Classification of Sand Using Deep Learning
Publication: Journal of Geotechnical and Geoenvironmental Engineering
Volume 149, Issue 11
Abstract
Identifying sands is an important requirement in many geotechnical exploration projects. Knowledge of the sand type can help in estimating the physical and mechanical properties of a soil. Previous studies revealed that machine learning approaches using neural networks (NN) can correctly identify up to 75% of individual sand particles using size and shape descriptors. This study explores the efficacy of deep learning methods for automatically classifying sand types from individual images of sand particles. Dynamic image analysis (DIA) was employed to generate a large data set of sand particle images, which were then used for training a deep learning model known as convolutional neural networks (CNN). The analysis was based on 40,000 binary particle images for twenty types of sand. The work demonstrates that computer vision has a remarkable ability to automatically classify 64% of individual sand particles among 20 types of sand, the accuracy for sand clusters can reach up to 100%, when a CNN model augmented with size and shape data was employed. The effects of domain size, size and shape parameters, and the selected CNN model on the classification accuracy were also investigated. The results demonstrate that sand classification using a larger number of sand types resulted in a lower classification accuracy. Classification accuracy of individual particles achieved using CNN were 10%–15% better than those achieved using NN. CNN can automatically and adaptively learn the spatial hierarchy of features which is superior to the handcrafted size and shape parameters, used by NN for identifying sand particles. The study suggests that classification accuracy benefits from data augmentation use of more particle orientations, even at the cost of trimming some particles, and suffers from reduction in image resolution. While model training requires a lot of computational work, a pretrained CNN model may potentially be tuned to run on mobile phones, which points to the potential for real-time field deployment to enable automatic soil classification on-site.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Particle images employed in this study are available from the corresponding author upon reasonable request.
Acknowledgments
Peace River, Hawaii, Fiji Pink, and Oolite sands were purchased from the Carib Sea company. Ottawa and Quartz Sands were purchased from AGSCO, Inc. Browse #1 and Ledge point sands were collected by the RV Investigator on Voyage IN2017_T01 and were freely provided by CSIRO Marine National Facility (MNF), courtesy of Dr. Ryan Beemer from the University of Massachusetts at Dartmouth. FRF and Vieques sands were provided courtesy of Dr. Sylvia Rodríguez-Abudo from the University of Puerto Rico at Mayaguez. Cape Cod sand was provided courtesy of Dr. Kenneth G. Foote of Woods Hole Oceanographic Institution. All other sands were collected by the authors from the indicated public beaches.
References
ASTM. 2017. Standard practice for classification of soils for engineering purposes (unified soil classification system). ASTM D2487. West Conshohocken, PA: ASTM.
Azizi, A., Y. A. Gilandeh, T. Mesri-Gundoshmian, A. A. Saleh-Bigdeli, and H. A. Moghaddam. 2020. “Classification of soil aggregates: A novel approach based on deep learning.” Soil Tillage Res. 199 (May): 104586. https://doi.org/10.1016/j.still.2020.104586.
Beemer, R. D., A. Bandini-Maeder, J. Shaw, and M. J. Cassidy. 2020. “Volumetric particle size distribution and variable granular density soils.” Geotech. Test. J. 43 (2): 1. https://doi.org/10.1520/GTJ20180286.
Beucher, A., C. B. Rasmussen, T. B. Moeslund, and M. H. Greve. 2022. “Interpretation of convolutional neural networks for acid sulfate soil classification.” Front. Environ. Sci. 679 (9). https://doi.org/10.3389/fenvs.2021.809995.
Cracknell, M. J., and A. M. Reading. 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 (Feb): 22–33. https://doi.org/10.1016/j.cageo.2013.10.008.
Goodfellow, I., Y. Bengio, and A. Courville. 2016. Deep learning. Cambridge, MA: MIT Press.
Guo, Y., Y. Liu, A. Oerlemans, S. Lao, S. Wu, and M. S. Lew. 2016. “Deep learning for visual understanding: A review.” Neurocomputing 187 (Apr): 27–48. https://doi.org/10.1016/j.neucom.2015.09.116.
Hao, H., R. Guo, Q. Gu, and X. Hu. 2019. “Machine learning application to automatically classify heavy minerals in river sand by using SEM/EDS data.” Miner. Eng. 143 (Nov): 105899. https://doi.org/10.1016/j.mineng.2019.105899.
He, K., X. Zhang, S. Ren, and J. Sun. 2016. “Deep residual learning for image recognition.” In Proc., IEEE Conf. on Computer Vision and Pattern Recognition, 770–778. New York: IEEE.
Howard, A., et al. 2019. “Searching for mobilenetv3.” In Proc., IEEE/CVF Int. Conf. on Computer Vision, 1314–1324. New York: IEEE.
Hryciew, R. D., A. M. Ghalib, and S. A. Raschke. 1998. “In-situ soil characterization using vision cone penetrometer (VisCPT).” In Geotechnical site characterization, 1081–1086. Rotterdam, Netherlands: A.A. Balkema.
Hryciw, R. D., J. Zheng, and K. Shetler. 2016. “Particle roundness and sphericity from images of assemblies by chart estimates and computer methods.” J. Geotech. Geoenviron. Eng. 142 (9): 04016038. https://doi.org/10.1061/(ASCE)GT.1943-5606.0001485.
Indraswari, R., R. Rokhana, and W. Herulambang. 2022. “Melanoma image classification based on MobileNetV2 network.” Procedia Comput. Sci. 197 (Jan): 198–207. https://doi.org/10.1016/j.procs.2021.12.132.
Kamilaris, A., and F. X. Prenafeta-Boldú. 2018. “Deep learning in agriculture: A survey.” Comput. Electron. Agric. 147 (Apr): 70–90. https://doi.org/10.1016/j.compag.2018.02.016.
Kim, Y., J. Ma, S. Y. Lim, J. Y. Song, and T. S. Yun. 2022. “Determination of shape parameters of sands: A deep learning approach.” Acta Geotech. 17 (4): 1521–1531. https://doi.org/10.1007/s11440-022-01464-1.
Kim, Y., H. S. Suh, and T. S. Yun. 2019. “Reliability and applicability of the Krumbein-Sloss chart for estimating geomechanical properties in sands.” Eng. Geol. 248 (Jan): 117–123. https://doi.org/10.1016/j.enggeo.2018.11.001.
Kim, Y., and T. S. Yun. 2021. “How to classify sand types: A deep learning approach.” Eng. Geol. 288 (Jul): 106142. https://doi.org/10.1016/j.enggeo.2021.106142.
Krumbein, W. C., and L. L. Sloss. 1951. Stratigraphy and sedimentation. 2nd ed. San Francisco: W. H. Freeman & Company.
LeCun, Y., Y. Bengio, and G. Hinton. 2015. “Deep learning.” Nature 521 (7553): 436–444. https://doi.org/10.1038/nature14539.
LeCun, Y., L. Bottou, Y. Bengio, and P. Haffner. 1998. “Gradient-based learning applied to document recognition.” Proc. IEEE 86 (11): 2278–2324. https://doi.org/10.1109/5.726791.
Lee, C. H., S. J. Lee, and M. Shin. 2022. “Characterization of variability in 2-dimensional particle geometry via 3D structured light scanning.” Transp. Geotech. 34 (May): 100760. https://doi.org/10.1016/j.trgeo.2022.100760.
Lee, J., N. Chirkov, E. Ignasheva, Y. Pisarchyk, M. Shieh, F. Riccardi, R. Sarokin, A. Kulik, and M. Grundmann. 2019. “On-device neural net inference with mobile gpus.” Preprint, submitted July 3, 2019. http://arxiv.org/abs/1907.01989.
Li, L., R. D. Beemer, and M. Iskander. 2021a. “Granulometry of two marine calcareous sands.” J. Geotech. Geoenviron. Eng. 147 (3): 04020171. https://doi.org/10.1061/(ASCE)GT.1943-5606.0002431.
Li, L., and M. Iskander. 2019. “Evaluation of dynamic image analysis for characterizing granular soils.” Geotech. Test. J. 43 (5): 1149–1173. https://doi.org/10.1520/GTJ20190137.
Li, L., and M. Iskander. 2021. “Evaluation of roundness parameters in use for sand.” J. Geotech. Geoenviron. Eng. 147 (9): 04021081. https://doi.org/10.1061/(ASCE)GT.1943-5606.0002585.
Li, L., and M. Iskander. 2022. “Use of machine learning for classification of sand particles.” Acta Geotech. 17 (10): 1–21. https://doi.org/10.1007/s11440-021-01443-y.
Li, Y., Z. Cao, A. Liang, B. Liang, L. Chen, H. Zhao, and C. Feng. 2022. “Egocentric prediction of action target in 3D.” Preprint, submitted March 24, 2022. http://arxiv.org/abs/2203.13116.
Li, Y., S. Ren, P. Wu, S. Chen, C. Feng, and W. Zhang. 2021b. “Learning distilled collaboration graph for multi-agent perception.” Adv. Neural Inf. Process. Syst. 34 (Dec): 29541–29552. https://doi.org/10.48550/arXiv.2111.00643.
Master, S. 2014. Large scale object detection. Prague, Czechia: Czech Technical Univ.
Nielsen, M. 2015. Neural networks and deep learning. San Francisco: Determination Press.
Perez, L., and J. Wang. 2017. “The effectiveness of data augmentation in image classification using deep learning.” Preprint, submitted December 13, 2017. http://arxiv.org/abs/1712.04621.
Ren, J. S. J., and L. Xu. 2015. “On vectorization of deep convolutional neural networks for vision tasks.” In Proc., AAAI Conf. on Artificial Intelligence. Washington, DC: Association for the Advancement of Artificial Intelligence.
Shorten, C., and T. M. Khoshgoftaar. 2019. “A survey on image data augmentation for deep learning.” J. Big Data 6 (1): 1–48. https://doi.org/10.1186/s40537-019-0197-0.
Sudarsan, B., W. Ji, V. Adamchuk, and A. Biswas. 2018. “Characterizing soil particle sizes using wavelet analysis of microscope images.” Comput. Electron. Agric. 148 (May): 217–225. https://doi.org/10.1016/j.compag.2018.03.019.
Szegedy, C., A. Toshev, and D. Erhan. 2013. “Deep neural networks for object detection.” Adv. Neural Inf. Process. Syst. 2013 (1): 26.
Wadell, H. 1933. “Sphericity and roundness of rock particles.” J. Geol. 41 (3): 310–331. https://doi.org/10.1086/624040.
Xu, M., S. Yoon, A. Fuentes, and D. S. Park. 2023. “A comprehensive survey of image augmentation techniques for deep learning.” Pattern Recognit. 2023 (Jan): 109347. https://doi.org/10.1016/j.patcog.2023.109347.
Zhang, J., C. Li, M. M. Rahaman, Y. Yao, P. Ma, J. Zhang, and M. Grzegorzek. 2022. “A comprehensive review of image analysis methods for microorganism counting: From classical image processing to deep learning approaches.” Artif. Intell. Rev. 2022 (Apr): 1–70. https://doi.org/10.1007/s10462-021-10082-4.
Zhao, Z. Q., P. Zheng, S. T. Xu, and X. Wu. 2019. “Object detection with deep learning: A review.” IEEE Trans. Neural Networks Learn. Syst. 30 (11): 3212–3232. https://doi.org/10.1109/TNNLS.2018.2876865.
Zheng, J., Z. Zhang, C. Li, Z. Li, and L. Gao. 2021. “Laboratory-on-a-smartphone for estimating angularity of granular soils.” Acta Geotech. 2021 (1): 1–24. https://doi.org/10.1007/s11440-021-01259-w.
Information & Authors
Information
Published In
Journal of Geotechnical and Geoenvironmental Engineering
Volume 149 • Issue 11 • November 2023
Copyright
© 2023 American Society of Civil Engineers.
History
Received: Nov 23, 2022
Accepted: May 31, 2023
Published online: Sep 4, 2023
Published in print: Nov 1, 2023
Discussion open until: Feb 4, 2024
ASCE Technical Topics:
- Artificial intelligence and machine learning
- Automation and robotics
- Computer models
- Computer programming
- Computing in civil engineering
- Earth materials
- Engineering fundamentals
- Engineering materials (by type)
- Geomaterials
- Geomechanics
- Geotechnical engineering
- Materials engineering
- Model accuracy
- Models (by type)
- Neural networks
- Particle size distribution
- Particles
- Soil classification
- Soil mechanics
- Soil properties
- Systems engineering
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.