Prediction of soil salinity using tree regression and artificial neural network in Ghorveh soils, Kurdistan Province

Document Type : Complete scientific research article

Authors

1 Kurdistan university

2 Ardakan University

Abstract

Background and objectives: Soil salinity is one of the major problems in arid and semi-arid area. In this condition, soluble salts accumulate in the soil surface and reduce yield and soil fertility. Soils survey and mapping can help to improve these soils. The investigation of variability of soil salinity using traditional methods is expensive and time consuming. Therefore, one of the ways to solve this challenge is using digital soil mapping that soil characteristics were mapped using auxiliary data. The aim of this research is using tree regression (TR) and artificial neural network (ANN) models and auxiliary data to prepare soil salinity map.
Materials and methods: Using Hypercube soil sampling method, 100 soil samples in depths 0-30 cm of Ghorveh soils, Kurdistan Province (covers 30000 ha) were taken and soil electrical conductivity was measured. Auxiliary data in this study were terrain attributes and Landsat 8 ETM+ data. Terrain parameters (include 15 parameters) and salinity index (SI) and normalized difference vegetative index (NDVI) were computed and extracted using SAGA and ArcGIS software, respectively. To make a relationship between soil salinity and auxiliary data, TR and ANN models were applied and were validated using cross validation method. Finally, soil salinity map were made using better model.
Results: To predict soil salinity, auxiliary variables include salinity index, wetness index, index of valley bottom flatness, NDVI index, Band 3, and Band 7 were the most important. The results of the study showed that ANN model (0.70, 0.036 and 0.190, respectively for determination of coefficient, mean error, and root mean square root) has more accuracy compared to TR model to predict soil salinity. Soil salinity content ranged between 0.23 to 6.93 dSm1 and the highest content of soil salinity located in central regions (lowland and bare land). In these central regions, auxiliary data include salinity index, index of valley bottom flatness, wetness index, band 7 and band 3 had the highest values and NDVI index had the lowest values.
Conclusion: Salinity index is the most important auxiliary data to predict soil salinity of the study area. Strong link between soil data and auxiliary data can impact on the accuracy of the model. In general, the results showed that pedometrics techniques in a wide range can be used for digital mapping of soil properties. It is suggested ANN model and auxiliary data such as terrain attributes and satellite images were applied to prepare map of soil properties in future studies.

Keywords


1.Abdinam, A. 2004. An investigation on preparing of the soil salinity map using correlation
method between imagery and soil salinity data in the Qazvin plain. J. Pazhouhesh and
Sazandegi. 64: 33-38. (In Persian)
2.Adhikari, K., Minasny, B., Greve, B.G., and Greve, M.H. 2014. Constructing a soil class map of
Denmark based on the FAO legend using digital techniques. Geoderma. 214 -215: 101-113.
3.Azhirabi, R., Kamkar, B., and Abdi, O. 2015. Comparison of different indices adopted from
Landsat images to map soil salinity in the army field of Gorgan. J. Soil Manage. Sust. Prod.
5: 1. 173-176. (In Persian)
4.Breiman, L., Friedman, J.H., Olshen, R.A., and Stone, C.J. 1984. Classification and
Regression Trees. Chapman & Hall, New York, 355p.
5.Brus, D.J., Kempen, B., and Heuvlink, G.B.M. 2011. Sampling for validation of digital soil
maps. Eur. J. Soil Sci. 62: 394-407.
6.Dai, P.F., Qigang, Z., Zhiqiang, L.V., Xuemei, W., and Gangcai, W.L. 2014. Spatial
prediction of soil organic matter content integrating artificial neural network and ordinary
kriging in Tibetan Plateau. Ecol. Ind. 45: 184-194.
7.Farifte, J., Farshad, A., and George, R.J. 2005. Assessing salt - affected soils using remote
sensing, solute modeling, and geophysics. Geoderma. 130: 191-206.
8.Grinand, C., Arrouays, D., Laroche, B., and Martin, M.P. 2008. Extrapolating regional soil
landscapes from an existing soil map: sampling intensity, validation procedures, and
integration of spatial context. Geoderma. 143: 180-190.
9.Hengel, T., Rossiter, D.G., and Stein, A. 2003. Soil sampling strategies for spatial prediction
by correlation with auxiliary maps. Geoderma. 120: 75-93.
10.Hengl, T., Toomanian, N., Reuter, H., and Malakouti, M.J. 2007. Methods to interpolate soil
categorical variables from profile observations: Lessons from Iran. Geoderma. 140: 417-427.
11.Heung, B., Bulmer, C.E., and Schmidt, M.G. 2014. Predictive soil parent material mapping
at a regional-scale: a random forest approach. Geoderma. 214-215: 141-154.
12.Jafari, A., Khademi, H., Finke, P., Wauw, J.V.D., and Ayoubi, S. 2014. Spatial prediction of
soil great groups by boosted regression trees using a limited point dataset in an arid region,
southeastern Iran. Geoderma. 232-234: 148-163.
13.Kempen, B., Brus, D.J., Heuvelink, G.B.M., and Stoorvogel, J.J. 2009. Updating the
1:50,000 Dutch soil map using legacy soil data: A multinomial logistic regression approach.
Geoderma. 151: 311-326.
14.Kheir, R.B., Greve M.H., Abdallah, C., and Dalgaard, T. 2010. Spatial soil zinc content
distribution from terrain parameters: A GIS-based decision-tree model in Lebanon. Environ.
Pollut. 158: 520-528.
15.Marcel, G.S., Feike, J.L., Martinus, T., and Van Genuchten, H. 1998. Neural Network
Analysis for Hierarchical Prediction of Soil Hydraulic Properties. Soil Sci Soc. Am. J.
62: 847-855.
16.McBratney, A.B., Odeh, I.O.A., Bishop, T.F.A., Dunbar, M.S., and Shatar, T.M. 2000.
An overview of pedometric techniques for use in soil survey. Geoderma. 97: 293-327.
17.McBratney, A.B., Santos, M.L.M., and Minasny, B. 2003. On digital soil mapping.
Geoderma. 117: 3-52.
18.Metternicht, G., and Zinck, J.A. 2004. Remote sensing of soil salinity: Potentials and
constraints. Remote Sens Environ. 64: 33-38.
19.Minasny, B., and McBratney, A. 2002. The method for fitting neural network parametric
pedotransfer functions. Soil Sci. Soc. Am. J. 66: 2. 352-361.
20.Minasny, B., and McBratney, A.B. 2006. A conditioned Latin hypercube method for
sampling in the presence of ancillary information. Comput. Geosci. 32: 1378-1388.
21.Nosrati, H., and Eftekhari, M. 2014. A new approach for variable selection using fuzzy logic.
Computational Intelligence in Electrical Engineering. 4: 71-83. (In Persian)
22.Pahlavan-Rad, M.R., Toomanian, N., Khormali, F., Brungard, C.W., Komaki, C.B., and
Bogaert. P. 2014. Updating soil survey maps using random forest and conditioned Latin
hypercube sampling in the loess derived soils of northern Iran. Geoderma. 232-234: 97-106.
23.Piccini, C., Marchetti, A., and Francaviglia. R. 2014. Estimation of soil organic matter by
geostatistical methods: use of auxiliary information in agricultural and environ-mental
assessment. Ecol. Ind. 36: 301-314.
24.Sparks, D.L., Page, A.L., Helmke, P.A., Leoppert, R.H., Soltanpour, P.N., Tabatabai, M.A.,
Johnston, G.T., and Summer, M.E. 1996. Methods of Soil Analysis. Soil. Sci. Soc. Am. J.
Madison, Wisconsin.
25.Tajgardan, T., Aubi, Sh., Shatai, Sh., and Khormali, F. 2009. Mapping soil surface salinity
using remote sensing data of ETM+. (Case study: North of Agh Ghala, Golestan province). J.
Soil Water Cons. 88: 9-15. (In Persian)
26.Taghizadeh-Mehrjardi, R., Nabiollahi, K., Minasny, B., and Triantafilis, J. 2015. Comparing
data mining classifiers to predict spatial distribution of USDA-family soil groups in Baneh
region, Iran. Geoderma. 253-254: 67-77.
27.Taghizadeh-Mehrjardi, R. 2016. Modern concepts in Soil Science (PEDOMETRICS).
Ardakan Univ. Press, 311p.
28.Taghizadeh-Mehrjardi, R., Minasny, B., Sarmadian, F., and Malone, B.P. 2014. Digital
mapping of soil salinity in Ardakan region, central Iran. Geoderma. 213: 15-28.
29.Taghizadeh-Mehrjardi, R., Nabiollahi, K., and Kerry, R. 2016. Digital mapping of soil
organic carbon at multiple depths using different data mining techniques in Baneh region,
Iran. Geoderma. 253-254: 67-77.
30.Taghizadeh-Mehrjardi, R., Sarmadian, F., Savaghebi, G.H., Omid, M., Tomanian, N., Rosta,
M.J., and Rahimian, M.H. 2013. The comparison of efficiency of neuro-fuzzy, genetic
algoritm, neural network an multivariate regression models to prediction of soil salinity
(Case study: Ardakan). J. Natur. Resour. 66: 2. 207-222. (In Persian)
31.Vasques, G.M., Dematte, J.A.M., Viscarra Rossel, R.A., Ramirez-Lopez, L., and Terra, F.S.
2014. Soil classification using visible/near-infrared diffuse reflectance spectra from multiple
depths. Geoderma. 223-225: 73-78.
32.Veronesi, F., Corstanje, R., and Mayr, T. 2014. Landscape scale estimation of soil carbon
stock using 3D modeling. Sci. Total Environ. 487: 578-586.