Machine learning applied to the prediction of rockfall slope probability
DOI:
https://doi.org/10.33448/rsd-v11i10.32603Keywords:
Rockfall; Machine learning; K-Nearest Neighbors; Rock slope stability.Abstract
O objetivo desse trabalho é propor um modelo de predição da probabilidade de queda de blocos em taludes rochosos utilizando o método K-Nearest Neighbors (KNN). Foi utilizado um banco de dados composto por 220 taludes rochosos, cujas variáveis estão relacionadas à presença de água, características do maciço rochoso, descalçamento de blocos, entre outras. Para cada talude do banco de dados, a probabilidade de queda de blocos (alta, média ou baixa) é conhecida e foi determinada através de análise de agrupamento. O número de vizinhos mais próximos (k) variou entre 1 e 20. A acurácia média obtida dos modelos de predição testados foi igual a 78,4%. Os modelos produziram resultados satisfatórios na previsão da probabilidade de queda de blocos, uma vez que a área sob a curva ROC foi igual a 0,80. O melhor modelo foi selecionado com base no valor de k com maior acurácia e maior área sob a curva ROC. O modelo selecionado teve um valor de k igual a 7.
References
Bar, N., & Barton, N. (2017). The Q-Slope Method for Rock Slope Engineering. Rock Mechanics and Rock Engineering 50, 3307–3322 (2017). https://doi.org/10.1007/s00603-017-1305-0.
Barton, N., Lien, R.., & Lunde, J. (1974). Engineering classification of rock masses for the design of rock support. Rock Mechanics and Rock Engineering. 6:189–236
Bieniawski, Z. (1989). Engineering rock mass classifications: a complete manual for engineers and geologists in mining, civil, and petroleum engineering. 1st ed. John Wiley & Sons.
Fernandes, A. T. dos R., Fonseca, J. L. T., Silva, I. L. P. da, Agamez Arias, P. D. M., Ramos, R. A., & Oliveira, W. D. de. (2021). Avaliação da influência das tensões de barra na previsão de cargas via redes neurais. Research, Society and Development, 10(12), e600101220917. https://doi.org/10.33448/rsd-v10i12.20917
Kassambara, A., & Mundt, F. (2020). Factoextra: Extract and Visualize the Results of Multivariate Data Analyses. R package version 1.0.7. https://CRAN.R-project.org/package=factoextra
Kassambara, A. (2017). Practical guide to cluster analysis in R unsupervised machine learning. STHDA.
Kaufman, L., & Rousseeuw, P. J. (1990). Finding Groups in Data: An Introduction to Cluster Analysis. Wiley Series in Probability and Statistics. ISBN: 0-47 1-73578-7.
Kubat, M. (2017). An Introduction to Machine Learning. Springer Cham. ISBN 978-3-319-63913-0 (eBook). https://doi.org/10.1007/978-3-319-63913-0
Lawrence, L. (1992). Data Preparation for a Neural Network. Neural Network. Special Report: A Miller Freeman Publication.
Mascarenhas, T. A. T., Moriel Junior, J. G., Gomes, R. de S. R., & Mello, G. J. (2020). Aplicação de algoritmos de aprendizado de máquina na classificação de Conhecimentos Especializados de Professores de Física. Research, Society and Development, 9(11), e86191110584. https://doi.org/10.33448/rsd-v9i11.10584
Naghadehi, M. Z., Jimenez, R., KhaloKakaie, R., & Jalali, S. M. E. (2013). A new open-pit mine slope instability index defined using the improved rock engineering systems approach. International Journal of Rock Mechanics and Mining Sciences.
https://doi.org/10.1016/j.ijrmms.2013.01.012
Ossani, P. C., Rossoni, D. F., Cirillo, M. Ângelo, & Borém, F. M. (2021). Classificação de cafés especiais usando técnicas de aprendizado de máquina. Research, Society and Development, 10(5), e13110514732. https://doi.org/10.33448/rsd-v10i5.14732
Ossani, P. C., Rossoni, D. F., Cirillo, M. Â., & Borém, F. M. (2020). Unsupervised classification of specialty coffees in Homogeneous sensory attributes through machine learning. Coffee Science, 15, e151780. 10.25186/cs.v15i.1780
Pessoa, A. D., Sousa, G. C. L. Araujo, R. da C. de, & Anjos, G. J. M. dos. (2021). Modelo de rede neural artificial para previsão da capacidade de carga de estacas cravadas. Research, Society and Development, 10(1), e12210111526. https://doi.org/10.33448/rsd-v10i1.11526
Pierson, L. A., & Van Vickle, R, (1993). Rockfall Hazard Rating System. Transportation Research Record N° 1343, National Research Board, Washington, D.C., pp 6-19.
R Core Team (2020). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. URL https://www.R-project.org/.
Romana, M. (1995). The geomechanical classification SMR for slope correction. In: Proceedings of the 8th ISRM congress on rock mechanics, vol 3. 8 p.
Santi, P. M., Russel, C. P., Higgins, J. D., & Spriet, J. I. (2009). Modification and statistical analysis of the Colorado Rockfall Hazard Rating System. Engineering Geology 104: 55–65. 10.1016/j.enggeo.2008.08.009
Santos, A. E. M., Lana, M. S. & Pereira, T. M. (2022). Evaluation of machine learning methods for rock mass classification. Neural Computing and Applications 34, 4633–4642 (2022). https://doi.org/10.1007/s00521-021-06618-y
Santos, A. E. M., Lana, M. S., & Pereira, T. M. (2021). Rock mass classification by multivariate statistical techniques and artificial intelligence. Geotechinical and Geological Engineering 39:2409–2430. https://doi.org/10.1007/s10706-020-01635-5
Santos, T. B., Lana, M. S., Pereira, T. M., & Canibulat, I. (2019). Quantitative hazard assessment system (Has-q) for open pit mine slopes. International Journal of Mining Science and Technology. Volume 29, Issue 3, Pages 419-427, ISSN 2095-2686, https://doi.org/10.1016/j.ijmst.2018.11.005
Silva, C. C. da, Lima, C. L. de, Silva, A. C. G. da, Moreno, G. M. M., Musah, A., Aldosery, A., Dutra, L., Ambrizzi, T., Borges, I. V. G., Tunali, M., Basibuyuk, S., Yenigün, O., Jones, K., Campos, L., Massoni, T. L., Silva Filho, A. G. da, Kostkova, P., & Santos, W. P. dos. (2021). Predição de casos de Dengue, Chikungunya e Zika em Recife, Brasil: uma abordagem espaço-temporal com base em condições climáticas, notificações de saúde e aprendizado de máquina. Research, Society and Development, 10(12), e452101220804. https://doi.org/10.33448/rsd-v10i12.20804
Venables, W. N. & Ripley, B. D. (2002) Modern Applied Statistics with S. Fourth Edition. Springer.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Larissa Regina Costa Silveira; Milene Sabino Lana; Tatiana Barreto dos Santos
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
1) Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2) Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
3) Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
