Bag-of-words-based anomaly-detection principal component analysis and stochastic optimization for debris flow detection and evacuation planning

Abstract. Debris flows are natural disasters, with soil mass, rocks, and water traveling down a mountainside slope. Debris flows are extremely dangerous; their occurrence incurs huge losses to life and property. The purpose of this research is to develop debris flow detection and emergency evacuation systems. A bag-of-words model is established for analyzing the features of debris flow events, and an anomaly-detection principal component analysis (PCA) model is proposed to detect debris flow. Using real-time debris flow prediction and monitoring, a stochastic optimization model for evacuation planning is formulated. Case studies of debris flow detection in Shenmu village and Fengchiu, central Taiwan, are conducted. Shenmu village and Fengchiu are areas of high potential debris flow, and each has a population of around 800 people. The results show that combining bag-of-words and anomaly-detection PCA methods could predict 6 out of 8 occurrences of actual events, providing a prediction rate of 75 %. In addition, the models make 13 predictions, and 6 of them are correct, providing a prediction accuracy of 46 %. Optimal parameters (including window size, bag length, filter ratio of training data, and anomaly threshold) of the models are also examined to increase the accuracy of debris flow prediction.