Machine Learning Estimation of the Unit Weight of Organic Soils
Source abstract
Abstract
The aim of this study is to search for and verify regression models of selected geotechnical parameters of organic soils that are useful in engineering practices. Various machine learning methodologies were employed, including decision tree, ensembles of trees, support vector regression, Gaussian process, and neural networks. The work was based on two qualitatively different examples of estimating the unit weight of soil (γt). In the first example, the results of cone penetration test (CPT) probing (cone resistance qc and friction resistance fs) were used. In the second example, the results of laboratory tests of other physical properties of these soils (content of organic parts LOIT and moisture content w) were used. The task was completed for 135 sets of test results, which were carried out at the Rzeszów training ground in Poland with in situ tests using the CPT probe and laboratory tests. A statistical analysis was carried out to initially determine the relationships between the variables. This work presents the results of a comparison of multiple linear regression models with regression models obtained using the machine learning (ML) method. The studies obtained ML models with mean absolute percentage errors (MAPE) that were smaller than those of statistical models. Consequently, for the CPT sounding data, the MAPE changed from 13.57% to 7.37%, and, for the second data set, from 7.87% to 1.25%. Software STATISTICA version 13.3 and the Regression Learner TM library from MATLAB R2024b were used to analyze the soil data.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Soil Geostatistics and Mapping · Image Processing and 3D Reconstruction · Soil and Unsaturated Flow
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Structural Mechanics, Faculty of Civil and Environmental Engineering and Architecture, Rzeszow University of Technology, Powstanców Warszawy 12 Av., 35-959 Rzeszow, Poland
Department of Geodesy and Geotechnics, Faculty of Civil and Environmental Engineering and Architecture, Rzeszow University of Technology, Powstanców Warszawy 12 Av., 35-959 Rzeszow, Poland
Department of Geotechnics, Roads and Geodesy, Faculty of Civil Engineering and Environmental Sciences, Bialystok University of Technology, Wiejska 45E Str., 15-351 Bialystok, Poland
Funding
Ministry of Science and Higher Education, Republic of Poland
References (49)
Show source-provided references
1. Gilbert, P.A. (1992). Effect of Sampling Disturbance on Laboratory-Measured Soil Properties, U.S. Army Engineer Waterways Experiment Station.
2. Mayne, P.W., Peuchen, J., and Bouwmeester, D. (2010, January 9–11). Soil unit weight estimation from CPTs. Proceedings of the 2rd International Symposium on Cone Penetration Testing, Huntington Beach, CA, USA.
3. Robertson, P., and Cabal, K. (2010, January 9–11). Estimating soil unit weight from CPT. Proceedings of the 2nd International Symposium on Cone Penetration Testing, Huntington Beach, CA, USA.
4. CPTU and DMT for estimating soil unit weight of Lake Bonneville Clay
5. Młynarek, Z., and Wierzbicki, J. (2014). Unit weight estimation from CPT for Indian offshore soft calcareous clay. CPTU and DMT in Soft Clays and Organic Soils, Exlemplum Press.
6. Kovacevic, M.S., Gavin, K.G., Reale, C., and Libric, L. (2018, January 21–22). The use of neural networks to develop CPT correlations for soils in northern Croatia. Proceedings of the 4th International Symposium on Cone Penetration Testing (CPT’18), Delft, The Netherlands.
7. Lengkeek, H.J., de Greef, J., and Joosten, S. (2018, January 21–22). CPT based unit weight estimation extended to soft organic soils and peat. Proceedings of the 4th International Symposium on Cone Penetration Testing (CPT’18), Delft, The Netherlands.
8. Lengkeek, H.J., and Brinkgreve, R.B.J. (2022). CPT-based unit weight estimation extended to soft organic clays and peat: An update. Cone Penetration Testing 2022, CRC Press.10.1201/9781003308829-71 ↗
9. Bishop, C.M., Bishop, H., and Cham, S. (2023). Deep Learning—Foundations and Concepts, Springer Nature.10.1007/978-3-031-45468-4 ↗
10. Deka, P.C. (2019). A Primer on Machine Learning Applications in Civil Engineering, CRC Press.10.1201/9780429451423 ↗
11. Transforming Civil Engineering with AI and Machine Learning: Innovations, Applications, and Future Directions10.55248/gengpi.6.0125.0528 ↗
12. Mobasheri, F., Hosseinpoor, M., Yahia, A., and Pourkamali-Anaraki, F. (2025). Machine Learning as an Innovative Engineering Tool for Controlling Concrete Performance: A Comprehensive Review. Arch. Comput. Methods Eng., 1–45.10.1007/s11831-025-10284-x ↗
13. 35 Years of (AI) in Geotechnical Engineering: State of the Art10.1007/s10706-020-01536-7 ↗
14. Machine learning and soil sciences: A review aided by machine learning tools10.5194/soil-6-35-2020 ↗
15. State-of-the-art review on the use of AI-enhanced computational mechanics in geotechnical engineering10.1007/s10462-024-10836-w ↗
16. Rauter, S., and Tschuchnigg, F. (2021). CPT Data Interpretation Employing Different Machine Learning Techniques. Geosciences, 11.10.3390/geosciences11070265 ↗
17. Machine Learning Models to Evaluate the Load-Settlement Behavior of Piles from Cone Penetration Test Data10.1007/s10706-023-02737-6 ↗
18. A practical approach for soil unit weight estimation using artificial neural networks10.1016/j.jsames.2023.104648 ↗
19. Use of CPT and other parameters for estimating soil unit weight using optimized machine learning models10.1007/s12145-025-01756-6 ↗
20. Lechowicz, Z., and Sulewska, M.J. (2023). Assessment of the Undrained Shear Strength and Settlement of Organic Soils under Embankment Loading Using Artificial Neural Networks. Materials, 16.10.3390/ma16010125 ↗
21. Yousefpour, N., Medina-Cetina, Z., Hernandez-Martinez, F.G., and Al-Tabbaa, A. (2021). Stiffness and Strength of Stabilized Organic Soils—Part II/II: Parametric Analysis and Modeling with Machine Learning. Geosciences, 11.10.3390/geosciences11050218 ↗
22. Machine Learning–Based Organic Soil Classification Using Cone Penetrometer Tests10.1061/JGGEFK.GTENG-12322 ↗
23. Czudec, G., and Bulanda, J. (2010). Geological and Engineering Geological Conditions for Recognition—Engineering for the Construction of Multi-Storey Building at Witolda Street in Rzeszów, Department of Geological Services Design and Construction and the Environment.
24. Identification of local organic soils based on cone penetration test results
25. (2002). Geotechnics. Field Studies. Standard No. PN-B-04452:2002.
26. (2008). Eurocode 7: Geotechnical Design—Part 1: General Rules. Standard No. EN 1997-1: 2008.
27. (2009). Eurocode 7: Geotechnical Design—Part 2: Ground Investigation and Testing. Standard No. EN 1997-2: 2009/10.
28. (2009). Geotechnical Investigation and Testing—Field Testing—Part 12: Mechanical Cone Penetration Test. Standard No. PN-EN ISO 22476-12:2009.
29. (2023). Geotechnical investigation and Testing—Field Testing—Part 1: Electrical Cone and Piezocone Penetration Test. Standard No. PN-EN ISO 22476-1:2023-06.
30. (1988). Building Soils. Laboratory Tests. Standard No. PN-B-04481: 1988.
31. (1986). Building Soils. Terms, Symbols, Division and Description of Soil. Standard No. PN-B-02480: 1986.
32. (2018). Geotechnical Investigation and Testing. Identification and Classification of Soil. Part 1: Identification and Description. Standard No. PN-EN ISO 14688-2: 2018-05.
33. (2018). Geotechnical Investigation and Testing. Identification and Classification of Soil. Part 2: Principles for a Classification. Standard No. PN-EN ISO 14688-1: 2018-05.
34. (2015). Geotechnical Investigation and Testing—Laboratory Testing of Soil—Part 1: Determination of Water Content. Standard No. PN-EN ISO 17892-1: 2015.
35. Verification of standard guidelines for organic matter content determination in organic soils by the loss on ignition method
36. Loss on ignition as a method for estimating organic and carbonate content in sediments: Reproducibility and comparability of results10.1023/A:1008119611481 ↗
37. (2014). Geotechnical Investigation and Testing—Laboratory Testing of Soil—Part 2: Determination of Bulk Density. Standard No. PN-EN ISO 17892-2:2014.
38. Evaluation of the unit weight of organic soils from a CPTM using an Artificial Neural Networks
39. Straż, G., and Borowiec, A. (2020). Estimating the unit weight of local organic soils from laboratory tests using artificial neural networks. Appl. Sci., 10.10.3390/app10072261 ↗
40. Stanisz, A. (2006). An Accessible Course in Statistics Using STATISTICA PL with Examples from Medicine. Basic Statistics, StatSoft.
41. Stanisz, A. (2007). An Accessible Course in Statistics Using STATISTICA PL with Examples from Medicine. Basic Statistics, StatSoft.
42. TIBCO Software Inc. (2025, August 06). Statistica (Data Analysis Software System), v. 13. Available online: https://docs.tibco.com/pub/stat/tibco-statistica-13-3-0_documentation.zip.
43. (2024, December 13). MathWorks: MATLAB Documentation (R2024b). Available online: https://ww2.mathworks.cn/products/new_products/release2024b.html.
44. Practical Bayesian Optimization of Machine Learning Algorithms
45. Breiman, L., Friedman, J.H., Olshen, R.A., and Stone, C.J. (1984). Classification and Regression Trees, CRC Press.
46. Bagging Predictors10.1023/A:1018054314350 ↗
47. A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting10.1006/jcss.1997.1504 ↗
48. Vapnik, N.V. (1995). The Nature of Statistical Learning Theory, Springer.10.1007/978-1-4757-2440-0 ↗
49. Rasmussen, C.E., and Williams, C.K.I. (2006). Gaussian Processes for Machine Learning, MIT Press.10.7551/mitpress/3206.001.0001 ↗