Modelling the occurrence of gullies in rangelands of southwest Spain

Gully erosion has been recognized as an important soil degradation process in rangelands of southwest Spain. In this paper, a relatively new data mining technique called Multivariate Adaptive Regression Splines (MARS) was applied to construct a model capable of predicting the location of gullies. A large database was used to support the model composed of a target variable (presence or absence of gullies) and 36 independent variables related to topography, lithology, soils, rainfall, land use and vegetation cover. The performance of the model was evaluated using the Receiver Operating Characteristic (ROC) curve for five external datasets. The model had high predictive power, with values for the area under the ROC curve of the external validation datasets varying from 0·75 to 0·98 (1·0 being perfect prediction). The most important variables explaining the spatial distribution of gullies were lithology and soil type. Finally the model was compiled and implemented into a geographical information system to obtain maps of susceptible areas for gully erosion. These maps show that approximately 7% of the study area presents favourable conditions for the development of gullies. The results demonstrate that MARS constitutes a valuable model in geomorphic research and could also be a useful tool for assessing the impacts of changing climate and land use on gully erosion. Copyright © 2009 John Wiley & Sons, Ltd.

[1]  W. Graf.  The development of montane arroyos and gullies , 1979 .

[2]  Jean Poesen,et al.  Assessment of sidewall erosion in large gullies using multi-temporal DEMs and logistic regression analysis , 2004 .

[3]  R. Morgan,et al.  Threshold conditions for initiation of valley-side gullies in the Middle Veld of Swaziland , 2003 .

[4]  John Bell,et al.  A review of methods for the assessment of prediction errors in conservation presence/absence models , 1997, Environmental Conservation.

[5]  José A. Martínez-Casasnovas,et al.  Prediction of existing gully erosion in vineyard parcels of the NE Spain: a logistic modelling approach , 1999 .

[6]  J. Friedman.  Multivariate adaptive regression splines , 1990 .

[7]  D. Mcclung,et al.  Numerical avalanche prediction: Bear Pass, British Columbia, Canada , 2003 .

[8]  Jesús Muñoz,et al.  Comparison of statistical methods commonly used in predictive modelling , 2004 .

[9]  G. Valentine,et al.  Probabilistic assessment of volcanic hazard to radioactive waste repositories in Japan: Intersection by a dike from a nearby composite volcano , 2001 .

[10]  J. Deckers,et al.  World Reference Base for Soil Resources , 1998 .

[11]  G. Wahba.  Smoothing noisy data with spline functions , 1975 .

[12]  Violette Geissen,et al.  Superficial and subterranean soil erosion in Tabasco, tropical Mexico : Development of a decision tree modeling approach , 2007 .

[13]  Karel Vandaele,et al.  Gully Erosion: Importance and Model Implications , 1998 .

[14]  Peter Craven,et al.  Smoothing noisy data with spline functions , 1978 .

[15]  I. Prosser,et al.  Gully formation and the role of valley floor vegetation , 1994 .

[16]  D. Tarboton.  A new method for the determination of flow directions and upslope areas in grid digital elevation models , 1997 .

[17]  Philip S. Yu,et al.  Data Mining: An Overview from a Database Perspective , 1996, IEEE Trans. Knowl. Data Eng..

[18]  John P. Wilson,et al.  Use of terrain variables for mapping gully erosion susceptibility in Lebanon , 2007 .

[19]  C. C. Watson,et al.  Logistic analysis of channel pattern thresholds: meandering, braiding, and incising , 2001 .

[20]  Xingquan Zhu,et al.  Knowledge Discovery and Data Mining: Challenges and Realities , 2007 .

[21]  Ángel Manuel Felicísimo Pérez.  Modelos digitales del terreno: introducción y aplicaciones en las ciencias ambientales , 1994 .

[22]  S. Schnabel,et al.  Gully erosion, land use and topographical thresholds during the last 60 years in a small rangeland catchment in SW Spain , 2009 .

[23]  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 .

[24]  Lyle H. Ungar,et al.  A comparison of two nonparametric estimation schemes: MARS and neural networks , 1993 .

[25]  Arturo García Navarro,et al.  Mapa de suelos de la provincia de Cáceres: escala, 1:300.000 , 2002 .

[26]  S. Schnabel.  Soil erosion and runoff production in a small watershed under silvo-pastoral landuse (dehesas) in Extremadura, Spain , 1997 .

[27]  E. Steigner,et al.  A New Method for the Determination of Fluorine , 1964 .

[28]  J. Poesen,et al.  Erosion, flooding and channel management in Mediterranean environments of southern Europe , 1997 .

[29]  F. Gallart,et al.  Recent gully erosion in the El Cautivo badlands (Tabernas, SE Spain). , 2000 .

[30]  C. Thorne,et al.  Quantitative analysis of land surface topography , 1987 .

[31]  J. M. DeLeo,et al.  Receiver operating characteristic laboratory (ROCLAB): Software for developing decision strategies that account for uncertainty , 1993, 1993 (2nd) International Symposium on Uncertainty Modeling and Analysis.

[32]  Santiago Beguería,et al.  Validation and Evaluation of Predictive Models in Hazard Assessment and Risk Management , 2006 .

[33]  Padhraic Smyth,et al.  From Data Mining to Knowledge Discovery in Databases , 1996, AI Mag..