Landslides Disaster Prediction: A Case Study for Badulla District

Abstract

Landslides are the one of the most recurrent and prominent disaster 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. Artificial Neural Networks (ANNs) and Hidden Markov Model (HMM) are now widely used in many computer applications spanning multiple domains. This research examines the effectiveness of using Artificial Neural Networks and Hidden Markov Model in landslides predictions and the possibility of applying the modern technology to predict landslides in a prominent geographical area in Sri Lanka. A thorough survey was conducted using a questionnaire with the participation of resource persons from several national universities in Sri Lanka to identify and rank the associated factors for landslides in Sri Lanka. Then, data was analyzed using the SPSS software. It shows that rainfall is the factor which associated the most. Twelve factors were identified and the identified factors were divided into internal factors and external factors. 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. The ArcGIS 10 software was used to extract the internal factors; slope, lithology, soil material, distance from drainage by using digital elevation models which were created using existing maps. External factors were collected by using past data. These factors were used to recognize the possibility to occur landslides by using an ANN and HMM. The models acquire the relationship between the factors of landslide during the training session. These Models with landslide related factors, the inputs are trained to predict three classes namely, ‘landslide occurs’, ‘landslide does not occur’ and ‘landslide likely to occur’. Once trained, the models predict the most likely class for the prevailing data. Then, a prototype was built using the Mathlab® software. Finally compared two models with regards to prediction accuracy, False Acceptance Rates and False Rejection rates. This research indicates that the Artificial Neural Network could be used as a strong decision support system to predict landslides efficiently and effectively than Hidden Markov Model. Factors were identified with regard to all the districts in the country so this model can be applied for any District. To the best of our knowledge it is the first time that such a research has been conducted in Sri Lanka. Therefore, the outcome of this research will be of immense beneficial to the country.