The knowledge expression on debris flow potential analysis through PCA + LDA and rough sets theory: a case study of Chen-Yu-Lan watershed, Nantou, Taiwan

Debris flow is often performed through identifying and analyzing the soil condition, hydraulic, geomorphological factors and vegetation conditions. In the present study, a spatial information analysis system is combined with a linear statistical method (principle components analysis with linear discriminant analysis, PCA + LDA) and an advanced data mining technique (discrete rough sets, DRS) to investigate the debris flow occurrence based on geomorphological and vegetation conditions factors. The analyzed data sources include (1) digital elevation model: to investigate the variation in the landscape, and (2) remote sensing data: to analyze the vegetation and plant conditions on the ground surface. The objective of this research is to define a method with the ability to forecast the level of debris flow susceptibility through the parallel study of statistical outcomes (PCA + LDA) and data mining results (DRS). The outcomes from PCA + LDA are inadequate due to the thresholds of the influenced variables not being examined. In this study, the DRS approach not only showed satisfactory results for the thresholds of influenced variables in the study area, but also the occurrence rules of debris flow are generated. Finally, the results show superior classification accuracy (70.8% for debris flow occurrence) for the DRS method over those of PCA + LDA analysis (54.2% for debris flow occurrence) for the analysis of debris flow occurrence. Therefore, this is an encouraging preliminary approach in the hazard assessment of debris flow.

[1]  K. Auer,et al.  A statistical approach to evaluate debris avalanche activity in central Virginia , 1993 .

[2]  T. Lei,et al.  The comparison of PCA and discrete rough set for feature extraction of remote sensing image classification – A case study on rice classification, Taiwan , 2008 .

[3]  Jacob T. Mundt,et al.  Discrimination of hoary cress and determination of its detection limits via hyperspectral image processing and accuracy assessment techniques , 2005 .

[4]  A. Huete,et al.  A review of vegetation indices , 1995 .

[5]  T. Pierson,et al.  Flow characteristics of large eruption-triggered debris flows at snow-clad volcanoes: constraints for debris-flow models , 1995 .

[6]  C. F. Lee,et al.  Assessment of landslide susceptibility on the natural terrain of Lantau Island, Hong Kong , 2001 .

[7]  P. Lin,et al.  Hazard Assessment of Debris Flows by Statistical Analysis and GIS in Central Taiwan , 2006 .

[8]  Konstantinos N. Plataniotis,et al.  Regularized discriminant analysis for the small sample size problem in face recognition , 2003, Pattern Recognit. Lett..

[9]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

[10]  Fausto Guzzetti,et al.  Use of GIS Technology in the Prediction and Monitoring of Landslide Hazard , 1999 .

[11]  M. Pareschi,et al.  Volcaniclastic debris flows in the Clanio Valley (Campania, Italy): insights for the assessment of hazard potential , 2002 .

[12]  Tien-Yin Chou,et al.  A novel data mining technique of analysis and classification for landslide problems , 2009 .

[13]  J. Corominas,et al.  A GIS-Based Multivariate Statistical Analysis for Shallow Landslide Susceptibility Mapping in La Pobla de Lillet Area (Eastern Pyrenees, Spain) , 2003 .

[14]  E. Aronson,et al.  Theory and method , 1985 .

[15]  Michael R. Lyu,et al.  Comparative Studies on Feature Extraction Methods for Multispectral Remote Sensing Image Classification , 2005, 2005 IEEE International Conference on Systems, Man and Cybernetics.

[16]  J. Corominas,et al.  Assessment of shallow landslide susceptibility by means of multivariate statistical techniques , 2001 .

[17]  H. Wang,et al.  Comparative evaluation of landslide susceptibility in Minamata area, Japan , 2005 .

[18]  Landslide Risk Assessment in Italy: A Case Study in the Umbria-Marche Apennines , 2004 .

[19]  P. Frattini,et al.  Geomorphological and historical data in assessing landslide hazard , 2003 .

[20]  Modelling of Landslide-Triggering Factors - A Case Study in the Northern Apennines, Italy , 2004 .

[21]  C.-Y. Lin,et al.  WinBasin: Using improved algorithms and the GIS technique for automated watershed modelling analysis from digital elevation models , 2008, Int. J. Geogr. Inf. Sci..

[22]  Jian Yang,et al.  Feature fusion: parallel strategy vs. serial strategy , 2003, Pattern Recognit..

[23]  Josef Kittler,et al.  Pattern recognition : a statistical approach , 1982 .

[24]  Sinh Hoa Nguyen,et al.  Pattern Extraction from Data , 1998, Fundam. Informaticae.

[25]  A. K. Turner,et al.  Landslides : investigation and mitigation , 1996 .

[26]  Wen-Chieh Chou,et al.  Soil erosion prediction and sediment yield estimation: the Taiwan experience , 2002 .

[27]  Andrea Taramelli,et al.  An example of debris-flows hazard modeling using GIS , 2004 .

[28]  Manoj Pant,et al.  Landslide hazard mapping based on geological attributes , 1992 .

[29]  R. Soeters,et al.  Use of Geomorphological Information in Indirect Landslide Susceptibility Assessment , 2003 .

[30]  Jian Yang,et al.  Why can LDA be performed in PCA transformed space? , 2003, Pattern Recognit..

[31]  A. Ivakhnenko.  Heuristic self-organization in problems of engineering cybernetics , 1970 .

[32]  Wen-Chieh Chou,et al.  Assessment of vegetation recovery and soil erosion at landslides caused by a catastrophic earthquake: A case study in Central Taiwan , 2006 .

[33]  Y. Serengil,et al.  Cover and management factors for the Universal Soil-Loss Equation for forest ecosystems in the Marmara region, Turkey , 2005 .

[34]  Ming-Der Yang,et al.  Assessing debris-flow hazard in a watershed in Taiwan , 2002 .

[35]  E. C. Ellis,et al.  Source resolution of the fine carbonaceous aerosol by principal component-stepwise regression analysis. , 1988, Environmental science & technology.

[36]  Chyan-Deng Jan,et al.  Probabilistic analysis of landslide potential of an inclined uniform soil layer of infinite length: application , 2007 .

[37]  A. Hossein Sahoolizadeh,et al.  A New Face Recognition Method using PCA, LDA and Neural Network , 2008 .

[38]  Qiang Shen,et al.  Rough set-aided keyword reduction for text categorization , 2001, Appl. Artif. Intell..

[39]  Saro Lee,et al.  Landslide susceptibility mapping using GIS and the weight-of-evidence model , 2004, Int. J. Geogr. Inf. Sci..

[40]  M. Turrini,et al.  An objective method to rank the importance of the factors predisposing to landslides with the GIS methodology: application to an area of the Apennines (Valnerina; Perugia, Italy) , 2002 .

[41]  L. Vulliet,et al.  Using neural networks to predict slope movements. , 1996 .

[42]  David M. Cruden,et al.  LANDSLIDE TYPES AND PROCESSES , 1958 .

[43]  T. Chou,et al.  The knowledge rules of debris flow event: A case study for investigation Chen Yu Lan River, Taiwan , 2008 .

[44]  C. F. Lee,et al.  A spatiotemporal probabilistic modelling of storm‐induced shallow landsliding using aerial photographs and logistic regression , 2003 .

[45]  Saro Lee,et al.  Landslide susceptibility mapping in the Damrei Romel area, Cambodia using frequency ratio and logistic regression models , 2006 .

[46]  John W. Tukey,et al.  A Projection Pursuit Algorithm for Exploratory Data Analysis , 1974, IEEE Transactions on Computers.

[47]  W. Torgerson.  Multidimensional scaling: I. Theory and method , 1952 .

[48]  D. Varnes.  SLOPE MOVEMENT TYPES AND PROCESSES , 1978 .

[49]  D. Varnes,et al.  Landslide types and processes , 2004 .

[50]  Chjeng-Lun Shieh,et al.  Impact of Chi-Chi earthquake on the occurrence of landslides and debris flows: example from the Chenyulan River watershed, Nantou, Taiwan , 2004 .

[51]  L. Ermini,et al.  Artificial Neural Networks applied to landslide susceptibility assessment , 2005 .