Predicting Optimum Moisture Content by the individual and hybrid approach of machine learning

Yinghui  Yang; Yahui  Dai; Qunting  Yang

doi:10.6180/jase.202508_28(8).0004

Predicting Optimum Moisture Content by the individual and hybrid approach of machine learning

Computer Science and Information Engineering

Yinghui Yang¹This email address is being protected from spambots. You need JavaScript enabled to view it., Yahui Dai², and Qunting Yang³

¹College of Information and Engineering, Henan University of Animal Husbandry and Economy; Zhengzhou Henan, 450045, China

²Science and Technology Research Institute of State Power Investment Group Co., LTD. Beijing,102209, China

³College of Air Traffic Management, Civil Aviation University of China; Tianjin, 300300, China

Received: June 23, 2024
Accepted: September 19, 2024
Publication Date: October 26, 2024

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202508_28(8).0004

The Optimal Moisture Content (OMC) is the moisture level at which soil reaches its maximum density during compaction, making it vital in geotechnical engineering and construction for establishing the best conditions for soil strength and stability in infrastructure. Existing methods to determine OMC are both expensive and time-intensive. Machine learning offers a promising alternative by enabling the creation of advanced predictive models and algorithms that can improve the accuracy and efficiency of OMC predictions compared to traditional empirical methods. This study aims to develop an advanced framework utilizing the Gaussian Process Regression (GPR) model for predicting OMC. The research demonstrates a strong relationship using GPR models between OMC and important soil parameters such as particle size distribution, linear shrinkage, and the kind and quantity of stabilizing chemicals. To further enhance the predictive accuracy of these models, two meta-heuristic optimization techniques—Atom Search Optimization (ASO) and Reptile Search Algorithm (RSA)—are employed. The study presents three distinct models—GPAS, GPRS, and a standalone GPR model—each providing critical insights for accurate OMC prediction. Among these, the GPAS model demonstrates superior performance, achieving an outstanding R² score of 0.992 and a notably low RMSE of 0.719. These results underscore the GPAS model’s exceptional reliability, precision, and its robust capability in forecasting the outcomes of soil stabilization efforts. Efficient OMC prediction helps in reducing the overuse of stabilizing additives and water, leading to more sustainable construction practices. It also minimizes the environmental impact associated with soil excavation and modification.

Keywords: Machine Learning, Gaussian Process Regression, Metaheuristic Algorithms, Optimum Moisture Content, Artificial Intelligence

[1] M. Selvam and S. Singh, (2023) “Influence of compaction methods on the optimum moisture content and performance of roller compacted concrete pavements" Journal of Materials in Civil Engineering 35(7): 04023176.
[2] A. Bryan, (1988) “Criteria for the suitability of soil for cement stabilization" Building and Environment 23(4): 309–319.
[3] D. Osula, (1996) “A comparative evaluation of cement and lime modification of laterite" Engineering geology 42(1): 71–81.
[4] A. Alavi, A. Gandomi, M. Gandomi, and S. Sadat Hosseini, (2009) “Prediction of maximum dry density and optimum moisture content of stabilised soil using RBF neural networks" The IES Journal Part A: Civil & Structural Engineering 2(2): 98–106.
[5] A. Sridharan and H. Nagaraj, (2005) “Plastic limit and compaction characteristics of finegrained soils" Proceedings of the institution of civil engineers-ground improvement 9(1): 17–22.
[6] A. Bera and A. Ghosh, (2011) “Regression model for prediction of optimum moisture content and maximum dry unit weight of fine grained soil" International Journal of Geotechnical Engineering 5(3): 297–305.
[7] H. F. Hama Ali, (2023) “Utilizing multivariable mathematical models to predict maximum dry density and optimum moisture content from physical soil properties" Multiscale and Multidisciplinary Modeling, Experiments and Design 6(4): 603–627.
[8] J. Khatti and K. S. Grover, (2023) “Assessment of fine-grained soil compaction parameters using advanced soft computing techniques" Arabian Journal of Geosciences 16(3): 208.
[9] K. Farooq, U. Khalid, and H. Mujtaba, (2016) “Prediction of compaction characteristics of fine-grained soils using consistency limits" Arabian Journal for Science and Engineering 41: 1319–1328.
[10] G. G. Tejani, B. Sadaghat, and S. Kumar, (2023) “Predict the maximum dry density of soil based on individual and hybrid methods of machine learning" Advances in engineering and intelligence systems 2(03): 98–109.
[11] H. A. Shah, Q. Yuan, U. Akmal, S. A. Shah, A. Salmi, Y. A. Awad, L. A. Shah, Y. Iftikhar, M. H. Javed, and M. I. Khan, (2022) “Application of machine learning techniques for predicting compressive, splitting tensile, and flexural strengths of concrete with metakaolin" Materials 15(15): 5435.
[12] H. Wang, Z. Lei, X. Zhang, B. Zhou, and J. Peng, (2016) “Machine learning basics" Deep learning: 98– 164.
[13] B. T. Pham, (2018) “A novel classifier based on composite hyper-cubes on iterated random projections for assessment of landslide susceptibility" Journal of the Geological Society of India 91(3): 355–362.
[14] B. T. Pham, T.-A. Hoang, D.-M. Nguyen, D. T. Bui, et al., (2018) “Prediction of shear strength of soft soil using machine learning methods" Catena 166: 181–191.
[15] J. Woodward. An introduction to geotechnical processes. CRC Press, 2004.
[16] C. M. Nwaiwu and E. O. Mezie, (2021) “Prediction of maximum dry unit weight and optimum moisture content for coarse-grained lateritic soils" Soils and Rocks 44(1): e2021054120.
[17] A. Rassoul and K. Mojtaba, (2015) “Predicting maximum dry density, optimum moisture content and California bearing ratio (CBR) through soil index using ordinary least squares (OLS) and artificial neural networks (ANNS)" International Journal of Innovative Technology and Exploring Engineering 5(3): 1–5.
[18] J. Sani, P. Yohanna, K. Etim, J. Osinubi, and O. Eberemu, (2017) “Reliability evaluation of optimum moisture content of tropical black clay treated with locust bean waste ash as road pavement sub-base material" Geotechnical and Geological Engineering 35: 2421–2431.
[19] A. H. Alavi, A. H. Gandomi, and A. Mollahasani, (2012) “A genetic programming-based approach for the performance characteristics assessment of stabilized soil" Variants of evolutionary algorithms for real-world applications: 343–376.
[20] B. M. Das and K. Sobhan. Principles of geotechnical engineering. PWS-Kent Publishing Company Boston, 1990.
[21] M. Nguyen Duc, A. Ho Sy, T. Nguyen Ngoc, and T. L. Hoang Thi. “An artificial intelligence approach based on multi-layer perceptron neural network and random forest for predicting maximum dry density and optimum moisture content of soil material in quang Ninh Province, Vietnam”. In: CIGOS 2021, Emerging Technologies and Applications for Green Infrastructure: Proceedings of the 6th International Conference on Geotechnics, Civil Engineering and Structures. Springer. 2022, 1745–1754.
[22] E. Akpokodje, (1985) “The stabilization of some arid zone soils with cement and lime" Quarterly Journal of Engineering Geology and Hydrogeology 18(2): 173–180.
[23] A. Hossein Alavi, A. Hossein Gandomi, A. Mollahassani, A. Akbar Heshmati, and A. Rashed, (2010) “Modeling of maximum dry density and optimum moisture content of stabilized soil using artificial neural networks" Journal of Plant Nutrition and Soil Science 173(3): 368–379.
[24] C. KS, Y. Chew, M. Osman, and M. G. SK. “Estimating maximum dry density and optimum moisture content of compacted soils”. In: international conference on advances in civil and environmental engineering. 2015, 1–8.
[25] W. Z. Taffese and K. A. Abegaz, (2022) “Prediction of compaction and strength properties of amended soil using machine learning" Buildings 12(5): 613.
[26] S. K. Das, P. Samui, and A. K. Sabat, (2011) “Application of artificial intelligence to maximum dry density and unconfined compressive strength of cement stabilized soil" Geotechnical and Geological Engineering 29: 329–342.
[27] S. Suman, M. Mahamaya, and S. K. Das, (2016) “Prediction of maximum dry density and unconfined compressive strength of cement stabilised soil using artificial intelligence techniques" International Journal of Geosynthetics and Ground Engineering 2: 1–11.
[28] P. Mehdipour, I. Navidi, M. Parsaeian, Y. Mohammadi, L. M. MORADI, D. E. REZAEI, K. Nourijelyani, and F. Farzadfar, (2014) “Application of Gaussian Process Regression (GPR) in estimating under-five mortality levels and trends in Iran 1990-2013, study protocol" Archives of Iranian Medicine:
[29] C. Rasmussen and C. Williams, (2005) “Gaussian processes for machine learning (adaptive computation and machine learning) the mit press" Cambridge, MA, USA: 69–106.
[30] B. Wang and T. Chen, (2015) “Gaussian process regression with multiple response variables" Chemometrics and Intelligent Laboratory Systems 142: 159–165.
[31] L.-L. Li, Y.-B. Chang, M.-L. Tseng, J.-Q. Liu, and M. K. Lim, (2020) “Wind power prediction using a novel model on wavelet decomposition-support vector machinesimproved atomic search algorithm" Journal of Cleaner Production 270: 121817.
[32] J. Too and A. R. Abdullah, (2020) “Chaotic atom search optimization for feature selection" Arabian Journal for Science and Engineering 45(8): 6063–6079.
[33] W. Zhao, L. Wang, and Z. Zhang, (2019) “A novel atom search optimization for dispersion coefficient estimation in groundwater" Future Generation Computer Systems 91: 601–610.
[34] L. Abualigah, M. Abd Elaziz, P. Sumari, Z. W. Geem, and A. H. Gandomi, (2022) “Reptile Search Algorithm (RSA): A nature-inspired meta-heuristic optimizer" Expert Systems with Applications 191: 116158.
[35] J. Yao, Y. Zhang, X. Liang, and T. Ding, (2024) “Investigating the estimation of optimum moisture content through support vector regression in individual and hybrid approaches" Multiscale and Multidisciplinary Modeling, Experiments and Design: 1–13.
[36] A. Hossein Alavi, A. Hossein Gandomi, A. Mollahassani, A. Akbar Heshmati, and A. Rashed, (2010) “Modeling of maximum dry density and optimum moisture content of stabilized soil using artificial neural networks" Journal of Plant Nutrition and Soil Science 173(3): 368–379.
[37] M. Nguyen Duc, A. Ho Sy, T. Nguyen Ngoc, and T. L. Hoang Thi. “An artificial intelligence approach based on multi-layer perceptron neural network and random forest for predicting maximum dry density and optimum moisture content of soil material in quang Ninh Province, Vietnam”. In: CIGOS 2021, Emerging Technologies and Applications for Green Infrastructure: Proceedings of the 6th International Conference on Geotechnics, Civil Engineering and Structures. Springer. 2022, 1745–1754.
[38] J. Zhang and P. Du, (2024) “Hybrid and individual least square support vector regression methods for estimating the optimal moisture content of stabilized soil" Multiscale and Multidisciplinary Modeling, Experiments and Design: 1–15.