Mapping soil erosion rates using self-organizing map (SOM) and geographic information system (GIS) on hillslopes

Assessment of soil erosion is necessary for any long-term soil conservation plan, yet, the procedure is costly and time-consuming when applied to a large domain. Using a portion of the Alborz mountains in the north of Iran as a test site, a methodology was developed and tested based on a self-organizing map. First, annual soil erosion rates were measured on a hillslope in the study area through the installation of 120 erosion pins. Soil erosion controlling factors (slope gradient, slope length, slope shape, vegetation canopy, and the percentage of clay, silt, and sand) were determined through analysis of a digital elevation model (DEM) and field studies. Then, the data were normalized and divided into three subsets of training, cross-validation, and testing subsets. Then, a self-organizing map (SOM) was constructed to establish a relationship between soil erosion and its controlling factors. The SOM network was trained using the training and cross-validation subset and was evaluated on the testing subset using statistical coefficients (NMSE and R-squared). The evaluation of the SOM on the testing subset showed its high performance in the soil erosion modeling (NMSE = 0.1 test R-squared = 0.9). Next, the tested SOM was fit to the input variables to model the annual soil erosion rate across the study area. Finally, the modeled values were exported to the geographic information system (GIS) to generate the final map. The generated soil erosion map was verified by comparing the estimated soil erosion rates on the map with the recorded values of 11 erosion pins.

[1]  A. Kawamura,et al.  Evaluation of sedimentation vulnerability at small hillside reservoirs in the semi-arid region of Tunisia using the Self-Organizing Map , 2010 .

[2]  J. Boardman,et al.  A 13‐year record of erosion on badland sites in the Karoo, South Africa , 2015 .

[3]  Martijn J. Booij,et al.  Spatial soil erosion estimation using an artificial neural network (ANN) and field plot data , 2018 .

[4]  R. Aalto,et al.  Effects of gradient, distance, curvature and aspect on steep burned and unburned hillslope soil erosion and deposition , 2017 .

[5]  M. Clarke,et al.  Process–form relationships in Southern Italian badlands: erosion rates and implications for landform evolution , 2006 .

[6]  A. Tarquis,et al.  Self-organizing map of soil properties in the context of hydrological modeling , 2020 .

[7]  R. Adams,et al.  Economics of Western Juniper Control in Central Oregon , 2005 .

[8]  Bin Zhang,et al.  Effect of vegetation restoration on soil and water erosion and nutrient losses of a severely eroded clayey Plinthudult in southeastern China , 2004 .

[9]  Massimiliano Pontil,et al.  Support Vector Machines: Theory and Applications , 2001, Machine Learning and Its Applications.

[10]  Fan-Rui Meng,et al.  Predict soil texture distributions using an artificial neural network model , 2009 .

[11]  Brian S. Penn,et al.  Using self-organizing maps to visualize high-dimensional data , 2005, Comput. Geosci..

[12]  Ali Akbar Safavi,et al.  A simple neural network model for the determination of aquifer parameters , 2007 .

[13]  David S. G. Thomas,et al.  Dune mobility and vegetation cover in the Southwest Kalahari desert , 1995 .

[14]  J. Boardman,et al.  Evidence from field-based studies of rates of soil erosion on degraded land in the central Karoo, South Africa , 2009 .

[15]  Mohamed Sultan,et al.  Statistical Applications to Downscale GRACE-Derived Terrestrial Water Storage Data and to Fill Temporal Gaps , 2020, Remote. Sens..

[16]  Erkan Aydar,et al.  Clustering of volcanic ash arising from different fragmentation mechanisms using Kohonen self-organizing maps , 2007, Comput. Geosci..

[17]  G. Hancock,et al.  Hillslope erosion measurement—a simple approach to a complex process , 2015 .

[18]  Orhan Erdaş,et al.  Estimating sediment yield from a forest road network by using a sediment prediction model and GIS techniques , 2008 .

[19]  I. Livingstone.  A twenty‐one‐year record of surface change on a Namib linear dune , 2003 .

[20]  P. Zander,et al.  Soil degradation, farming practices, institutions and policy responses: An analytical framework , 2011 .

[21]  K. Kipfmueller,et al.  Reconstructed Temperature And Precipitation On A Millennial Timescale From Tree-Rings In The Southern Colorado Plateau, U.S.A. , 2005 .

[22]  J. Nicolau,et al.  Plot‐scale effects on runoff and erosion along a slope degradation gradient , 2010 .

[23]  Mohamed Sultan,et al.  Mapping the Distribution of Shallow Groundwater Occurrences Using Remote Sensing-Based Statistical Modeling over Southwest Saudi Arabia , 2020, Remote. Sens..

[24]  Xinxiao Yu,et al.  Simulated erosion using soils from vegetated slopes in the Jiufeng Mountains, China , 2016 .

[25]  Xin-bao Zhang,et al.  Comparison of the soil losses from (7)Be measurements and the monitoring data by erosion pins and runoff plots in the Three Gorges Reservoir region, China. , 2011, Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine.

[26]  G. Gerold,et al.  Pedo-hydrological and sediment responses to simulated rainfall on soils of the Konya uplands (Turkey) , 1995 .

[27]  O. J. Vrieze,et al.  Kohonen Network , 1995, Artificial Neural Networks.

[28]  Vito Ferro,et al.  Slope curvature influence on soil erosion and deposition processes , 2000 .

[29]  Markus Weiler,et al.  Storage of water on vegetation under simulated rainfall of varying intensity , 2006 .

[30]  Donald Gray.  Effect of Slope Shape on Soil Erosion , 2016 .

[31]  Mark A. Nearing,et al.  Artificial neural networks of soil erosion and runoff prediction at the plot scale , 2003 .

[32]  V. Gholami,et al.  The impact of vegetation on the bank erosion (Case study: The Haraz River) , 2018 .

[33]  Vahid Nourani,et al.  Emotional ANN (EANN) and Wavelet-ANN (WANN) Approaches for Markovian and Seasonal Based Modeling of Rainfall-Runoff Process , 2018, Water Resources Management.

[34]  J. Moeyersons.  Soil loss by rainwash: a case study from Rwanda. , 1990 .

[35]  Gwo-Fong Lin,et al.  Development of a support‐vector‐machine‐based model for daily pan evaporation estimation , 2012 .

[36]  M. J. Booij,et al.  Trend analysis of hydro-climatic variables in the north of Iran , 2019, Theoretical and Applied Climatology.

[37]  M. Sultan,et al.  Tracing Holocene channels and landforms of the Nile Delta through integration of early elevation, geophysical, and sediment core data , 2020 .

[38]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[39]  Rajib Maity,et al.  Potential of support vector regression for prediction of monthly streamflow using endogenous property , 2010 .

[40]  Jichun Wu,et al.  Using support vector machines to predict cation exchange capacity of different soil horizons in Qingdao City, China , 2014 .

[41]  Júlia Seixas,et al.  Vulnerability of water resources, vegetation productivity and soil erosion to climate change in Mediterranean watersheds , 2008 .

[42]  Carolina Boix-Fayos,et al.  Measuring soil erosion by field plots: understanding the sources of variation , 2006 .

[43]  J.-M. Masson.  L'érosion des sols par l'eau en climat méditerranéen. Méthodes expérimentales pour l'étude des quantités érodées à l'échelle du champ , 1972 .

[44]  Chi Zhang,et al.  Predicting the spatiotemporal variation in soil wind erosion across Central Asia in response to climate change in the 21st century. , 2019, The Science of the total environment.

[45]  M. J. Kirby,et al.  Surface wash at the semi-arid break in slope , 1974 .

[46]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[47]  W. H. Wischmeier,et al.  Predicting rainfall erosion losses : a guide to conservation planning , 1978 .

[48]  E. Baafi,et al.  Application of artificial neural network coupled with genetic algorithm and simulated annealing to solve groundwater inflow problem to an advancing open pit mine , 2016 .

[49]  Stuart P. Hardegree,et al.  Runoff and Erosion After Cutting Western Juniper , 2007 .

[50]  D. Lawler.  A New Technique for the Automatic Monitoring of Erosion and Deposition Rates , 1991 .

[51]  D. Nikkami,et al.  Assessing dominant factors affecting soil erosion using a portable rainfall simulator , 2008 .

[52]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[53]  M. Mokarram,et al.  Using self-organizing maps for determination of soil fertility (case study: Shiraz plain) , 2017 .

[54]  J. Poesen,et al.  Scale-dependency of sediment yield from badland areas in Mediterranean environments , 2011 .

[55]  G. Hancock,et al.  Estimation of Soil Erosion Using Field and Modelling Approaches in an Undisturbed Arnhem Land Catchment, Northern Territory, Australia , 2008 .

[56]  Friedrich Quiel,et al.  Geomorphometric feature analysis using morphometric parameterization and artificial neural networks , 2008 .

[57]  C. Harden,et al.  Rates and Processes of Streambank Erosion in Tributaries of the Little River, Tennessee , 2009 .

[58]  K. P. Bartsch,et al.  Using Empirical Erosion Models and GIS to Determine Erosion Risk at Camp Williams, Utah , 2002 .

[59]  L. Bracken,et al.  The influence of rainfall distribution and morphological factors on runoff delivery from dryland catchments in SE Spain , 2005 .

[60]  M. Subašić,et al.  Using self-organizing maps in the visualization and analysis of forest inventory , 2012 .

[61]  Stefan Hinz,et al.  Supervised and Semi-Supervised Self-Organizing Maps for Regression and Classification Focusing on Hyperspectral Data , 2019, Remote. Sens..

[62]  S. Schumm.  EVOLUTION OF DRAINAGE SYSTEMS AND SLOPES IN BADLANDS AT PERTH AMBOY, NEW JERSEY , 1956 .

[63]  T. Kohonen.  Self-organized formation of topographically correct feature maps , 1982 .

[64]  M. A. Nearingb,et al.  Artificial neural networks of soil erosion and runoff prediction at the plot scale , 2003 .

[65]  J. McNair,et al.  Measuring Streambank Erosion: A Comparison of Erosion Pins, Total Station, and Terrestrial Laser Scanner , 2018, Water.

[66]  G. Pickup,et al.  Identifying large‐scale erosion and deposition processes from airborne gamma radiometrics and digital elevation models in a weathered landscape , 2000 .

[67]  D. Higaki,et al.  Estimation of Soil Erosion Rates and Eroded Sediment in a Degraded Catchment of the Siwalik Hills, Nepal , 2013 .

[68]  S. Kearney,et al.  Improving the utility of erosion pins: absolute value of pin height change as an indicator of relative erosion , 2017 .