Elsevier

CATENA

Volume 196, January 2021, 104902
CATENA

Soil erosion modeling using erosion pins and artificial neural networks

https://doi.org/10.1016/j.catena.2020.104902Get rights and content

Highlights

  • Erosion pins and ANNs were successfully used to assess the spatial variation of soil erosion.

  • Splash erosion is the dominant type of erosion in the study area compared to the erosion caused by surface runoff.

  • The highest soil erosion rates occur on the lower half of the hillslopes.

Abstract

Assessment of soil erosion is crucial for any long-term soil conservation plan. Traditional in-situ measurements provide a precise amount of erosion rate; however, the procedure is costly and time-consuming when applied over an extensive area. This study aimed to investigate the use of erosion pins and artificial neural networks (ANNs) to assess the spatial distribution of annual soil erosion rates in the mountainous areas of the north of Iran. First, annual surface erosion and splash erosion were measured using two types of erosion pins. Next, the variables affecting soil erosion (vegetation canopy, the shape of slope, slope gradient, slope length, and soil properties) were identified and estimated through field studies and analysis of a digital elevation model (DEM) and the data set were divided into three subsets of training, cross-validation, and testing. Seven artificial neural network algorithms were used and evaluated to estimate the annual soil erosion rates for the areas without recorded erosion data. Finally, the modeled values were mapped in GIS, and the longitudinal profiles of soil erosion were extracted. Findings showed that (1) Consideration should be given to the generalized feed forward (GFF) network, given the high accuracy rate (NMSE:0.1; R-sqr:0.9) compared to other tested ANN algorithms. (2) Vegetation canopy was found to be the most significant variable in annual soil erosion rate (R: −0.75 to −0.85) compared to other input variables. And (3) Annual measurements of erosion pins revealed that the splash erosion is higher (contributing 62 percent to total erosion) compared to surface runoff erosion (contributing 38 percent to total erosion).

Introduction

Soil erosion is one of the most important types of soil degradation, causing environmental concerns in many parts of the world (Luetzenburg et al., 2020, Li et al., 2020). Soil erosion is the movement and transport of soil by various agents, such as water, wind, and mass movement (Bullock, 2005). In the humid and semi-humid climatic regions such as the north of Iran, the dominant form of erosion is water erosion (Esmaeeli Gholzom and Gholami, 2012, Khaleghi and Varvani, 2018). Water erosion may occur as splash erosion, surface erosion, or stream erosion on the hillslopes and piping or gully erosions at foot slopes. Human activities can also result in erosion in two ways, directly through soil moving operations, such as quarrying, and indirectly whereby activities such as cultivation destabilize slope materials and accelerate erosion through the wind, water, or gravity.

The above-mentioned factors exacerbate soil degradation by reducing soil fertility and loss of vegetation cover in forests and rangelands and result in adverse effects on agricultural and food production as well as water resources through contamination and sedimentation in dam reservoirs (Aldrich et al., 2005, Pierson et al., 2007, Akay et al., 2008, Gholami and Khaleghi, 2013).

Various factors affect soil erosion including the amount and intensity of rainfall, land-use, vegetation cover, soil properties, and length and gradient of slopes (Yair and Lavee, 1974, Masson, 1971, Pastor and Castro, 1995, Martınez-Casasnovas, 1998, Uson, 1998, Di Stefano et al., 2000, Pickup and Marks, 2000).

Soil erosion has been investigated in numerous studies. Descroix and Poulenard (1995) demonstrated that soil erosion increases with the slope to some certain gradient (27%). Bohm and Gerold (1995) demonstrated that vegetation cover is the most significant compared to other controlling factors such as soil properties and slope gradient. Kirkby et al. (2005) concluded that the soil erosion rate on hillslopes generally is affected by the combination of slope and vegetation.

There are several methods for measuring soil erosion ​​on hillslopes, including field plots, erosion pins, or using empirical models. Field plots are used to estimate soil erosion or runoff from specific rainfall events or within a given time interval. The use of plots provides an accurate estimate with the choice of time intervals from a storm event to a monthly or annual time scale. However, field plots need continuous maintenance and reconstitution that makes the process costly and time-consuming.

Another method is to use erosion pins, which have been used in previous studies and proven to be a simple and efficient tool (Schumm, 1956, Emmett, 1965, Ranwell, 1964, Clayton and Tinker, 1971, Kirkby and Kirkby, 1974, Haigh, 1977, Shi et al., 2013, Boardman et al., 2015(. The erosion pins are cheaper and easier to use compared to field plots, and they are suitable for long time scales such as annual erosion rate; however, it is challenging to use erosion pins for estimating soil erosion in short time scales (e.g., a specific rainfall event or specific day) (Ireland, 1939, Emmett, 1965, Haigh, 1977, Loughran, 1989, Hancock et al., 2008, Boardman and Favis-Mortlock, 2016, Kearney et al., 2017(. The selection of technique or method of measurement depends on the type of erosion, the purpose, and the target accuracy of the measurement.

Numerous studies have been conducted to measure various forms of soil erosion using erosion pins (Boardman and Favis-Mortlock, 2016). According to Haigh (1977), the use of erosion pins in soil erosion measurements originated in the USA by Colbert, 1956, Schumm, 1956. They used erosion pins to estimate soil erosion rates in badlands. Erosion pins were also used to estimate various forms of erosions, such as riverbank erosion (Lawler, 1978, Lawler, 1991, Lawler, 1992, Lawler, 1993), down-land paths (Streeter, 1975, Summer, 1986), badland erosion (Clarke and Rendell, 2006, Nadal-Romero et al., 2011, Boardman et al., 2015, Hancock and Lowry, 2015), wind erosion in sand dunes (Jungerius et al., 1981, Jungerius and van der Meulen, 1989, Wiggs et al., 1995, Livingstone, 2003) and gully erosion (Harvey,1974). It was reported in several case studies that erosion pins are an efficient method to estimate soil erosion on hillslopes (Tervuren, 1990, Harden et al., 2009, Keay-Bright and Boardman, 2009). For example, Nadal-Romero et al. (2011) used and tested various methods to estimate sediments in Mediterranean badland areas. According to their results, erosion pins were the second-best method after gauging stations. Kumar Ghimire et al. (2013) used erosion pins to evaluate various types of erosion (e.g., gully erosion, sheet erosion, bank erosion, and landslides) in the Himalaya region. They demonstrated that the erosion rate in the Himalaya is significantly high compared to other regions.

Soil erosion measurement is an expensive and time-consuming process, and it can not be performed over an extensive study area. To address this issue, field-based measurement models can be used. These models are based on establishing a relationship between estimated soil erosion (as output or target) and affecting factors in soil erosion (e.g., slope, vegetation cover, soil properties) in the field plot or erosion pins area and applying those relationships to the rest of the study area with unknown erosion rates. Therefore, Modeling methods such as artificial neural networks (ANN)s in conjunction with field data can reduce the costs and workload of the process and enables us to estimate the soil erosion throughout the study area. ANNs have been widely used in hydrological and environmental modeling processes (Anctil and Rat, 2005, Isik et al., 2013, Gholami et al., 2018, Sahour et al., 2020, Alshehri et al., 2020). Rosa et al. (1999) evaluated the interaction between land-cover and land-use characteristics and soil erosion using decision trees and ANNs. Harris and Boardman (1998) used expert systems in conjunction with ANNs as an alternative paradigm to measurable process-based erosion modeling for the South Downs in England. Moreover, geographic information system (GIS) is a useful tool for mapping and analyzing the soil erosion intensity when coupled with ANNs (Martınez-Casasnovas, 1998, Dixon, 2004, Zhao et al., 2009, Rosas and Gutierrez, 2020).

The objective of this study is to model, map, and analyze the soil erosion using erosion pins and an optimum ANN coupled to a GIS and identify the critical hillslopes for soil conservation plan operations.

Section snippets

Study area

The study area is a portion of the Alborz Mountains in the north of Iran, extending between 36°05′ N to 37° N and 53°05′ E to 53°10′ E and has a semi-humid climate (Esmaeeli Gholzom and Gholami, 2012). The predominant pattern of precipitation in the area is rainfall and rarely snow (Tehrani et al., 2019). The majority of precipitation events (about 70 percent) occur during the cold seasons (winter and autumn). Spring and winter precipitation contribute to 20 and 10 presents of annual

Measurement of the annual soil erosion using erosion pins

As we mentioned earlier, we used erosion pins to measure annual soil erosion on the hillslope. We recorded the measurements one year after we established the pins in the study area. The values for surface erosion, splash erosion, and total erosion, as well as their corresponding input values for some arbitrary points, were presented in Table 1. According to the measurements, annual soil erosion in the study area was ranged from 0 to 33.6 kg.m−2 (average: 9.4 kg.m−2). The annual surface runoff

Discussion

In this study, the annual erosion rates were presented as splash erosion, surface runoff erosion, and total soil erosion. According to our correlation analysis, the most significant variables in soil erosion are vegetation canopy percentage, curvature (shape of the slope), slope length, slope gradient, and soil texture (Clay and sand percent), respectively. Among those variables, curvature, slope gradient, slope length, and sand value have a positive correlation (direct relationship) with soil

Conclusion

ANN-based models can be a powerful tool for estimating hydrological or soil erosion parameters. Nevertheless, what is essential in this regard is choosing a suitable method or algorithm. In the first step of estimating soil erosion, it is necessary to select the erosion measurement method according to the objectives of the study and the type of erosion that needs to be investigated. Both erosion pins and erosion plots are types of field-based measurements that have proven to be very effective

Declaration of Competing Interest

The authors declared that there is no conflict of interest.

Acknowledgments

We would like to thank the Natural Resources Organization and Watershed Management of Mazandaran for providing the topographic data.

References (79)

  • J. Li et al.

    Predicting the spatiotemporal variation in soil wind erosion across Central Asia in response to climate change in the 21st century

    Sci. Total Environ.

    (2020)
  • G. Luetzenburg et al.

    Climate and land use change effects on soil erosion in two small agricultural catchment systems Fugnitz-Austria

    Can Revull-Spain. Sci. Total Environ.

    (2020)
  • F.B. Pierson et al.

    Runoff and erosion after cutting western juniper

    Rangeland Ecol. Manage.

    (2007)
  • M.A. Rosas et al.

    Assessing soil erosion risk at national scale in developing countries: The technical challenges, a proposed methodology, and a case history

    Sci. Total Environ.

    (2020)
  • N. Samani et al.

    A simple neural network model for the determination of aquifer parameters

    J. Hydrol.

    (2007)
  • J. Sun et al.

    Simulated erosion using soils from vegetated slopes in the Jiufeng Mountains

    China. Catena.

    (2016)
  • Z. Zhang et al.

    Spatially explicit quantification of total soil erosion by RTK GPS in wind and water eroded croplands

    Sci. Total Environ.

    (2020)
  • Z. Zhao et al.

    Predict soil texture distributions using an artificial neural network model

    Comput. Electron. Agri.

    (2009)
  • F. Alshehri et al.

    Mapping the Distribution of Shallow Groundwater Occurrences Using Remote Sensing-Based Statistical Modeling over Southwest Saudi Arabia

    Remote Sensing

    (2020)
  • Anctil, F., Rat, A., 2005. Evaluation of neural networks streamflow forecasting on 47 watersheds. J. Hydrol. Eng .ASCE...
  • Boardman, J., Favis-Mortlock, D.T., Foster, IDL., 2015. A 13-year record of erosion on badland sites in the Karoo,...
  • J. Boardman et al.

    The use of erosion pins in geomorphology

    Geomorphological Techniques, Chap.

    (2016)
  • P. Bohm et al.

    Pedo-hydrological and sediment responses to simulated rainfall on soils of the Konya Uplands (Turkey)

    Catena.

    (1995)
  • Bullock , P., 2005. Climate change impact. Encyclopedia of Soils in the Environment. Cranfield University–Silsoe,...
  • M.L. Clarke et al.

    Process-form realtionships in southern Italian badlands: erosion rates and implications for landform evolution

    Earth Surf. Proc. Land.

    (2006)
  • L. Clayton et al.

    Rates of hillslope lowering in the Badlands of North Dakota. North Dakota University Water Resources Research Institute, Report W1–221-012-71. W73.09121.N.T.I.S

    PB

    (1971)
  • E.H. Colbert

    Rates of erosion in the Chinle Formation

    Plateau.

    (1956)
  • Descroix, L., Poulenard, J., 1995. Les formes d’érosion dans la Sierra Madre Ocidentale (Nord Ouest du Mexique). Bull....
  • C. Di Stefano et al.

    Slope curvature influence on soil erosion and deposition processes

    Water Resour. Res.

    (2000)
  • B. Dixon

    Prediction of groundwater vulnerability using an integrated GIS-based neuro-fuzy techniques

    J. Spa. hydrol.

    (2004)
  • W.W. Emmett

    The Virgil Network: methods of measurement and a sampling of data collected

    Int. Assoc. Sci. Hydrol. Publ.

    (1965)
  • H. Esmaeeli Gholzom et al.

    A comparison between natural forests and reforested lands in terms of runoff generation potential and hydrologic response (case study: Kasilian Watershed)

    Soil Water Res.

    (2012)
  • G. Gholami et al.

    The impact of vegetation on the bank erosion (case study: the Haraz river)

    Soil Water Res.

    (2013)
  • D. Gray

    Effect of slope shape on soil erosion

    J. civil environ. eng.

    (2016)
  • Foster, G.R., 2001. Keynote: soil erosion prediction technology for conservation planning. In: Stott, D.E., Mohtar,...
  • Haigh, M.J., 1977. The use of erosion pins in the study of slope evolution. In, Shorter Technical Methods (ll)....
  • G.R. Hancock et al.

    Estimation of soil erosion using field and modelling approaches in an undisturbed Arnhem land catchment, Northern Territory, Australia

    Geogr. Res.

    (2008)
  • G.R. Hancock et al.

    Hillslope erosion measurement–a simple approach to a complex process

    Hydrol. Process.

    (2015)
  • Harden, C.P., Foster, W., Morris, C., Chartrand, K.J., Henry, E., 2009. Rates and processes of streambank erosion in...
  • Cited by (57)

    View all citing articles on Scopus
    View full text