Predicting gully initiation: comparing data mining techniques, analytical hierarchy processes and the topographic threshold
作者： Tal Svoray , Evgenia Michailov , Avraham Cohen , Lior Rokah , Arnon Sturm
DOI: 10.1002/ESP.2273
关键词: Reliability (statistics) 、 Analytic hierarchy process 、 Spatial database 、 Expert system 、 Mathematics 、 Variable (computer science) 、 Soil resistance 、 Data mining 、 Decision tree 、 Analytical hierarchy
摘要: Predicting gully initiation at catchment scale was done previously by integrating a geographical information system (GIS) with physically based models, statistical procedures or knowledge-based expert systems. However, the reliability and validity of applying these are still questionable. In this work, data mining (DM) procedure on decision trees applied to identify areas risk. Performance compared analytic hierarchy process (AHP) commonly used topographic threshold (TT) technique. A spatial database test composed target variable (presence absence initial points) ten independent environmental, climatic human-induced variables. The following findings emerged: using same input layers, DM provided better predictive ability points than application both AHP TT. main difference between TT very high overestimation inherent in addition, minimum slope observed for soil detachment 2°, whereas other studies it is 3°. This could be explained resistance, which substantially lower agricultural fields, while most unploughed soil. Finally, rainfall intensity events >62.2 mm h-1 (for period 30 min) were found have significant effect initiation. Copyright © 2012 John Wiley & Sons, Ltd.
sci-hub.se 参考文章(59)
Charles E. Metz, Pu-Lan Wang, Helen B. Kronman, A New Approach for Testing the Significance of Differences Between ROC Curves Measured from Correlated Data Information Processing in Medical Imaging. pp. 432- 445 ,(1984) , 10.1007/978-94-009-6045-9_25
David G Tarboton, Rafael L Bras, Ignacio Rodriguez-Iturbe, The analysis of river basins and channel networks using digital terrain data Massachusetts Institute of Technology. ,(1989)
John C. Platt, Fast training of support vector machines using sequential minimal optimization Advances in kernel methods. pp. 185- 208 ,(1999)
Gregory Piatetsky-Shapiro, Usama M. Fayyad, Padhraic Smyth, From data mining to knowledge discovery: an overview knowledge discovery and data mining. pp. 1- 34 ,(1996)
Christopher M. Bishop, Neural networks for pattern recognition ,(1995)
Mark A. Hall, Ian H. Witten, Eibe Frank, Data Mining: Practical Machine Learning Tools and Techniques ,(1999)
Gary M. Weiss, Mining with Rare Cases The Data Mining and Knowledge Discovery Handbook. pp. 747- 757 ,(2005) , 10.1007/978-0-387-09823-4_38
Chang Shu, Donald H. Burn, Artificial neural network ensembles and their application in pooled flood frequency analysis Water Resources Research. ,vol. 40, ,(2004) , 10.1029/2003WR002816
J. R. Ni, Y. K. Li, Approach to soil erosion assessment in terms of land-use structure changes Journal of Soil and Water Conservation. ,vol. 58, pp. 158- 169 ,(2003)
J. R. Quinlan, Bagging, boosting, and C4.S national conference on artificial intelligence. pp. 725- 730 ,(1996)