Generation of Penetrometric Profile of the Soil Applying Machine Learning to Measure While Drilling Data from Deep Foundation Machinery
Source abstract
Abstract
The study performed in this article aimed to reproduce the penetrometric profile of the soil from the perforation parameters of deep foundation and ground improvement. This could allow for more easily interpretable information on the soil strength during execution as well as validate the design hypotheses. To achieve this goal, a series of Machine Learning algorithms have been used and compared with traditionally applied analytical formulas. Dynamic time warping is used to measure the likeness of the results with the expected shape. The results show that the algorithms are capable of better fitting the penetrometric profiles of the soil. Tree ensemble methods stand out with the best results.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Drilling and Well Engineering · Tunneling and Rock Mechanics
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Departamento de Ingeniería Civil: Construcción, E.T.S. de Ingenieros de Caminos, Canales y Puertos, Universidad Politécnica de Madrid, 28040 Madrid, Spain
Menard España, 28001 Madrid, Spain
Departamento de Ingeniería y Morfología del Terreno, E.T.S. de Ingenieros de Caminos, Canales y Puertos, Universidad Politécnica de Madrid, 28040 Madrid, Spain
References (72)
Show source-provided references
1. Laudanski, G., Reiffsteck, J.-L., and Benoît, J. (2012). Experimental study of drilling parameters using a test embankment. Geotechnical and Geophysical Site Characterization 4, CRC Press.
2. Burch, T.K. (2018). Model-Based Demography, Springer International Publishing. Demographic Research Monographs.10.1007/978-3-319-65433-1 ↗
3. ISSMGE (2022, June 25). Reference List for Machine Learning and Its Applications in Geotechnical Engineering. Available online: https://www.issmge.org/news/reference-list-for-machine-learning-and-its-applications-in-geotechnical-engineering-part-i-need-to-know-knowledge0.
4. Jaksa, M., and Liu, Z. (2021). Editorial for Special Issue “Applications of Artificial Intelligence and Machine Learning in Geotechnical Engineering”. Geosciences, 11.10.3390/geosciences11100399 ↗
5. Rahman, M., and Jaksa, M. (2022, January 1–5). Deep Learning for Rainfall Prediction: Data Enhancement, Forecasting, and Estimation. Proceedings of the 20th ICSMGE-State of the Art and Invited Lectures, Sydney, Australia.
6. Rahman, M., and Jaksa, M. (2022, January 1–5). Machine learning in geotechnical engineering: Opportunities and applications. Proceedings of the 20th ICSMGE-State of the Art and Invited Lectures, Sydney, Australia.
7. Abdallah, A. (2022, January 1–5). Artificial neural network prediction of the water retention curve from physical soil parameters: Comparing continuous and pointwise approaches. Proceedings of the 20th International Conference on Soil Mechanics and Geotechnical Engineering, Sydney, Australia.
8. Asr, A.A. (2022, January 1–5). An evolutionary modelling approach to compressed air tunneling in non-homogeneous and layered geo-materials to predict air losses. Proceedings of the 20th International Conference on Soil Mechanics and Geotechnical Engineering, Sydney, Australia.
9. Bunieski, S. (2022, January 1–5). Practical methodologies to apply machine learning algorithms to ground improvement data. Proceedings of the 20th International Conference on Soil Mechanics and Geotechnical Engineering, Sydney, Australia.
10. Congress, S.S.C., Gajurel, A., Chimauriya, H., and Puppala, A.J. (2022, January 1–5). A review of the applications of artificial intelligence techniques in geotechnical engineering disciplines. Proceedings of the 20th International Conference on Soil Mechanics and Geotechnical Engineering, Sydney, Australia.
11. Haasnoot, J., Madlener, P., and Tiggelman, L. (2022, January 1–5). Cooperation leads to a digital toolbox for future geotechnical engineers. Proceedings of the 20th International Conference on Soil Mechanics and Geotechnical Engineering, Sydney, Australia.
12. Jong, S.C., Ong, D.E.L., and Oh, E. (2022, January 1–5). A Bayesian approach to the prediction of strength parameters. Proceedings of the 20th International Conference on Soil Mechanics and Geotechnical Engineering, Sydney, Australia.
13. Kim, Y., Kim, J., Park, J., and Yun, T.S. (2022, January 1–5). Deep learning based classification model of rock mass based on RMR of tunnel face. Proceedings of the 20th International Conference on Soil Mechanics and Geotechnical Engineering, Sydney, Australia.
14. Meng, J., Mattsson, H., and Laue, J. (2022, January 1–5). An artificial neural network approach for three-dimensional slope stability prediction. Proceedings of the 20th International Conference on Soil Mechanics and Geotechnical Engineering, Sydney, Australia.
15. Shi, C., and Wang, Y. (2022, January 1–5). Data-driven subsurface stratigraphy from prior knowledge and sparse site-specific measurements using multiple point statistics. Proceedings of the 20th International Conference on Soil Mechanics and Geotechnical Engineering, Sydney, Australia.
16. Smyrniou, E., Nuttall, J., and Coelho, B.Z. (2022, January 1–5). Using neural network components to model soil constitutive behaviour. Proceedings of the 20th International Conference on Soil Mechanics and Geotechnical Engineering, Sydney, Australia.
17. Tinoco, J., and Correia, A.G. (2022, January 1–5). When artificial neural networks and genetic algorithms work together on soil embankments stability condition identification. Proceedings of the 20th International Conference on Soil Mechanics and Geotechnical Engineering, Sydney, Australia.
18. Wang, Z.Z., and Goh, S.H. (May, January 29). Adaptive training of convolutional neural networks for slope reliability analysis in spatially variable soils. Proceedings of the 7th International Young Geotechnical Engineers Conference, Sydney, Australia.
19. Scott, B. (May, January 29). Soil desiccation crack recognition and quantification using deep learning. Proceedings of the 7th International Young Geotechnical Engineers Conference, Sydney, Australia.
20. Rahman, M., and Jaksa, M. (2022, January 1–5). Evaluation of residual strength of rocks based on acoustic emission data using AI. Proceedings of the 20th International Conference on Soil Mechanics and Geotechnical Engineering, Sydney, Australia.
21. Zhang, L.-M., and Xiao, T. (2022, January 1–5). Storm-based forecasting of man-made slope failures using machine learning. Proceedings of the 20th International Conference on Soil Mechanics and Geotechnical Engineering, Sydney, Australia.
22. (2023). Abstract Book of 4th International Symposium on Machine Learning and Big Data in Geoscience (Standard No. ISSMGE TC309). Available online: https://www.ismlg2023.com/abstracts.
23. García, E.M., Alberti, M.G., and Arcos, A.A. (2023). Measurement-While-Drilling Based Estimation of Dynamic Penetrometer Values Using Machine Learning. Abstract of the 4th International Symposium on Machine Learning and Big Data in Geoscience, University College Cork.
24. Interpolation and stratification of multilayer soil property profile from sparse measurements using machine learning methods10.1016/j.enggeo.2019.105430 ↗
25. Soil database development with the application of machine learning methods in soil properties prediction10.1016/j.enggeo.2022.106769 ↗
26. How to classify sand types: A deep learning approach10.1016/j.enggeo.2021.106142 ↗
27. A framework of active learning and semi-supervised learning for lithology identification based on improved naive Bayes10.1016/j.eswa.2022.117278 ↗
28. A novel integrated strategy of easy pruning, parameter searching, and re-parameterization for lightweight intelligent lithology identification10.1016/j.eswa.2023.120657 ↗
29. Classification with noisy labels through tree-based models and semi-supervised learning: A case study of lithology identification10.1016/j.eswa.2023.122506 ↗
30. Research on lithology identification method based on mechanical specific energy principle and machine learning theory10.1016/j.eswa.2021.116142 ↗
31. Back-propagation neural networks for modeling complex systems10.1016/0954-1810(94)00011-S ↗
32. Flaate, K. (1964). An Investigation of the Validity of Three Pile Driving Formulae in Cohesionless Material, Norwegian Geotechnical Institute. Publication No. 56.
33. Prediction of pile bearing capacity using artificial neural networks10.1016/0266-352X(95)00027-8 ↗
34. Bearing capacity and settlement of pile foundations
35. Modelling pile capacity using Gaussian process regression10.1016/j.compgeo.2010.07.012 ↗
36. Predicting axial capacity of driven piles in cohesive soils using intelligent computing10.1016/j.engappai.2011.08.009 ↗
37. Millán Muñoz, M.Á., Galindo Aires, R., and Santos de Alencar, A.T. (2022, January 24–27). Red neuronal para el cálculo de la capacidad portante de cimentaciones superficiales sobre roca. Proceedings of the XI Simposio Nacional de Ingeniería Geotécnica, Mieres, Spain.
38. Beattie, N. (2009). Monitoring-While-Drilling for Open-Pit Mining in a Hard Rock Environment. [Master’s Thesis, Queen’s University].
39. Zhou, H., Monteiro, S.T., Hatherly, P., Ramos, F., Nettleton, E., and Oppolzer, F. (2009, January 2–4). Spectral Feature Selection for Automated Rock Recognition using Gaussian Process Classification. Proceedings of the Australasian Conference on Robotics and Automation (ACRA), Sydney, Australia.
40. Zhou, H., Hatherly, P., Monteiro, S.T., Ramos, F., Oppolzer, F., Nettleton, E., and Scheding, S. (2012, January 14–18). Automatic rock recognition from drilling performance data. Proceedings of the 2012 IEEE International Conference on Robotics and Automation, St. Paul, MN, USA.10.1109/ICRA.2012.6224745 ↗
41. Rock Recognition From MWD Data: A Comparative Study of Boosting, Neural Networks, and Fuzzy Logic10.1109/LGRS.2010.2046312 ↗
42. A Machine Learning Approach for Material Type Logging and Chemical Assaying from Autonomous Measure-While-Drilling (MWD) Data10.1007/s11004-021-09970-w ↗
43. Establishing relationships between structural data from close-range terrestrial digital photogrammetry and measurement while drilling data10.1016/j.enggeo.2020.105480 ↗
44. Monitor-While-Drilling-based estimation of rock mass rating with computational intelligence: The case of tunnel excavation front10.1016/j.autcon.2018.05.019 ↗
45. Improving face decisions in tunnelling by machine learning-based MWD analysis10.1002/geot.202100070 ↗
46. Predicting rate of penetration during drilling of deep geothermal well in Korea using artificial neural networks and real-time data collection10.1016/j.jngse.2019.05.004 ↗
47. Data-driven model for the identification of the rock type at a drilling bit10.1016/j.petrol.2019.03.041 ↗
48. Machine learning for classification of stratified geology from MWD data10.1016/j.oregeorev.2022.104737 ↗
49. Artificial neural network response assessment of a single footing on soft soil reinforced by rigid inclusions10.1016/j.engstruct.2023.115753 ↗
50. Pathways and challenges of the application of artificial intelligence to geohazards modelling10.1016/j.gr.2020.08.007 ↗
51. Deep learning for geological hazards analysis: Data, models, applications, and opportunities10.1016/j.earscirev.2021.103858 ↗
52. Machine learning methods for landslide susceptibility studies: A comparative overview of algorithm performance10.1016/j.earscirev.2020.103225 ↗
53. A systematic review and meta-analysis of artificial neural network application in geotechnical engineering: Theory and applications10.1007/s00521-019-04109-9 ↗
54. Machine learning and landslide studies: Recent advances and applications10.1007/s11069-022-05423-7 ↗
55. Xie, J., Huang, J., Zeng, C., Jiang, S.-H., and Podlich, N. (2020). Systematic Literature Review on Data-Driven Models for Predictive Maintenance of Railway Track: Implications in Geotechnical Engineering. Geosciences, 10.10.3390/geosciences10110425 ↗
56. State-of-the-art review of soft computing applications in underground excavations10.1016/j.gsf.2019.12.003 ↗
57. Application of deep learning algorithms in geotechnical engineering: A short critical review10.1007/s10462-021-09967-1 ↗
58. Machine Learning-Based Modelling of Soil Properties for Geotechnical Design: Review, Tool Development and Comparison10.1007/s11831-021-09615-5 ↗
59. Möller, B., Bergdahl, U., and K, E. (2004, January 19–22). Soil-rock sounding with MWD—A modern technique to investigate hard soils and rocks. Proceedings of the 2nd International Conference on Site Characterization, Porto, Portugal.
60. A Laboratory Study of Rock Breakage by Rotary Drilling10.2118/1163-G ↗
61. The Concept of Specific Energy in Rock Drilling10.1016/0148-9062(65)90022-7 ↗
62. Recording Drilling Parameters in Ground Engineering
63. (2008). Geotechnical Investigation and Testing—Field Testing—Part 2: Dynamic Probing (Standard No. UNE-EN ISO 22476-2:2008).
64. García, E.M., Alberti, M.G., and Arcos Álvarez, A.A. (2022). Measurement-While-Drilling Based Estimation of Dynamic Penetrometer Values Using Decision Trees and Random Forests. Appl. Sci., 12.10.3390/app12094565 ↗
65. Association of Geotechnical & Geoenvironmental Specialists (2023, December 10). AGS Data Format. Available online: https://www.ags.org.uk/data-format/.
66. (2023, December 10). Pandas. Available online: https://pandas.pydata.org/.
67. Association of Geotechnical & Geoenvironmental Specialists (2023, December 10). AGS Python Library. Available online: https://gitlab.com/ags-data-format-wg/ags-python-library.
68. SMOTE: Synthetic Minority Over-sampling Technique10.1613/jair.953 ↗
69. (2023, December 10). Scikit-learn. Sklearn.Model_Selection. GridSearchCV Class. Available online: https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.GridSearchCV.html#sklearn.model_selection.GridSearchCV.
70. Matejka, J., and Fitzmaurice, G. (2017, January 6–11). Same Stats, Different Graphs: Generating Datasets with Varied Appearance and Identical Statistics through Simulated Annealing. Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems, Denver, CO, USA.10.1145/3025453.3025912 ↗
71. Charles, D.J., Axtell, M.D., and Gourvenec, S. (September, January 28). Assessing the quality of synthetic CPT training data using time series similarity. Proceedings of the 4th International Symposium on Machine Learning & Big Data in Geoscience, Cork, Ireland.
72. Morse, M.D., and Patel, J.M. (2007, January 12–14). An efficient and accurate method for evaluating time series similarity. Proceedings of the 2007 ACM SIGMOD International Conference on Management of Data, Beijing, China.10.1145/1247480.1247544 ↗