Predictions of Weekly Soil Movements Using Moving-Average and Support-Vector Methods: A Case-Study in Chamoli, India
- 1.1k Downloads
Landslides plague the Himalayan region, and landslide occurrence is widespread in hilly areas. Thus, it is important to predict soil movements and associated landslide events in advance of their occurrence. A recent approach to predicting soil movements is to use machine-learning techniques. In machine-learning literature, both moving-average-based methods (Seasonal Autoregressive Integrated Moving Average (SARIMA) model and Autoregressive (AR) model) and support-vector-based methods (Sequential Minimal Optimization; SMO) have been proposed. However, an evaluation of these methods on real-world landslide prediction has been little explored. The primary objective of this paper is to compare SARIMA, AR, and SMO methods in their ability to predict soil movements recorded at a real-world landslide site. A SARIMA model, an AR model, and a SMO model were compared in their ability to predict soil movements (in degrees) at the Tangni landslide in Chamoli, India. Time-series data about soil movements from five-sensors placed on the Tangni landslide hill were collected daily over a 78-week period from July 2012 to July 2014. Different model parameters were calibrated to the training data (first 62-weeks) and then made to predict the test data (the last 16-weeks). Results revealed that the moving-average models (SARIMA and AR) performed better compared to the support-vector models (SMO) during both training and test. Specifically, the SARIMA model possessed the smallest error compared to the AR and SMO models during test. We discuss the implications of using moving-average methods in predicting soil movements and associated landslides at real-world landslide locations.
KeywordsLandslides SARIMA SMO Autoregression Soil movements Tangni landslide
The project was supported from grants (awards: IITM/NDMA/VD/184, IITM/DRDO-DTRL/VD/179, and IITM/DCoN/VD/204) to Varun Dutt. We are also grateful to Indian Institute of Technology Mandi for providing computational resources for this project.
- 2.Parkash, S.: Historical records of socio-economically significant landslides in India. J. South Asia Disaster Stud. 4(2), 177–204 (2011)Google Scholar
- 3.Chaturvedi, P., Srivastava, S., Kaur, P.B.: Landslide earlywarning system development using statistical analysis of sensors’ data at Tangni Landslide, Uttarakhand, India. In: Deep, K., et al. (eds.) Sixth International Conference on Soft Computing for Problem Solving. AISC 2017, vol. 547, pp. 259–270. Springer, Singapore (2017)CrossRefGoogle Scholar
- 13.Zhu, C.H., Hu, G.D.: Time series prediction of landslide displacement using SVM model: application to Baishuihe landslide in Three Gorges Reservoir area, China. In: Yarlagadda, P., Yun-Hae, K. (eds.) Applied Mechanics and Materials, vol. 239, pp. 1413–1420. Trans Tech Publications (2013)Google Scholar
- 15.Duan, G.H., Niu, R.Q.: A method of dynamic data mining for landslide monitoring data. J. Yangtze River Sci. Res. Inst. 30(5), 10 (2013)Google Scholar
- 16.Qiang, L.I., Duan-you, L.I.: Research of dynamic predication technique for landslide displacement monitoring. J. Yangtze River Sci. Res. Inst. 22(6) (2005)Google Scholar
- 17.India News: Landslides near Badrinath in Uttarakhand, 13 August 2013. https://www.indiatvnews.com/news/india/landslides-near-badrinathin-uttarakhand-26296.html. Accessed 7 Apr 2019
- 18.Asteriou, D., Hall, S.G.: ARIMA models and the Box-Jenkins methodology. Appl. Econom. 2(2), 265–286 (2011)Google Scholar
- 19.Hyndman, R.J., Athanasopoulos, G.: Forecasting: Principles and Practice, 2nd edn. OTexts, Melbourne (2018)Google Scholar
- 20.Platt, J.: Sequential minimal optimization: a fast algorithm for training support vector machines, April 1998. https://www.microsoft.com/enus/research/publication/sequential-minimal-optimization-a-fast-algorithm-fortraining-support-vector-machines/. Accessed 7 Apr 2019