Modelling of the factors affecting interrill erosion in pasture and forest landuses using artificial neural networks

Document Type : Complete scientific research article

Authors

1 Department of soil science, College of Agriculture, Vali-e-Asr University, Rafsanjan, Iran

2 3 Institute for Resource Management, Berlin, Germany

Abstract

Background and Objective: Interrill erosion is one of the most important types of erosion, in which various factors such as soil, runoff, and rainfall influence its process and rate. Few studies have been conducted using artificial neural networks (ANNs) to determine the factors affecting interrill erosion in Iran. Furthermore, no research has been carried out in Jiroft on this matter. Therefore, this study was conducted to evaluate the factors influencing interrill erosion using ANNs in four different regions around Jiroft in Kerman province.
Materials and Methods: For this research, 100 soil samples were collected from two pastures and two forest land uses at depths of 0-10 cm using a random sampling method. Some physical and chemical properties were determined. The amount of interrill erosion was measured using Kamphorst rainfall simulator. Modelling was performed using feedforward multi-layer perceptrons (MLP) with the error backpropagation and Levenberg-Marquardt training algorithm along with 11 soil characteristics in two scenarios. Hill sensitivity analysis was used to investigate the significance of the input variables.
Results: The results revealed that in the study areas, clay, silt, sand (0.05-2 mm), geometric standard deviation (σg), and geometric mean diameter (dg) of particles play a crucial role in interrill erosion while cementing agents such as organic matter (OM) and calcium carbonate equivalent (CCE) were less important. According to the results, the protected forest with high contents of sand as well as low amounts of silt, organic matter and calcium carbonate equivalent showed the lowest erosion rate (2.63 tons /ha). The R2 values for the test datasets in the scenario 1 (with input variables including soil acidity (pH), electrical conductivity (EC), bulk density (BD), organic matter, calcium carbonate equivalent, particulate organic matter (POM), sand, silt, and clay) were 0.81. Whereas the R2 values in the scenario 2 (with input variables such as pH, EC, BD, OM, CCE, POM, the dg and σg) were 0.72. In addition, root-mean-square error (RMSE) for the testing dataset in scenarios 1 and 2 were 0.77 and 1.14, respectively.
Conclusion: Both scenarios had almost the same accuracy in interrill erosion modeling. However, according to the values of R2 and RMSE of the data in scenario 1, this scenario showed better accuracy than scenario 2. In general, the results showed that the ANNs can estimate the amount of interrill erosion using appropriate input variables with high accuracy, and therefore it might be considered as a useful technique to estimate interrill erosion.

Keywords


1.Amiri, I., Sodaiezade, H., Mosleh Arani, A., Taie Semiromi, J., and Hakimzade, M.A. 2019. Autecology of Tecomella undulata (Roxb.) Seem in southernIran. J. Forest Pop. Res. 26: 4. 506-519. (In Persian)
2.Armstrong, A., and Quinton, J.N., Heng B.C.P., and Chandler, J.H. 2011. Variability of interrill erosion at low slopes. Earth Surface Processes and Landforms. 36: 1. 97-106.
3.Asadi, H., Moussavi, A., Ghadiri, H., and Rose, C.W. 2011. Flow-driven soil erosion processes and the size selectivity of sediment. J. Hydrol. 406: 1. 73-81.
4.Aslan, Z., Erdemir, G., Feoli, E.,Giorgi, F., and Okcu, D. 2019. Effects of Climate Change on Soil Erosion Risk Assessed by Clustering and Artificial Neural Network. Pure and applied geophysics. 176: 937-949.
5.Becvar, M. 2006. Sediment loadand suspended sediment concentration prediction. Soil and water research.1: 23-31.
6.Blake, G.R., and Hartge, K.H. 1986. Bulk density. In: Klute, A. (Ed.), Methods of Soil Analysis Part 1, Physical and Mineralogical Methods. Agron. Monogr. 9, 2nd ed. ASA and SSSA, Madison, WI, Pp: 364-367.
7.Calero, N., Barron, V., and Torrent, J. 2008. Water dispersible clay in calcareous soils of southwestern Spain. Catena. 74: 22-30.
8.Dhamge, N.R., Atmapoojya, S.L., and Kadu, M.S. 2012. Genetic algorithm driven ANN model for runoff estimation. Procedia Technology. 6: 501-508.
9.Fallahzade, J., and Hajabbasi, M.A. 2012. Land use effects on carbohydrate fractions total and particulate organic matter of forest soils in central Zagros Mountains. J. Appl. Sci. 12: 4. 387-392.
10.Gee, G.W., and Bauder, J.W. 1996. Particle-size analyses In: Klute, A. (Ed.), Methods of Soil Analyses. Part 1: Physical and Mineralogical Methods, 2nd ed. Agron. Monogr,vol. 9. ASA and SSSA, Madison, WI, Pp: 383-411.
11.Ghazanfarpour, N., Moradi, H.R., and Feiznia, S. 2011. Interrill sediment yield and erodibility in parts of Esfahan Segzi-Kuhpayeh rangelands using rainfall simulator. J. Water Soil Cons. 17: 4. 199-205. (In Persian)
12.Gholami, V., Booij, M.J., Nikzad Tehrani, E., and Hadian M.A. 2018. Spatial soil erosion estimation using an artificial neural network (ANN) and field plot data. Catena. 163: 210-218.
13.Golmohamadi, F., Nabiollahi, K., Taghizadeh-Mehrjardi, R., and Davari, M. 2017. Digital mapping of soil erodibility (Case study: Dehgolan, Kurdistan province). J. Water Soil Cons. 24: 6. 87-103. (In Persian)
14.Hengl, T., Huvelink, G.B.M., and Stein, A. 2004. A generic framework for spatial prediction of soil variablesbased on regression-kriging. Geoderma. 120: 1-2. 75-93.
15.Hill, M.C. 2000. Methods and guidelines for effective model calibration. Building partnerships, Pp: 1-10.

16.Hosseini, S.M., Mosaedi, A., Naseri, K., and Golkarian, A. 2012. Modeling the effect of Hill slope on features of rill erosion based on incomplete Gamma function in Ahmad-Abad, Mashhad.J. Water Soil. 26: 5. 1215-1225.(In Persian)

21.Licznar, P., and Nearing, M.A. 2003. Artificial neural networks of soil erosion and runoff prediction at the plot scale. Catena. 51: 2. 89-114.
22.Liu, D., She, D., Yu, S., Shao, G., and Chen, D. 2015. Rainfall intensity and slope gradient effects on sediment losses and splash from a saline-sodic soil under coastal reclamation. Catena. 128: 54-62.
23.Liu, G., Xu, W.N., Zhang, Q., and Xia, Zh. 2012. Interrill and Rill Erosion on Hillslope. Applied Mechanics and Materials. 170-173: 1344-1347.

24.McLean, E.Q. 1982. Soil pH and lime requirement. In: Page, A.L. Miller, R.H. Keeney, D.R (Eds). Methods of Soil Analysis, Part 2. Chemical and microbiological properties, 2nd Ed Agronomy. 9: 199-224.

25.Roades, J.D. 1996. Salinity: electrical conductivity and total dissolved solids. Method of soil analysis, Part 3: Chemical Methods. Madison. Wisconsin, USA, Pp: 417-436.
26.Robichaud, P.R., Wagenbrenner, J.W., and Brown, R.E. 2010. Rill erosion in natural and disturbed forests: 1. Measurements, Water resources research. 46 W10506: 1-14.
27.Roodab Paydar Consulting Engineers. 2011. Detailed studies of forest resources management plan in Tal Siah area, ministry of Agriculture, Pp: 1-50. (In Persian)
28.Sabznegar Afaq Co. 1999. Farrash rangeland design, ministry of Agriculture. (In Persian)
29.Saman Sabz Ariyan Consulting Engineers. 2008. Marghzar rangeland design, ministry of Agriculture, Pp: 1-60. (In Persian)
30.Sarkar, T., and Mishra, M. 2018. Soil erosion susceptibility mapping with the application of logistic regression and artificial neural network. J. Geovisual. Spat. Anal. 2: 8. https://doi.org/ 10.1007/s41651-018-0015-9.
31.Shahini Shamsabadi, M., Esfandiarpour-Borujeni, I., Mosleh, Z., Shirani, H., and Salehi, M.H. 2019. Error and uncertainty analysis in preparation of thematic maps using artificial neural network and environmental data (A case study: digital soil map of shahrekord plain). J. Geograph. Environ. Plan.
73: 23-36.
32.Sharifi, A., Shirani, H., Besalatpour, A.A., and Esfandiarpour-Borujeni, I. 2020. Effect of forest and pasture land uses on interrill erosion and some of soil physical properties in southern Iran. J. Water Soil. 34: 2. 455-469.
33.Shi, Z.H., Fang, N.F., Wu, F.Z.,Wang, L., Yue, B.J., and Wu, G.L. 2012. Soil erosion processes and sediment sorting associated with transport mechanisms on steep slopes.J. Hydrol. 454-455: 123-130.
34.Shirani, H. 2017. Artificial neural networks with an application in agricultural and natural resource science. Vali-E-Asr University of Rafsanjan Press, 320p. (In Persian)
35.Shirani, H., Hosseinifard, S.J., and Hashemipour, H. 2018. Factors affecting cadmium absorbed by pistachio kernel in calcareous soils, southeast of Iran. Science of the total environment.
616-617: 881-888.
36.Shirazi, M.A., and Boersma, L. 1984.A unifying quantitative analysisof soil texture. Soil Sci. Soc. Amer. J. 48: 142-147.
37.Singh, R.D., Lohani, A.K., and Kumar, R. 2012. Hydrological time series modeling: a comparison between adaptive neuro-fuzzy, neural network and autoregressive techniques. J. Hydrol. 442-443: 23-35.
38.Sparks, D.L. Ed. 1996. Methods of Soil Analysis, Part3. Chemical Methods. SSSA Book Series, vol. 5. American Society of Agronomy and Soil Science Society of America, Madison, WI, USA. 1390p.
39.Walkly, A., and Black, I.A. 1934. An examination of digestion methods for determining soil organic matter and a proposed modification of the chromic and titration. Soil Sci. Soc. Amer. J.
37: 29-38.
40.Wang, C., Wang, B., Wang, Y., Wang, Y., and Zhang, W. 2020. Improved interrill erosion prediction by considering the impact of the near- surface hydraulic gradient. Soil and Tillage Research. 203: 104687.
41.Wang, L., and Shi, Z.H. 2015. Size selectivity of eroded sediment associated with soil texture on steep slopes. Soil Sci. Soc. Amer. J. 79: 3. 917-929.
42.Zangiabadi, M., Rangavar, A., Rafahi, H.Gh., Shorafa, M., and Bihamta, M. 2010. Investigation of the most important factors affecting on soil erosion in Kalat semi-arid rangelands.J. Water Soil. 24: 4. 737-744.
43.Zema, D.A., Lucas-Borja, M.E.,Fotia, L., Rosaci, D., Sarne, G.M.L.,and Zimbone, S.M. 2020. Predictingthe hydrological response of a forest after wildfire and soil treatmentsusing an Artificial Neural Network. Computers and Electronics in Agriculture. 170: 105280.