Abstract
The shape parameters of sand particles can be determined by either a Krumbein-Sloss chart or mathematical computation based on the particle image. However, these approaches are limited by user-dependent uncertainty and complicated algorithms with computational issues. This study explores the feasibility of predicting the shape parameters of sand particles via a well-trained deep learning model. Over 7000 sand particle images from six different sand types were used, and the corresponding shape parameters such as sphericity, roundness, slenderness, and circularity were computed. Inception-ResNet-v2 whose performance has been widely validated, as one of convolutional neural network-based model, used the pair dataset (i.e., image and each computed shape parameter) and comprised a pre-trained network for feature extraction and a regression output layer. Strategic data augmentation helped in increasing the number of training data to reduce the test loss efficiently. Several hyperparameters were carefully tuned to accomplish model optimization, while the generalization ability of the model was evaluated during training by using a validation dataset. The prediction results showed that the trained model yielded a highly accurate and precise prediction of the shape parameters, regardless of the image types. The predicted roundness had relatively scattered values in comparison with other parameters, presumably because of its indeterminate definition of the ground-truth. Thus, the proposed trained model enables accurate prediction of the shape parameters of sand particles solely based on an image containing the complete shape of the particle, without mathematical computation.
Similar content being viewed by others
References
Alqahtani N, Alzubaidi F, Armstrong RT et al (2020) Machine learning for predicting properties of porous media from 2d X-ray images. J Pet Sci Eng 184:106514. https://doi.org/10.1016/j.petrol.2019.106514
Badrinarayanan V, Kendall A, Cipolla R (2017) SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39:2481–2495. https://doi.org/10.1109/TPAMI.2016.2644615
Bergstra J, Bengio Y (2012) Random search for hyper-parameter optimization. J Mach Learn Res 13:281–305
Chen LC, Papandreou G, Kokkinos I et al (2017) DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell 40:834–848
Cho GC, Dodds J, Santamarina JC (2006) Particle shape effects on packing density
Claesen M, De Moor B (2015) Hyperparameter search in machine learning. arXiv Preprint. arXiv:1502.02127
Cui X, Goel V, Kingsbury B (2015) Data augmentation for deep convolutional neural network acoustic modeling. IEEE/ACM Trans Audio Speech Lang Process 23:1469–1477. https://doi.org/10.1109/ICASSP.2015.7178831
Girshick R, Donahue J, Darrell T et al (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. Proc IEEE Conf Comput Vis pattern Recognit. https://doi.org/10.1109/CVPR.2014.81
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 770–778
Hinton GE (2012) A practical guide to training restricted Boltzmann machines. Springer, Berlin
Hryciw RD, Zheng J, Shetler K (2016) Particle roundness and sphericity from images of assemblies by chart estimates and computer methods. J Geotech Geoenvironmental Eng 142:04016038. https://doi.org/10.1061/(ASCE)GT.1943-5606.0001485
Huang H, Luo J, Tutumluer E et al (2020) Size and shape determination of riprap and large-sized aggregates using field imaging. Illinois Center for Transportation/Illinois Department of Transportation.
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning. PMLR, pp 448–456
Kim Y, Yun TS (2021) How to classify sand types: a deep learning approach. Eng Geol 288:106142. https://doi.org/10.1016/j.enggeo.2021.106142
Kim KY, Suh HS, Yun TS et al (2016) Effect of particle shape on the shear strength of fault gouge. Geosci J 20:351–359. https://doi.org/10.1007/s12303-015-0051-0
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. https://doi.org/10.1016/j.enggeo.2018.11.001
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097–1105
Krumbein WC, Sloss LL (1951) Stratigraphy and sedimentation. W. H. Freeman and Company, San Francisco
Larochelle H, Erhan D, Courville A et al (2007) An empirical evaluation of deep architectures on problems with many factors of variation. Int Conf Mach Learn PMLR. https://doi.org/10.1145/1273496.1273556
LeCun YA, Bottou L, Orr GB, Müller KR (2012) Efficient backprop. Springer, Berlin
Lee C, Suh HS, Yoon B, Yun TS (2017) Particle shape effect on thermal conductivity and shear wave velocity in sands. Acta Geotech 12:615–625. https://doi.org/10.1007/s11440-017-0524-6
Li M, Soltanolkotabi M, Oymak S (2020) Gradient descent with early stopping is provably robust to label noise for overparameterized neural networks. In: International conference on artificial intelligence and statistics. PMLR, pp 4313–4324
Li J, Shao S, Hong J (2021) Machine learning shadowgraph for particle size and shape characterization. Meas Sci Technol 32:015406. https://doi.org/10.1088/1361-6501/abae90
Lin M, Chen Q, Yan S (2013) Network in network. arXiv Preprint. arXiv:1312.4400
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 3431–3440
Mikołajczyk A, Grochowski M (2018) Data augmentation for improving deep learning in image classification problem. In: 2018 International interdisciplinary PhD workshop (IIPhDW). IEEE, pp 117–122
Niu Y, Mostaghimi P, Shabaninejad M et al (2020) Digital rock segmentation for petrophysical analysis with reduced user bias using convolutional neural networks. Water Resour Res. https://doi.org/10.1029/2019WR026597
Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9:62–66
Prechelt L (1998) Early stopping-but when? Springer, Berlin
Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. Adv Neural Inf Process Syst 28:91–99
Riley NA (1941) Projection sphericity. J Sediment Res 11:94–95
Shin H, Santamarina JC (2013) Role of particle angularity on the mechanical behavior of granular mixtures. J Geotech Geoenvironmental Eng 139:353–355. https://doi.org/10.1061/(ASCE)GT.1943-5606.0000768
Shorten C, Khoshgoftaar TM (2019) A survey on image data augmentation for deep learning. J Big Data 6:1–48. https://doi.org/10.1186/s40537-019-0197-0
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv Preprint
Suh HS, Kim KY, Lee J, Yun TS (2017) Quantification of bulk form and angularity of particle with correlation of shear strength and packing density in sands. Eng Geol 220:256–265. https://doi.org/10.1016/j.enggeo.2017.02.015
Sun Q, Zheng J (2020) Clone granular soils with mixed particle morphological characteristics by integrating spherical harmonics with Gaussian mixture model, expectation–maximization, and Dirichlet process. Acta Geotech 15:2779–2796
Szegedy C, Liu W, Jia Y et al (2015) Going deeper with convolutions. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 1–9
Szegedy C, Ioffe S, Vanhoucke V, Alemi AA (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: AAAI Conf Artif Intell
Tang S, Wang J, Tang C (2021) Identification of microseismic events in rock engineering by a convolutional neural network combined with an attention mechanism. Rock Mech Rock Eng 54:47–69. https://doi.org/10.1007/s00603-020-02259-0
Wadell H (1933) Sphericity and roundness of rock particles. J Geol 41:310–331. https://doi.org/10.1086/624040
Wang J, Perez L (2017) The effectiveness of data augmentation in image classification using deep learning. Convolutional Neural Netw Vis Recognit 11:1–8
Yang J, Luo XD (2015) Exploring the relationship between critical state and particle shape for granular materials. J Mech Phys Solids 84:196–213. https://doi.org/10.1016/j.jmps.2015.08.001
Yang D, Wang X, Zhang H et al (2021) A mask R-CNN based particle identification for quantitative shape evaluation of granular materials. Powder Technol 392:296–305. https://doi.org/10.1016/j.powtec.2021.07.005
Zheng J, Hryciw RD (2015) Traditional soil particle sphericity, roundness and surface roughness by computational geometry. Géotechnique 65:494–506. https://doi.org/10.1680/geot.14.P.192
Zheng J, Hryciw RD (2016) Roundness and sphericity of soil particles in assemblies by computational geometry. J Comput Civ Eng 30:04016021. https://doi.org/10.1061/(asce)cp.1943-5487.0000578
Zheng J, He H, Alimohammadi H (2021) Three-dimensional Wadell roundness for particle angularity characterization of granular soils. Acta Geotech 16:133–149. https://doi.org/10.1007/s11440-020-01004-9
Zheng J, Zhang Z, Li C et al (2021) Laboratory-on-a-smartphone for estimating angularity of granular soils. Acta Geotech. https://doi.org/10.1007/s11440-021-01259-w
Acknowledgements
This work was supported by the Land and Housing Institute (LHI) grant funded by the Korea Land and Housing Corporation, and the National Research Foundation of Korea (NRF) Grant funded by the Korea government (MSIT) (Nos. 2020R1A2C1014815, NRF-2021R1A5A1032433).
Author information
Authors and Affiliations
Contributions
Yejin Kim: Conceptualization, Methodology, Software, Validation, Investigation, Data curation, Writing—Original draft preparation. Jeehoon Ma: Data curation, Methodology. Seok Yong Lim: Data curation, Methodology. Jun Young Song: Data curation, Methodology, Writing—Original draft preparation. Tae Sup Yun: Conceptualization, Formal analysis, Validation, Writing—Reviewing and Editing, Supervision, Project administration.
Corresponding author
Ethics declarations
Conflicts of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Kim, Y., Ma, J., Lim, S.Y. et al. Determination of shape parameters of sands: a deep learning approach. Acta Geotech. 17, 1521–1531 (2022). https://doi.org/10.1007/s11440-022-01464-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11440-022-01464-1