A2_landslideprediction_s17007.docx

Statement of Problem By Praveen Kumar (S17007) [Research Methodology] Research Topic: Prediction of the landslide and early warning in advance using machine learning techniques. Introduction of Problem: Landslides due to the movement of soil mass are a big problem in India especially in Himachal Pradesh and Uttarakhand [1]. Landslides are natural hazards that often happen without warning and cause massive damage to property and life across the world. However, with unbelievable 11,000 deaths in the last 12 years, India tops the world in landslide deaths. According to the Geological Survey of India (GSI), in the year 2017, 12 landslides were reported in India. This year, the GSI has listed 23 events till August 2018 [2]. One way to overcome the landslide problem is to use machine learning to predict the landslide in advance. Previously there has been used some machine learning algorithm to predict the landslide. However, a comparison of ensemble and non-ensemble ML algorithms for debris-flow prediction has not been undertaken. So, in this paper, I would like to compare the ensemble and non-ensemble machine-learning algorithms to predict the landslide. Literature Review: Some researchers have applied machine learning to landslides. For example, Hao et al. [3] broke the landslide displacement into cycle terms and trend terms and combined with the periodicity characteristics of time series to analyze cycle items of landslide displacement. Dujuan et al. [4] used the Back Propagation (BP) neural network to predict its displacement based on the work of Hao. Qiang and Duan [5] proposed a time series analysis with capabilities of the forecasting complex systems in development trend and adopted timing analysis method to establish the ARIMA model and the CAR model for landslide displacement dynamic forecasts. Yesilnacar et al. [6] combined logistic regression and neural networks to overcome shortcomings of the statistical methods that could not effectively build models of complex geological disasters. Xiangenjun [7] used a rough set to dig out the inherent law of slope disaster activities from the historical slope data. Daifuchu [8] focused on the natural landslide spatial prediction in Hong Kong adopted two or single type to support vector machine for spatial prediction of landslide hazard and compared with Logistic regression models at the same time [9]. Methodology: Based on the literature review I found that there is no comparison of ensemble and nonensemble algorithms. So, in this paper I would like to compare the ensemble and non-ensemble algorithms for predicting the landslide ahead of the time. The ensemble algorithms that I will use are Random forest, Voting, Bagging and SMO with the non-ensemble algorithms like SARIMA, Holt-Winter, LSTM, and Autoregression in the comparison. After that I would like to analysis the result of ensemble and non-ensemble algorithm and conclude that which method is best for the landslide prediction.

Reference 1. Pande, R. K. (2006). Landslide problems in Uttaranchal, India: issues and challenges. Disaster Prevention and Management: An International Journal, 15(2), 247-255. 2. Landslide Recent Incidents - Geological Survey of India. Retrieved from https://gsi.gov.in

3. Hao,X.Y.,Hao,X.H,Xiong,H.M.,et al, JournalofEngineeringGeology,7(3):279-283, 1999. 4. Du, J., Yin, K.L., Chai, B., Chinese Journal of Rock Mechanics and Engineering,(09): 1783-1789, 2009.

5. Li, Q., Li, R.Y., Journal of Yangtze River Scientific Research Institute,22(6), 2005. 6. E.Yesilnacar, T.Topal. Engineering Geology, 79:251-266, 2005.

7. Wang, G.Y., Cui, H.L., Li, Q., Rock and Soil Mechanics, 30(8): 2418-2422, 2009. 8. Lin, D.C., An, F.P., Guo, Z.L., et al., Rock and Soil Mechanics, 32(1), 2011. 9. Jian Huang, Zhihuan Liu, and Ni Li. “Study on displacement prediction of landslide based on neural network “, ISSN: 0975-7384 CODEN(USA): JCPRC5.