Abstract
Particle classification is essential for geotechnical engineering practice since particle shapes correlate with the mechanical and hydraulic properties of sand layers. Traditional shape classification is tedious, subjective, and time-consuming because it depends on manual visual comparison with reference particles. This study demonstrates the feasibility of employing machine learning algorithms for sand classification. Machine learning (ML) models are increasingly being introduced for automatic identification and classification of various objects. Nine types of sand were selected, and the analysis was based on 2000 binary images of each sand that were obtained from dynamic image analysis (DIA). Each particle was represented by six engineering size and four shape descriptors. The efficacy of seven ML models for automatically classifying individual sand particles was explored. The study demonstrates that the size and shape descriptors are efficient and robust to identify up to 75% of sand particles, using a neural network classifier. In addition, use of scale-invariant feature transform (SIFT) features was also explored to permit future generalization of sand classification using image datasets containing images with different scales and resolutions. Adding SIFT to size and shape can increase classification accuracy to 83% using a random forest classifier. The analysis also reveals that histograms of orientation gradients of SIFT keypoints in sand appear well correlated with sphericity and convexity of particles. This study suggests that a dataset of 2000 particles per sand is sufficient for optimal classification performance and that image preprocessing of DIA images was not necessary.
Similar content being viewed by others
Availability of data and material
All images used are proprietary to the authors, and they can be made available upon reasonable request.
Code availability
All the python scripts used are proprietary to the authors and are not available online.
References
Abdi H, Williams LJ (2010) Principal component analysis. Wiley Interdiscip Rev Comput Stat 2(4):433–459
Abraham S, Huynh C, Vu H (2020) Classification of soils into hydrologic groups using machine learning. Data 5(1):2
ASTM International. D6913/D6913M-17 (2017) Standard test methods for particle-size distribution (gradation) of soils using sieve analysis. ASTM International, West Conshohocken. https://doi.org/10.1520/D6913_D6913M-17
Azhar R, Tuwohingide D, Kamudi D, Suciati N (2015) Batik image classification using SIFT feature extraction, bag of features and support vector machine. Proc Comput Sci 72:24–30
Beemer RD, Bandini-Maeder AN, Shaw J, Lebrec U, Cassidy MJ (2018) The granular structure of two marine carbonate sediments. In: ASME 2018 37th international conference on ocean, offshore and arctic engineering. American Society of Mechanical Engineers Digital Collection
Beemer RD, Sadekov A, Lebrec U, Shaw J, Bandini-Maeder AN, Cassidy MJ (2019) Impact of biology on particle crushing in offshore calcareous sediments. In: GeoCongress 2019. American Society of Civil Engineers, Philadelphia. https://doi.org/10.1061/9780784482124.065
Beemer RD, Bandini-Maeder A, Shaw J, Cassidy MJ (2020) Volumetric particle size distribution and variable granular density soils. Geotech Test J 43(2):20180286
Bergen KJ, Johnson PA, Maarten V, Beroza GC (2019) Machine learning for data-driven discovery in solid Earth geoscience. Science 363(6433)
Bhattacharya B, Solomatine DP (2006) Machine learning in soil classification. Neural Netw 19(2):186–195
Carey C, Boucher T, Mahadevan S, Bartholomew P, Dyar MD (2015) Machine learning tools for mineral recognition and classification from Raman spectroscopy. J Raman Spectrosc 46(10):894–903
Cho GC, Dodds J, Santamarina JC (2006) Particle shape effects on packing density, stiffness, and strength: natural and crushed sands. J Geotech Geoenviron Eng 132(5):591–602
Cracknell MJ, Reading AM (2014) Geological mapping using remote sensing data: a comparison of five machine learning algorithms, their response to variations in the spatial distribution of training data and the use of explicit spatial information. Comput Geosci 63:22–33
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05), vol 1. IEEE, pp 886–893
Demars KR (1982) Unique engineering properties and compression behavior of deep-sea calcareous sediments. In: Geotechnical properties, behavior, and performance of calcareous soils. ASTM International
Deng Y, Yilmaz Y, Gokce A, Chang CS (2021) Influence of particle size on the drained shear behavior of a dense fluvial sand. Acta Geotech 1–18
Friedl MA, Brodley CE (1997) Decision tree classification of land cover from remotely sensed data. Remote Sens Environ 61(3):399–409
Fushiki T (2011) Estimation of prediction error by using K-fold cross-validation. Stat Comput 21(2):137–146
Guo D, Chen H, Tang L, Chen Z, Samui P (2021) Assessment of rockburst risk using multivariate adaptive regression splines and deep forest model. Acta Geotech
Guo G, Wang H, Bell D, Bi Y, Greer K (2003) KNN model-based approach in classification. In: OTM confederated international conferences “on the move to meaningful internet systems”. Springer, Berlin, pp 986–996
Hao H, Guo R, Gu Q, Hu X (2019) Machine learning application to automatically classify heavy minerals in river sand by using SEM/EDS data. Miner Eng 143:105899
Hartigan JA, Wong MA (1979) Algorithm AS 136: a k-means clustering algorithm. J R Stat Soc Ser C Appl Stat 28(1):100–108
Hryciw RD, Zheng J, Shetler K (2016) Particle roundness and sphericity from images of assemblies by chart estimates and computer methods. J Geotech Geoenviron Eng 142(9):04016038
Kim Y, Suh HS, Yun TS (2019) Reliability and applicability of the Krumbein–Sloss chart for estimating geomechanical properties in sands. Eng Geol 248:117–123
Kim Y, Yun TS (2021) How to classify sand types: a deep learning approach. Eng Geol 288:106142
Krumbein WC, Sloss LL (1951) Stratigraphy and sedimentation. Soil Sci 71(5):401
Kuo C-Y, Freeman R (2000) Imaging indices for quantification of shape, angularity, and surface texture of aggregates. Transp Res Rec J Transp Res Board 1721:57–65
Li L, Beemer RD, Iskander M (2021) Granulometry of two marine calcareous sands. J Geotech Geoenviron Eng 147(3):04020171
Li L, Iskander M (2019) Evaluation of dynamic image analysis for characterizing granular soils. Geotech Test J 43(5):1149–1173
Li L, Iskander M (2021) Comparison of 2D and 3D dynamic image analysis for characterization of natural sands. Eng Geol 290:106052
Li L, Iskander M (2021) Evaluation of roundness parameters in use for sand. J Geotech Geoenviron Eng 147(9):04021081
Li N, Hao H, Jiang Z, Jiang F, Guo R, Gu Q, Hu X (2020) A multi-task multi-class learning method for automatic identification of heavy minerals from river sand. Comput Geosci 135:104403
Li L, Sun Q, Iskander M (2021) Efficacy of 3D dynamic image analysis for characterizing the morphology of natural sands. Géotechnique. https://doi.org/10.1680/jgeot.21.00128
Liu Z, Gilbert G, Cepeda JM, Lysdahl AOK, Piciullo L, Hefre H, Lacasse S (2021) Modelling of shallow landslides with machine learning algorithms. Geosci Front 12(1):385–393
Lou XW, Huang DC, Fan LM, Xu AJ (2014) An image classification algorithm based on bag of visual words and multi-kernel learning. J Multimed 9(2):269
Lowe D (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110
Machairas NP, Iskander MG (2018) An investigation of pile design utilizing advanced data analytics. In: IFCEE 2018, pp 132–141
Machairas N, Li L, Iskander M (2020) Application of dynamic image analysis to sand particle classification using deep learning. In: Geo-congress 2020: modeling, geomaterials, and site characterization. American Society of Civil Engineers, Reston, pp 612–621
Maitre J, Bouchard K, Bédard LP (2019) Mineral grains recognition using computer vision and machine learning. Comput Geosci 130:84–93
McCoy JT, Auret L (2019) Machine learning applications in minerals processing: a review. Miner Eng 132:95–109
Mohri M, Rostamizadeh A, Talwalkar A (2018) Foundations of machine learning. MIT Press, Cambridge
Mora CF, Kwan AKH (2000) Sphericity, shape factor, and convexity measurement of coarse aggregate for concrete using digital image processing. Cem Concr Res 30(3):351–358
Ontivero-Ortega M, Lage-Castellanos A, Valente G, Goebel R, Valdes-Sosa M (2017) Fast Gaussian Naïve Bayes for searchlight classification analysis. Neuroimage 163:471–479
Pal M (2005) Random forest classifier for remote sensing classification. Int J Remote Sens 26(1):217–222
Patel HH, Prajapati P (2018) Study and analysis of decision tree based classification algorithms. Int J Comput Sci Eng 6(10):74–78
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Vanderplas J (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825–2830
Rey-Otero I, Morel JM, Delbracio M (2014) An analysis of scale-space sampling in SIFT. In: 2014 IEEE international conference on image processing (ICIP). IEEE, pp 4847–4851
Semple RM (1988) The mechanical properties of carbonate soils. In: International conference on calcareous sediments, pp 807–836
Shahin MA, Jaksa MB, Maier HR (2001) Artificial neural network applications in geotechnical engineering. Aust Geomech 36(1):49–62
Shoji D, Noguchi R, Otsuki S, Hino H (2018) Classification of volcanic ash particles using a convolutional neural network and probability. Sci Rep 8(1):1–12
Soille P (2013) Morphological image analysis: principles and applications. Springer, Berlin
Suescun-Florez E, Iskander M, Bless S (2020) Evolution of particle damage of sand during axial compression via arrested tests. Acta Geotech 15(1):95–112
Sun Q, Zheng J, Coop MR, Altuhafi FN (2019) Minimum image quality for reliable optical characterizations of soil particle shapes. Comput Geotech 114:103110
Wadell H (1932) Volume, shape, and roundness of rock particles. J Geol 40(5):443–451
Wang Y, Ma G, Mei J, Zou Y, Zhang D, Zhou W, Cao X (2021) Machine learning reveals the influences of grain morphology on grain crushing strength. Acta Geotech 1–14
Zhang M, Shi W, Xu Z (2020) Systematic comparison of five machine-learning models in classification and interpolation of soil particle size fractions using different transformed data. Hydrol Earth Syst Sci 24(5):2505–2526
Zhang P, Yin ZY, Jin YF, Liu XF (2021) Modelling the mechanical behaviour of soils using machine learning algorithms with explicit formulations. Acta Geotech 1–20
Zhang W, Wu C (2019) Machine learning predictive models for pile drivability: an evaluation of random forest regression and multivariate adaptive regression splines. In: International conference on information technology in geo-engineering. Springer, Cham, pp 243–255
Zhang W, Wu C, Li Y, Wang L, Samui P (2021) Assessment of pile drivability using random forest regression and multivariate adaptive regression splines. Georisk Assess Manag Risk Eng Syst Geohazards 15(1):27–40
Zhang W, Wu C, Zhong H, Li Y, Wang L (2021) Prediction of undrained shear strength using extreme gradient boosting and random forest based on Bayesian optimization. Geosci Front 12(1):469–477
Zheng A, Casari A (2018) Feature engineering for machine learning: principles and techniques for data scientists. O’Reilly Media, Inc, Newton
Zhuang L, Nakata Y, Kim UG, Kim D (2014) Influence of relative density, particle shape, and stress path on the plane strain compression behavior of granular materials. Acta Geotech 9(2):241–255
Funding
No funding was received for conducting this study.
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. The specific roles are as follows: LL contributed to the data curation, software development, investigation, formal analysis, methodology, visualization, and writing—original draft. MI was involved in the conceptualization, supervision, validation, project administration, provision of resources, and writing—review and editing.
Corresponding author
Ethics declarations
Conflict of interest
The authors have no relevant financial or non-financial interests to disclose.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix: Hyperparameters used in machine learning classifiers
Appendix: Hyperparameters used in machine learning classifiers
Support vector machines (SVMs) | Decision tree | Naïve Bayes | K-nearest neighbors (KNN) | Neural network (MLP) | Random forest | |
---|---|---|---|---|---|---|
Hyperparameters | Kernel function: Gaussian | Maximum number of splits: 210 | Kernel type: Gaussian | Number of neighbors: 9 | Number of fully connected layers: 1 | Maximum number of splits: 523 |
Kernel scale: 0.020709 | Split criterion: Gini’s diversity index | … | Distance metric: cosine | First layer size: 25 | Number of trees: 24 | |
Multiclass method: one-vs-all | … | … | Distance weight: inverse | Iteration limit: 1000 | … |
Rights and permissions
About this article
Cite this article
Li, L., Iskander, M. Use of machine learning for classification of sand particles. Acta Geotech. 17, 4739–4759 (2022). https://doi.org/10.1007/s11440-021-01443-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11440-021-01443-y