahi-Madvar H, Gholami M, Gharabaghi B, Morteza Seyedian S (2021) A predictive equation for residual strength using a hybrid of subset selection of maximum dissimilarity method with Pareto optimal multi-gene genetic programming. Geosci Front 12(5):101222. https://doi.org/10.1016/j.gsf.2021.101222
Akbarzadeh MR, Ghafourian H, Anvari A, Pourhanasa R, Nehdi ML (2023) Estimating compressive strength of concrete using neural electromagnetic field optimization. Materials (Basel) 16(11):4200
Hoque MI, Hasan M, Islam MS, Houda M, Abdallah M, Sobuz MHR (2023) Machine learning methods to predict and analyse unconfined compressive strength of stabilised soft soil with polypropylene columns. Cogent Eng 10(1):2220492. https://doi.org/10.1080/23311916.2023.2220492
Kumar M, Biswas R, Kumar DR, Pradeep T, Samui P (2022) Metaheuristic models for the prediction of bearing capacity of pile foundation. Geomech Eng 31(2):129
Biswas R et al (2023) A novel integrated approach of RUNge Kutta optimizer and ANN for estimating compressive strength of self-compacting concrete. Case Stud Constr Mater 18:e02163
Taffese WZ, Abegaz KA (2022) Prediction of compaction and strength properties of amended soil using machine learning. Buildings 12(5):613
Xiong L, Yao Y (2021) Study on an adaptive thermal comfort model with K-nearest-neighbors (KNN) algorithm. Build Environ 202:108026
Abu Alfeilat HA et al (2019) Effects of distance measure choice on k-nearest neighbor classifier performance: a review. Big data 7(4):221–248
Uddin S, Haque I, Lu H, Moni MA, Gide E (2022) Comparative performance analysis of K-nearest neighbour (KNN) algorithm and its different variants for disease prediction. Sci Rep 12(1):6256
Sadeeq HT, Abdulazeez AM (2022) Giant trevally optimizer (GTO): a novel metaheuristic algorithm for global optimization and challenging engineering problems. IEEE Access 10:121615–121640
Kaur S, Awasthi LK, Sangal AL, Dhiman G (2020) Tunicate swarm algorithm: a new bio-inspired based metaheuristic paradigm for global optimization. Eng Appl Artif Intell 90:103541
Sharma A, Dasgotra A, Tiwari SK, Sharma A, Jately V, Azzopardi B (2021) Parameter extraction of photovoltaic module using tunicate swarm algorithm. Electronics 10(8):878
Kumar M, Samui P (2022) Reliability analysis of pile foundation using GMDH, GP and MARS BT-CIGOS 2021, Emerging Technologies and Applications for Green Infrastructure. 2022, pp. 1151–1159
Kumar M, Tn DS (2023) Genetic programming based compressive strength prediction model for green concrete. Mater Today Proc. https://doi.org/10.1016/j.matpr.2023.03.024
Sharma LK, Singh TN (2018) Regression-based models for the prediction of unconfined compressive strength of artificially structured soil. Eng Comput 34(1):175–186. https://doi.org/10.1007/s00366-017-0528-8
Kumar M, Fathima NZ, Kumar DR (2024) A novel XGBoost and RF-based metaheuristic models for concrete compression strength BT-sustainable innovations in construction management pp. 495–503
Funding
No funding.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing of interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
Test Dataset | ||||||
---|---|---|---|---|---|---|
Soil (%) | Cement (%) | Lime (%) | LL (%) | PL (%) | PI (%) | UCS (kN/m2) |
94 | 2 | 4 | 45 | 26 | 19 | 2450 |
94 | 2 | 4 | 27 | 16 | 11 | 2050 |
94 | 2 | 4 | 23 | 22 | 1 | 1100 |
94 | 2 | 4 | 89 | 19 | 70 | 1400 |
94 | 6 | 0 | 55 | 20 | 35 | 1200 |
96 | 0 | 4 | 31.78 | 21 | 10.78 | 1154 |
70 | 30 | 0 | 57 | 41.5 | 15.5 | 2076.95 |
94 | 2 | 4 | 50 | 15 | 35 | 3000 |
94 | 4 | 2 | 24 | 21 | 3 | 2300 |
94 | 6 | 0 | 55 | 23 | 32 | 1570 |
90 | 6 | 4 | 23 | 18 | 5 | 2900 |
96 | 4 | 0 | 35 | 27 | 8 | 4200 |
94 | 4 | 2 | 40 | 18 | 22 | 2990 |
92 | 6 | 2 | 37 | 16 | 21 | 4900 |
94 | 6 | 0 | 42 | 23 | 19 | 2300 |
92 | 4 | 4 | 46 | 16 | 30 | 1820 |
94 | 4 | 2 | 38 | 17 | 21 | 2300 |
94 | 0 | 6 | 66 | 24 | 42 | 1250 |
94 | 4 | 2 | 35 | 29 | 6 | 3210 |
85 | 15 | 0 | 49 | 40.7 | 8.3 | 2545.81 |
95 | 0 | 5 | 31 | 14 | 17 | 3900 |
95 | 5 | 0 | 32 | 24 | 8 | 2150 |
94 | 6 | 0 | 55 | 30 | 25 | 3300 |
92 | 2 | 6 | 40 | 20 | 20 | 1610 |
92 | 2 | 6 | 45 | 26 | 19 | 2450 |
96 | 0 | 4 | 30 | 18 | 12 | 3000 |
94 | 6 | 0 | 29 | 14 | 15 | 2200 |
94 | 6 | 0 | 35 | 21 | 14 | 2270 |
96 | 4 | 0 | 24 | 20 | 4 | 4100 |
70 | 0 | 30 | 38.4 | 32 | 6.4 | 461.89 |
70 | 30 | 0 | 39 | 32.2 | 6.8 | 3297 |
94 | 0 | 6 | 80 | 58 | 22 | 180 |
94 | 6 | 0 | 44 | 22 | 22 | 3200 |
94 | 6 | 0 | 51 | 25 | 26 | 4020 |
94 | 4 | 2 | 19 | 14 | 5 | 2540 |
96 | 4 | 0 | 21 | 17 | 4 | 4700 |
94 | 6 | 0 | 45 | 12 | 33 | 1980 |
94 | 0 | 6 | 33 | 12 | 21 | 2450 |
94 | 6 | 0 | 25 | 21 | 4 | 4100 |
94 | 6 | 0 | 25 | 12 | 13 | 2700 |
94 | 6 | 0 | 35 | 15 | 20 | 2300 |
94 | 4 | 2 | 32 | 13 | 19 | 1980 |
93 | 7 | 0 | 48 | 40.3 | 7.7 | 609.97 |
94 | 6 | 0 | 36.4 | 19 | 17.4 | 2020 |
94 | 4 | 2 | 72 | 23 | 49 | 1300 |
94 | 6 | 0 | 18 | 14 | 4 | 4400 |
91 | 0 | 9 | 54 | 32 | 22 | 1930 |
94 | 4 | 2 | 29 | 16 | 13 | 2000 |
94 | 0 | 6 | 29 | 18 | 11 | 4600 |
95 | 5 | 0 | 23 | 18 | 5 | 3100 |
97 | 3 | 0 | 18 | 14 | 4 | 4400 |
94 | 6 | 0 | 29 | 22 | 7 | 3250 |
94 | 4 | 2 | 45 | 26 | 19 | 1750 |
92 | 4 | 4 | 32 | 17 | 15 | 3100 |
94 | 6 | 0 | 40 | 20 | 20 | 1610 |
95 | 5 | 0 | 25 | 21 | 4 | 4100 |
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhao, Q., Shi, Y. Prediction of Unconfined Compressive Strength of Stabilized Sand Using Machine Learning Methods. Indian Geotech J (2024). https://doi.org/10.1007/s40098-024-00924-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s40098-024-00924-7