Modeling soil electrical conductivity using machine learning: Implications for sustainable land use in saline coastal regions

Ramin Samieifard, Patrick Joseph Drohan, Ahmad Heidari

Article ID: 11427
Vol 8, Issue 2, 2025


Abstract


Soil salinization is a difficult challenge for agricultural productivity and environmental sustainability, particularly in arid and semi-arid coastal regions. This study investigates the spatial variability of soil electrical conductivity (EC) and its relationship with key cations and anions (Na+, K+, Ca2+, Mg2+, Cl⁻, CO32⁻, HCO3⁻, SO42⁻) along the southeastern coast of the Caspian Sea in Iran. Using a combination of field-based soil sampling, laboratory analyses, and Landsat 8 spectral data, linear Multiple Linear Regression and Partial Least Squares Regression (MLR, PLSR) and nonlinear Artifician Neural Network and Support Vector Machine (ANN, SVM) modeling approaches were employed to estimate and map soil EC. Results identified Na+ and Cl⁻ as the primary contributors to salinity (r = 0.78 and r = 0.88, respectively), with NaCl salts dominating the region’s soil salinity dynamics. Secondary contributions from Potassium Chloride KCl and Magnesium Chloride MgCl2 were also observed. Coastal landforms such as lagoon relicts and coastal plains exhibited the highest salinity levels, attributed to geomorphic processes and anthropogenic activities. Among the predictive models, the SVM algorithm outperformed others, achieving higher R2 values and lower RMSE (RMSETest = 27.35 and RMSETrain = 24.62, respectively), underscoring its effectiveness in capturing complex soil-environment interactions. This study highlights the utility of digital soil mapping (DSM) for assessing soil salinity and provides actionable insights for sustainable land management, particularly in mitigating salinity and enhancing agricultural practices in vulnerable coastal systems.


Keywords


electrical conductivity; SVM; salinity; coastal landforms; remote sensing

Full Text:

PDF


References


1. Zhang Z, Ren J, Wang Y, et al. Study on the EC prediction of cracked soda saline-alkali soil based on texture analysis of high-resolution images from ground-based observation and machine learning methods. Soil and Tillage Research. 2024; 244: 106234. doi: 10.1016/j.still.2024.106234

2. Iseas MS, Sainato CM, Gómez A, et al. Assessing salinity and sodicity of irrigated soils using apparent electrical conductivity in the Pampean region. Environmental Earth Sciences. 2024; 83(12). doi: 10.1007/s12665-024-11643-w

3. Abdullahi M, Elnaggar A, Omar M, et al. Land degradation, causes, implications and sustainable management in arid and semi arid regions: a case study of Egypt. Egyptian Journal of Soil Science. 2023; 63(4): 0-0. doi: 10.21608/ejss.2023.230986.1647

4. Elmeknassi M, Elghali A, de Carvalho HWP, et al. A review of organic and inorganic amendments to treat saline-sodic soils: Emphasis on waste valorization for a circular economy approach. Science of The Total Environment. 2024; 921: 171087. doi: 10.1016/j.scitotenv.2024.171087

5. González-Nava VJ, Solís-Valdéz S, Manríquez J, et al. Detection of sodium ion in aqueous soil extract using Prussian blue modified screen-printed electrodes. Electrochimica Acta. 2025; 513: 145564. doi: 10.1016/j.electacta.2024.145564

6. Kumar P, Tiwari P, Biswas A, et al. Spatio-temporal assessment of soil salinization utilizing remote sensing derivatives, and prediction modeling: Implications for sustainable development. Geoscience Frontiers. 2024; 15(6): 101881. doi: 10.1016/j.gsf.2024.101881

7. González‐Nava VJ, Cárdenas Mijangos J, Frausto‐Castillo RF, et al. Hemodialysis Wastewater Treatment via Electrocoagulation and Electro‐Oxidation: Modular Pilot‐Level Modeling and Simulation. ChemPlusChem. 2024; 89(6). doi: 10.1002/cplu.202300671

8. Xing J, Li X, Li Z, et al. Remediation of soda-saline-alkali soil through soil amendments: Microbially mediated carbon and nitrogen cycles and remediation mechanisms. Science of The Total Environment. 2024; 924: 171641. doi: 10.1016/j.scitotenv.2024.171641

9. Sheng D, Meng X, Wen X, et al. Hydrochemical characteristics, quality and health risk assessment of nitrate enriched coastal groundwater in northern China. Journal of Cleaner Production. 2023; 403: 136872. doi: 10.1016/j.jclepro.2023.136872

10. Hill AC. Land-atmosphere carbon dioxide and methane exchange in a temperate salt marsh. University of Delaware; 2023.

11. Rafik A, Ibouh H, El Alaoui El Fels A, et al. Soil Salinity Detection and Mapping in an Environment under Water Stress between 1984 and 2018 (Case of the Largest Oasis in Africa-Morocco). Remote Sensing. 2022; 14(7): 1606. doi: 10.3390/rs14071606

12. Wang F, Han L, Liu L, et al. Advancements and Perspective in the Quantitative Assessment of Soil Salinity Utilizing Remote Sensing and Machine Learning Algorithms: A Review. Remote Sensing. 2024; 16(24): 4812. doi: 10.3390/rs16244812

13. Diaz-Gonzalez FA, Vuelvas J, Correa CA, et al. Machine learning and remote sensing techniques applied to estimate soil indicators – Review. Ecological Indicators. 2022; 135: 108517. doi: 10.1016/j.ecolind.2021.108517

14. Zeraatpisheh M, Ayoubi S, Jafari A, et al. Comparing the efficiency of digital and conventional soil mapping to predict soil types in a semi-arid region in Iran. Geomorphology. 2017; 285: 186-204. doi: 10.1016/j.geomorph.2017.02.015

15. Nouri A, Esfandiari M, Eftekhari K, et al. Development support vector machine, artificial neural network and artificial neural network – genetic algorithm hybrid models for estimating erodible fraction of soil to wind erosion. International Journal of River Basin Management. 2023; 22(3): 379-388. doi: 10.1080/15715124.2022.2153856

16. Alomar S, Mireei SA, Hemmat A, et al. Comparison of Vis/SWNIR and NIR spectrometers combined with different multivariate techniques for estimating soil fertility parameters of calcareous topsoil in an arid climate. Biosystems Engineering. 2021; 201: 50-66. doi: 10.1016/j.biosystemseng.2020.11.007

17. Kakroodi AA, Kroonenberg SB, Hoogendoorn RM, et al. Rapid Holocene sea-level changes along the Iranian Caspian coast. Quaternary International. 2012; 263: 93-103. doi: 10.1016/j.quaint.2011.12.021

18. Kakroodi AA, Kroonenberg SB, Beni AN, et al. Short- and Long-Term Development of the Miankaleh Spit, Southeast Caspian Sea, Iran. Journal of Coastal Research. 2014; 298: 1236-1242. doi: 10.2112/jcoastres-d-12-00174.1

19. Samiei-Fard R, Heidari A, Drohan PJ, et al. The Effect of Using a Geopedological Approach in Determining Land Quality Indicators, Land Degradation, and Development (Case Study: Caspian Sea Coast). Environments. 2024; 11(1): 20. doi: 10.3390/environments11010020

20. Samiei-Fard R, Heidari A, Konyushkova M, et al. Application of particle size distribution throughout the soil profile as a criterion for recognition of newly developed geoforms in the Southeastern Caspian coast. CATENA. 2021; 203: 105362. doi: 10.1016/j.catena.2021.105362

21. Sparks DL, Page AL, Helmke PA, Loeppert RH. Methods of soil analysis, part 3: Chemical methods. John Wiley & Sons; 2020.

22. Harikaran GK. Machine Learning Approaches for Predicting Soil Properties of Vemagal Hobli, Kolar District, Karnataka [PhD thesis]. University of Agricultural Sciences, GKVK, Bangalore; 2022.

23. AbdelRahman MAE, Metwaly MM, Shalaby A. Quantitative assessment of soil saline degradation using remote sensing indices in Siwa Oasis. Remote Sensing Applications: Society and Environment. 2019; 13: 53-60. doi: 10.1016/j.rsase.2018.10.004

24. Schoeneberger P, Wysocki DA. Geomorphic Description System, Version 5.0. Natural Resources Conservation Service, National Soil Survey Center, Lincoln, NE, USA; 2017.




DOI: https://doi.org/10.24294/jgc11427

Refbacks

  • There are currently no refbacks.


Copyright (c) 2025 Author(s)

License URL: https://creativecommons.org/licenses/by/4.0/

This site is licensed under a Creative Commons Attribution 4.0 International License.