Spatial modeling of soil saturation percentage using machine learning methods in Sistan plain

Jamalzehi Samareh, Younes; Shahriari, Ali; Pahlavan-Rad, Mohammad Reza; Ziaei Javid, Alireza; Bameri, Abolfazl

doi:10.22034/jelsa.2025.479520.1087

Spatial modeling of soil saturation percentage using machine learning methods in Sistan plain

Document Type : Original research article

Authors

Younes Jamalzehi Samareh ¹

Ali Shahriari ²

Mohammad Reza Pahlavan-Rad ³

Alireza Ziaei Javid ⁴

Abolfazl Bameri ²

¹ M.Sc Graduate of Soil Science, Department of Soil Science and Engineering, University of Zabol, Zabol, Iran

² Department of Soil Science and Engineering, University of Zabol, Zabol, Iran

³ Soil and Water Research Department, Golestan Agricultural and Natural Resources Research and Education Center, AREEO, Gorgan, Iran

⁴ Researcher, Devision of Soil Formation, Classification and Survey Researches, Soil and Water Research Institute, Karaj, Iran

10.22034/jelsa.2025.479520.1087

Abstract

Soil maps are an urgent need for different land users and decision-makers. In recent years, attention to digital soil mapping has greatly increased, but most studies have focused on surface soil, even though land users are faced with the three-dimensional (3D) structure of soil. Saturation percentage (SP) is one of the physical attributes of soil moisture, which can be considered in land management, especially in the direction of soil water retention in connection with other attributes, in arid areas. Therefore, the present study was conducted with the aim of digital mapping of SP in 3D using some machine learning methods in the Sistan Plain, which is located on the Hirmand River delta in a hyper-arid region. To carry out this research, the information from 576 soil profiles located in the Sistan Plain was used and the percentage of saturated soil moisture was measured using the standard method at depths of 0-15, 15-30, 30-60, and 60-100 cm using the weighted average method. Random forest (RF), quantile regression forest (QRF), and cubist methods were used for spatial modeling. The results showed that the variables derived from remote sensing showed a significant correlation with the SP parameter only at the first and second depths, which were close to the ground surface, but the variables derived from DEM had a significant correlation at all depths. These variables were mainly related to alluvial activities, which had the greatest effect on soil changes in the studied area. Among the models, the RF method showed the best performance for spatial modeling of SP in all depths. The 3D modeling of the percentage of SP showed that the value of SP is the lowest in the south and medium in the middle of the area, and the highest in the north of the Sistan plain at the edge of the Hamoun wetlands. SP value is repeated with the same spatial trend, but the average value of SP increases from the surface to the depth. It seems that the changes in this attribute are in line with the 3D changes in the soil texture components in the region. Based on the results of the three-dimensional zoning of SP, it could be recommended that in the northern areas of the Sistan Plain, irrigation should be done with a longer time interval than in the southern regions for the same agricultural products. In the fields of natural resources, to manage vegetation and especially to deal with wind erosion, plants with shallow and deep roots in the northern regions, and trees and plants with deep roots in the southern regions can be considered. Machine learning methods, especially RF, can be effective in preparing digital and 3D maps of soil characteristics and can help different land users manage their land better.

Highlights

RF model excels in 3D SP mapping in Sistan Plain, outperforming QRF and Cubist.
SP lowest in south, highest in north near Hamoun wetlands, rises with depth.
DEM variables key for SP at all depths; RS variables effective only at 0-30 cm.
SP aligns with soil texture changes, linked to alluvial activity in hyper-arid area.
Suggests longer irrigation intervals in north, deep-root plants in south for management.

Keywords

Deltaic soils

Hyper-arid region

Land management

Random forest

Adeniyi, O.D., Bature, H., & Mearker, M. A. (2024). Systematic Review on Digital Soil Mapping Approaches in Lowland Areas. Land, 13, 379. https://doi.org/10.3390/land13030379.

Agbu, P. A., Fehrenbacher, D. J., & Jansen, I. J. (1990). Soil property relationships with SPOT satellite digital data in east central Illinois. Soil Science Society of America Journal, 54(3), 807-812. https://doi.org/10.2136/sssaj1990.03615995005400030031x

Ahmad Aali, K., Parsinejad, M., & Rahmani, B. (2009). Estimation of Saturation Percentage of Soil Using Multiple Regression,ANN, and ANFIS Techniques. Computer and Information Science, 2(3), 127-136

Akpa, S. I. C., Odeh, I. O. A. & Bishop, T. F. A. (2014). Digital mapping of soil particle-size fractions for Nigeria. Soil Science Society of America Journal, 78. 1953-1966. https://doi.org/10.2136/sssaj2014.05.0202

Aksoy, E., Panagos, P., & Montanarella, L. (2012). Spatial prediction of soil organic carbon of Crete by using geostatistics. In: Minasny, B., Malone, B.P., McBratney, A.B. (Eds.), Digital Soil Assessments and Beyond. CRC Press, London, 149–159.

Amirian Chekan, A., Taghizadeh Mehrjerdi, R., Sarmadian, F., & Heidary, A. (2017). Three-dimensional mapping of soil texture using spline depth functions and artificial neural networks. Iranian Journal of Soil and Water Research, 48(1). 113-123. [In Persian]

Athey, S., Tibshirani, J., & Wager, S. (2019). Generalized random forests. https://doi.org/10.1214/18-aos1709.

Bameri, A., Khormali, F., Kiani, F., & Dehghani, A. A. (2015). Spatial variability of soil organic carbon in different hillslope positions in Toshan area, Golestan Province, Iran: Geostatistical approaches. Journal of Mountain Science, 12(6), 1422-1433. https://doi.org/10.1007/s11629-014-3213-z

Ben-Dor, E., Chabrillat, S., Dematt, J., Taylor, G., Hill, J., Whiting, M., & Sommer, S. (2009). Using imaging spectroscopy to study soil properties. Remote Sens. Environ. 113 (1), 38-55. Imaging Spectroscopy Special Issue. https://doi.org/10.1016/j.rse.2008.09.019 OUCI+2

Bishop, T. F. A., McBratney, A. B. & Laslett, G. M. (1999). Modelling soil attribute depth functions with equal-area quadratic smoothing splines. Geoderma, 91, 27-45. https://doi.org/10.1016/s0016-7061(99)00003-8

Boehner, J., & Selige, T. (2006). Spatial prediction of soil attributes using terrain analysis and climate regionalisation. Gottinger Geographische Abhandlungen, 115, 13-28

Boettinger, J. L., Ramsey, R. D., Bodily, J. M., Cole, N. J., Kienast-Brown, S., Nield, S. J., ... & Stum, A. K. (2008). Landsat spectral data for digital soil mapping. In Digital soil mapping with limited data (pp. 193-202). Dordrecht: Springer Netherlands. https://doi.org/10.1007/978-1-4020-8592-5_16

Camera, C., C., Zomeni, Z., Noller, J. S., Zissimos, A. M., Christoforou, I. C., & Bruggeman, A. (2017). A high resolution map of soil types and physical properties for Cyprus: A digital soil mapping optimization. Geoderma, 285, 35-49. https://doi.org/10.1016/j.geoderma.2016.09.019

Cao, J., Guo, Z., Lv, Y., Xu, M., Huang, C., & Liang, H. (2023). Pollution risk prediction for cadmium in soil from an abandoned mine based on random forest model. International Journal of Environmental Research and Public Health, 20(6), 5097. https://doi.org/10.3390/ijerph20065097

Delbari, M., Afrasiab, P., Gharabaghi, B., Amiri, M., & Salehian, A. (2019). Spatial variability analysis and mapping of soil physical and chemical attributes in a salt-affected soil. Arabian Journal of Geosciences, 12(3), 68-86.
https://doi.org/10.1007/s12517-018-4207-x.

Dharumarajan, S., & Hegde, R. (2022). Digital mapping of soil texture classes using Random Forest classification algorithm. Soil Use and Management, 38(1), 135-149. https://doi.org/10.1111/sum.12668

Duan, M., Guo, Z., Zhang, X., & Wang, C. (2022). Influences of different environmental covariates on county-scale soil type identification using remote sensing images. Ecological Indicators, 139, 108951.
https://doi.org/10.1016/j.ecolind.2022.108951

Emami, M., Khormali, F., Pahlavan-Rad, M. R., & Ebrahimi, S. (2024). Digital modeling of surface and subsurface soil salinity in Golestan province, Iran. Geoderma Regional, 37, e00800. https://doi.org/10.1016/j.geodrs.2024.e00800.

Emami, M., Khormali, F., Pahlavan-Rad, M. R., & Ebrahimi, S. (2024b). Preparation of three-dimensional maps of soil particle size fraction by combining quantile regression forest algorithm and spline functions in the north of Golestan province. Iran., Iranian Journal of Soil and Water Research, 55 (1), 51-68. [In Persian] https://doi.org/10.22059/ijswr.2023.366978.669594

Fan, N. Q., Zhao, F. H., Zhu, L. J., Qin, C. Z., & Zhu, A. X. (2022). Digital soil mapping with adaptive consideration of the applicability of environmental covariates over large areas. International Journal of Applied Earth Observation and Geoinformation, 113, 102986. https://doi.org/10.1016/j.jag.2022.102986

Filippi, P., Jones, E., & Bishop, T.F. (2020). Catchment-scale 3D mapping of depth to soil sodicity constraints through combining public and on-farm soil databases – A potential tool for on-farm management. Geoderma, 374, 114396. https://doi.org/10.1016/j.geoderma.2020.114396

Gholamalizadeh Ahangar, A., Sarani, F., Hashemi, M., & Shabani, A. (2015). Comparison of linear regression methods, geostatistical and artificial neural network modeling of organic carbon in dry land of Sistan plain. Water and Soil, 28(6), 1250-1260. [In Persian] https://doi.org/10.22067/jsw.v0i0.32714

Grunwald, S., Thompson, J. A., Minasny, B., & Boettinger, J. L. (2012). Digital soil mapping in a changing world. In Digital Soil Assessments and Beyond (pp. 301-306). CRC Press London. https://doi.org/10.1201/b12728-60

Gyamerah, S. A., & Moyo, E. (2020). Long‐Term Exchange Rate Probability Density Forecasting Using Gaussian Kernel and Quantile Random Forest. Complexity, 2020(1), 1972962. https://doi.org/10.1155/2020/1972962

Hashemi, M. , Gholamalizadeh Ahangar, A. , Bameri, A. , Sarani, F. & Hejazizadeh, A. (2016). Survey and Zoning of Soil Physical and Chemical Properties Using Geostatistical Methods in GIS (Case Study: Miankangi Region in Sistan). Water and Soil, 30(2), 443-458. [In Persian]. https://doi.org/10.22067/jsw.v30i2.25950

Hengl, T., Heuvelink, G. B., Kempen, B., Leenaars, J. G., Walsh, M. G., Shepherd, K. D., ... & Tondoh, J. E. (2015). Mapping soil properties of Africa at 250 m resolution: Random forests significantly improve current predictions. PloS one, 10(6), e0125814. https://doi.org/10.1371/journal.pone.0125814

Heung, B., Bulmer, C. E., Schmidt, M. G., & Zhang, J. (2022). Provincial-scale digital soil mapping using a random forest approach for British Columbia. Canadian Journal of Soil Science, 102(03), 597-620. http://dx.doi.org/10.1139/cjss-2021-0090

Hom, B. K. (1981). Hill shading and the reflectance map. Proceedings of the IEEE, 69(1), 14-47. https://doi.org/10.1109/proc.1981.11918

IUSS. 7th global digital soil mapping workshop (2016). Available online: https://projects.au.dk/digitalsoilmapping// (accessed on 1st August 2023).

Jamalzehi Samrah, Y. (2022). Three-dimensional spatial modeling texture components and saturation percentage of soil in the Sistan plain. MSc's thesis. Faculty of Water and Soil, University of Zabol. 186 p.

Jamalzehi Samareh, Y., Shahriari, A., Pahlavan-Rad, M., Ziaei Javaid, A. & Bameri, A. (2021). Preparation of three-dimensional maps of the size of soil particles in the floodplain of Sistan [Conference presentation]. The Seventeenth Iran Soil Science Congress and 4th National Farm Water Management Conference, Soil and Water Research Institute, Karaj, Iran. [In Persian]

Jamshidi, M., Delavar, M. A., Taghizadehe-Mehrjerdi, R., & Brungard, C. (2019). Evaluating digital soil mapping approaches for 3D mapping of soil organic carbon. Iranian Journal of Soil Research, 33(2), 227–239. [In Persian]. https://doi.org/10.22092/ijsr.2019.119764

Jena, R. K., Moharana, P. C., Dharumarajan, S., Sharma, G. K., Ray, P., Deb Roy, P., Ghosh, D., Das, B., Alsuhaibani, A. M., & Gaber, A. (2023). Spatial prediction of soil particle-size fractions using digital soil mapping in the North Eastern region of India. Land, 12(7), 1295. https://doi.org/10.3390/land12071295

Karimi Nezhad, M. T., Tabatabaii, S. M., & Gholami, A. (2015). Geochemical assessment of steel smelter-impacted urban soils, Ahvaz, Iran. Journal of Geochemical Exploration, 152, 91–109. https://doi.org/10.1016/j.gexplo.2015.01.005

Kidd, D., Searle, R., Grundy, M., McBratney, A., Robinson, N., O’Brien, L., Zund, P., Arrouays, D., Thomas, M., Padarian, J., Jones, E., Bennett, J. M., Minasny, B., Holmes, K., Malone, B. P., Liddicoat, C., Meier, E. A., Stockmann, U., Wilson, P., Wilford, J., Payne, J., Ringrose-Voase, A., Slater, B., Odgers, N., Gray, J., van Gool, D., Andrews, K., Harms, B., Stower, L., & Triantafilis, J. (2020). Operationalising digital soil mapping – Lessons from Australia. Geoderma Regional, 23, e00335. https://doi.org/10.1016/j.geodrs.2020.e00335

Kidd, D., Searle, R., & Wilson, P. (2018). Digital soil mapping: application, opportunity and challenges. Soil Science Policy Journal (1), 35–40. Available at https://www.soilscienceaustralia.org.au/publications/soil-policy-journal/

Kuhn, M. K., Weston, S., Keefer, C., & Coulter, N. (2016). Cubist models for regression [Computer software manual]. https://cran.r-project.org/package=Cubist

Lotfollahi, L., Delavar, M. A., Biswas, A., Jamshidi, M., Taghizadeh-Mehrjardi, R., & Fatehi, S. H. (2023). Modeling the spatial distribution of sand, silt, and clay particles based on GlobalSoilMap and limited data. DESERT, 28(2), 243–263.

Malone, B. P., McBratney, A. B., Minasny, B. & Laslett, G. M. (2009). Mapping continuous depth functions of soil carbon storage and available water capacity. Geoderma, 154, 138-152. https://doi.org/10.1016/j.geoderma.2009.10.007

Malone, B. P., Minasny, B., & McBratney, A. B. (2016). Using R for digital soil mapping (pp. 133–136). Springer. https://doi.org/10.1007/978-3-319-44327-0

Meinshausen, N. (2017). quantregForest: Quantile regression forests [Computer software manual]. CRAN.
https://cran.r-project.org/web/packages/quantregForest/index.html

Metinfar, H., Maqsoodi, Z., Mousavi, S., & Jalali, M. (2019). Evaluation of machine learning methods in digital organic carbon mapping of agricultural soils (part of Khorram Abad plain. Water and Soil Magazine, 24(4), 327–343. [In Persian]

Mirakzehi, K., Pahlavan-Rad, M. R., Shahriari, A., & Bameri, A. (2018). Digital soil mapping of deltaic soils: A case of study from Hirmand (Helmand) river delta. Geoderma, 313, 233–240. https://doi.org/10.1016/j.geoderma.2017.10.039

Montanarella, L., & Panagos, P. (2021). The relevance of sustainable soil management within the European Green Deal. Land Use Policy, 100, 104950. https://doi.org/10.1016/j.landusepol.2020.104950

Mousavi, S. R., Sarmadian, F., Omid, M. K., & Bogaert, P. (2022). Three-dimensional mapping of soil organic carbon using soil and environmental covariates in an arid and semi-arid region of Iran. Measurement, 201, 111706. https://doi.org/10.1016/j.measurement.2022.111706

Mulder, V., de Bruin, S., Schaepman, M., & Mayr, T. (2011). The use of remote sensing in soil and terrain mapping - a review. Geoderma, 162(1–2), 1–19. https://doi.org/10.1016/j.geoderma.2011.03.021

Naimi mardani, S., Ayoubi, S., Demattê, J., Zeraatpisheh, M., Amorim, M. T., & Oliveira Mello, F. A. (2021). Spatial prediction of soil surface properties in an arid region using synthetic soil image and machine learning. Geocarto International, 1–25. https://doi.org/10.1080/10106049.2021.1996639

Pahlavan-Rad, M. R., & Akbarimoghaddam, A. (2018). Spatial variability of soil texture fractions and pH in a flood plain (case study from eastern Iran). Catena, 160, 275–281. https://doi.org/10.1016/j.catena.2017.09.004

Piri, H. (2012). Assessment of computational methods of estimation of potential evapotranspiration using lysimeter data (Case study: Sistan Plain). Journal of Irrigation and Water Engineering, 3(9), 50–62. [In Persian]

Quinlan, J. R. (1992). Learning with continuous classes. In Proceedings of the Fifth Australian Joint Conference on Artificial Intelligence (pp. 343–348). World Scientific.

Rodiguez, F., Maire, E., Courjault-Rade, D., & Darrozes, J. (2002). The Black Top Hat function applied to a DEM: A tool to estimate recent incision in a mountainous watershed. Geophysical Research Letters, 29(1), 91–94. https://doi.org/10.1029/2001gl013484

Selmy, S. A., Abd El-Aziz, S., El-Desoky, A., & El-Sayed, M. A. (2022). Characterizing, predicting, and mapping of soil spatial variability in Gharb El-Mawhoub area of Dakhla Oasis using geostatistics and GIS approaches. Journal of the Saudi Society of Agricultural Sciences, 21(4), 383–396. https://doi.org/10.1016/j.jssas.2021.05.004

Shahriari, M., Delbari, M., Afrasiab, P., & Pahlavan-Rad, M. R. (2019). Predicting regional spatial distribution of soil texture in floodplains using remote sensing data: A case of southeastern Iran. Catena, 182, 104–149. https://doi.org/10.1016/j.catena.2019.104149

Shams, M. Y., Tarek, Z., Elshewey, A. M., Hany, M., Darwish, A., & Hassanien, A. E. (2023). A machine learning based model for predicting temperature under the effects of climate change. In A. E. Hassanien & A. Darwish (Eds.), The power of data: Driving climate change with data science and artificial intelligence innovations (pp. 61–81). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-22457-4_4

Siyasar, H., Honar, T., & Abdolahipour, M. (2020). Comparing of generalized linear models, random forest and gradient boosting trees in estimation of reference crop evapotranspiration (Case study: The Sistan Plain). JWSS, 23(4), 395–410. [In Persian] https://doi.org/10.47176/jwss.23.4.40631

Soil Science Division Staff. (2017). Soil survey manual (C. Ditzler, K. Scheffe, & H. C. Monger, Eds.) (USDA Handbook 18). Government Printing Office.

Stivent, G. A., & Khan, M. A. (1996). Saturation percentage as a measure of soil texture in the lower Indus Basin. Journal of Soil Science, 17(1), 255–263. https://doi.org/10.1111/j.1365-2389.1966.tb01471.x

Taghizadeh Mehrjardi, R., Minasny, B., Sarmadian, F., & Malone, B. P. (2014). Digital mapping of soil salinity in Ardakan region, central Iran. Geoderma, 213, 15–28. https://doi.org/10.1016/j.geoderma.2013.07.027

Taghizadeh-Mehrjardi, R., Emadi, M., Cherati, A., Heung, B., Mosavi, A., & Scholten, T. (2021). Bio-inspired hybridization of artificial neural networks: An application for mapping the spatial distribution of soil texture fractions. Remote Sensing, Article 1–23. https://doi.org/10.3390/rs13040612

Wadoux, A. M.-C., Minasny, B., & McBratney, A. B. (2020). Machine learning for digital soil mapping: Applications, challenges and suggested solutions. Earth-Science Reviews, 210, 103359. https://doi.org/10.1016/j.earscirev.2020.103359

Wager, S., & Athey, S. (2018). Estimation and inference of heterogeneous treatment effects using random forests. Journal of the American Statistical Association, 113(523), 1228–1242. https://doi.org/10.1080/01621459.2017.1319839

Wei, Y., Ding, J., Yang, S., Yang, X., & Wang, F. (2021). Comparisons of random forest and stochastic gradient treeboost algorithms for mapping soil electrical conductivity with multiple subsets using Landsat OLI and DEM/GIS-based data at a type oasis in Xinjiang, China. European Journal of Remote Sensing, 54(1), 158–181. https://doi.org/10.1080/22797254.2021.1888657

Wulf, H., Mulder, T., Schaepman, M., Keller, A., & Jörg, P. (2014). Remote sensing of soils (Tech. Rep. 00.0338.PZ/435-0501). University of Zurich. https://doi.org/10.5167/uzh-109992

Zeraatpisheh, M., Ayoubi, S., Jafari, A., Tajik, S., & Finke, P. (2019). Digital mapping of soil properties using multiple machine learning in a semi-arid region, central Iran. Geoderma, 338, 445–452. https://doi.org/10.1016/j.geoderma.2018.11.011

Zhang, Y., Ji, W., Saurette, D. D., Easher, T. H., Li, H., Shi, Z., Adamchuk, V. I., & Biswas, A. (2020). Three-dimensional digital soil mapping of multiple soil properties at a field-scale using regression kriging. Geoderma, 366, 114253. https://doi.org/10.1016/j.geoderma.2020.114253

Žížala, D., Minařík, R., Skála, J., Beitlerová, H., Juřicová, A., Rojas, J. R., Penížek, V., & Zádorová, T. (2022). High-resolution agriculture soil property maps from digital soil mapping methods, Czech Republic. Catena, 212, 106024. https://doi.org/10.1016/j.catena.2022.106024

Zulfiqari, F., & Abedi, Gh. (2019). Modeling the effective factors in the concentration of dust particles in the air using the method CUBIST. In International Conference on Dust in Southwest Asia, Zabol. [In Persian]