Performance of Hidden Markov Model in Landslide Prediction
2013-05-06 11:16:24   来源：   评论：0 点击：

Abstract—Landslides are most recurrent and prominent disasters in Sri Lanka. Sri Lanka has been subjected to a number of extreme landslide disasters that resulted in a significant loss of life, material damage, and distress. It is required to explore a solution towards preparedness and mitigation to reduce recurrent losses associated with landslides. My objective of this research was to examine the effectiveness of using Hidden Markov Model in landslides predictions and to apply the newly developed techniques to the study area of Badulla in Sri Lanka. A thorough survey was conducted with the participation of resource persons from several national universities in Sri Lanka to identify and rank the influencing factors for landslides. Landslide database was created using existing topographic; soil, drainage, land cover maps and historical data. The landslide related factors which include external factors (Rainfall, Number of Previous Occurrences and Influence of Construction) and internal factors (Soil Material, Geology, Land Use, Curvature, Soil Texture, Slope, Aspect, Soil Drainage, and Soil Effective Thickness) were extracted from the landslide database. Then probabilities of those factors are used to recognize landslides by using Hidden Markov Model based on Viterbi algorithm. In this model which consist of the landslide related factors as observations will be trained to predict three states namely, ‘landslide occurs’, ‘landslide does not occur’ and ‘landslide likely to occur’. Once trained, the model will be able to predict the most likely class for the prevailing data. This research indicates that Hidden Markov Model was turned out to be an effective tool in landslides prediction efficiency.

Index Terms—Landslides Prediction, Hidden Markov Model, landslide related factors

Cite: L. D. C. S. Subhashini and H. L. Premaratne, "Performance of Hidden Markov Model in Landslide Prediction," Lecture Notes on Information Theory, Vol.1, No.1, pp. 34-38, March 2013. doi: 10.12720/lnit.1.1.34-38