Predição de Escorregamentos de Encostas baseada em Aprendizado de Máquina

• Laedson S. Pedreira UEFS
• Rodrigo T. Calumby UEFS
• Maria do S. C. São Mateus UEFS

DOI: https://doi.org/10.5753/erbase.2021.20054

Abstract

Slope landslides are one of the main phenomena causing natural disasters in Brazilian cities, causing, every year, countless material damages and causing a large number of fatal victims. In this context, this work proposes the application of machine learning techniques to predict slope landslides, individually, in time and space, using data from multiple sources. For this, data integration was performed and several predictive algorithms about the occurrence or not of slope slides were evaluated. The results of the experiments showed that the algorithms were able to achieve promising performance.

References

Achour, Y. and Pourghasemi, H. R. (2020). How do machine learning techniques help in increasing accuracy of landslide susceptibility maps? Geoscience Frontiers, 11(3):871–883.

IBGE (2019). Suscetibilidade a deslizamentos do Brasil: primeira aproximação. Instituto Brasileiro de Geografia e Estatística IBGE, Rio de Janeiro.

Korup, O. and Stolle, A. (2014). Landslide prediction from machine learning. Geology Today, 30.

Liu, Z., Gilbert, G., Cepeda, J. M., Lysdahl, A. O. K., Piciullo, L., Hefre, H., and Lacasse, S. (2021). Modelling of shallow landslides with machine learning algorithms. Geoscience Frontiers, 12(1):385–393.

Tehrani, F. S., Santinelli, G., and Herrera, M. (2019). A framework for predicting rainfallinduced landslides using machine learning methods. 17th European Conference on Soil Mechanics and Geotechnical Engineering, ECSMGE 2019 Proceedings.

Tominaga, K., Santoro, J., and do. Amaral, R. (2015). Desastres naturais: conhecer para prevenir, volume 3ed. Instituto Geológico, São Paulo.