Spatial prediction and modeling of soil salinity using simple cokriging, artificial neural networks, and support vector machines in El Outaya plain, Biskra, southeastern Algeria

Abstract

Soil salinization is one of the most predominant environmental hazards responsible for agricultural land degradation, especially in the arid and semi-arid regions. An accurate spatial prediction and modeling of soil salinity in agricultural land are so important for farmers and decision-makers to develop the appropriate mechanisms to prevent the loss of fertile soil and increase crop production. El Outaya plain is marked by soil salinity increases due to the excessive use of poor groundwater quality for irrigation. This study aims to compare the performance of simple kriging, cokriging (SCOK), multilayer perceptron neural networks (MLP-NN), and support vector machines (SVM) in the prediction of topsoil and subsoil salinity. The field covariates including geochemical properties of irrigation groundwater and physical properties of soil and environmental covariates including digital elevation model and remote sensing derivatives were used as input candidates to SCOK, MLP-NN, and SVM. The optimal input combination was determined using multiple linear stepwise regression (MLSR). The results revealed that the SCOK using field covariates including water electrical conductivity (ECw) and sand percentage (sand %), and environmental covariates including land surface temperature (LST), topographic wetness index (TWI), and elevation could significantly increase the accuracy of soil salinity spatial prediction. The comparison of the prediction accuracy of the different modeling techniques using the Taylor diagram indicated that MLP-NN using LST, TWI, and elevation as inputs were more accurate in predicting the topsoil salinity [ECs (TS)] with a mean absolute error (MAE) of 0.43, root mean square error (RMSE) of 0.6 and correlation coefficient of 0.946. MLP-NN using ECw and sand % as inputs were more accurate in predicting the subsoil salinity [ECs (SS)] with MAE of 0.38, RMSE of 0.6, and R of 0.968.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

References

  1. Abdennour MA, Douaoui A, Barrena J et al (2020) Geochemical characterization of the salinity of irrigated soils in arid regions (Biskra, SE Algeria). Acta Geochim. https://doi.org/10.1007/s11631-020-00426-2

    Article  Google Scholar 

  2. Abuelgasim A, Ammad R (2018) Mapping soil salinity in arid and semi-arid regions using landsat 8 OLI satellite data. Remote Sens Appl Soc Environ 13:415–425. https://doi.org/10.1016/j.rsase.2018.12.010

    Article  Google Scholar 

  3. Achieng KO (2019) Computers and geosciences modelling of soil moisture retention curve using machine learning techniques: artificial and deep neural networks vs support vector regression models. Comput Geosci 133:104320. https://doi.org/10.1016/j.cageo.2019.104320

    Article  Google Scholar 

  4. Avdan U, Jovanovska G (2016) Algorithm for automated mapping of land surface temperature using LANDSAT 8 Satellite Data. J Sensors 8

  5. Benchetrit M (1956) Les sols d’Algérie. Rev géographie Alp 44:749–761. https://doi.org/10.3406/rga.1956.1790

    Article  Google Scholar 

  6. BISHOP CM (1995) Deep neural networks for pattern recognition

  7. Boudibi S, Sakaa B, Zapata-Sierra AJ (2019) Groundwater quality assessment using GIS, ordinary kriging and WQI in an arid area. Ponte 75:204–226. https://doi.org/10.21506/j.ponte.2019.12.14

    Article  Google Scholar 

  8. Boudjema A (2015) Hydrogéologie, vulnérabilité et modélisation de la nappe du Mio-Pliocène d’El Outaya, (Biskra, Sud-Est algérien). Mohamed Khider Biskra

  9. Bradaï A, Douaoui A, Bettahar N, Yahiaoui I (2016) Improving the prediction accuracy of groundwater salinity mapping using indicator Kriging method. J Irrig Drain Eng 142:11. https://doi.org/10.1061/(ASCE)IR.1943-4774.0001019

    Article  Google Scholar 

  10. Cambardella CA, Moorman TB, Parkin TB et al (1994) Field-scale variability of soil properties in Central Iowa Soils. Soil Sci Soc Am J 58:1501–1511. https://doi.org/10.2136/sssaj1994.03615995005800050033x

    Article  Google Scholar 

  11. Ceryan N (2014) Application of support vector machines and relevance vector machines in predicting uniaxial compressive strength of volcanic rocks. J Afr Earth Sci 100:634–644. https://doi.org/10.1016/j.jafrearsci.2014.08.006

    Article  Google Scholar 

  12. Cherkassky V, Ma Y (2004) Practical selection of SVM parameters and noise estimation for SVM regression. Neural Netw 17:113–126. https://doi.org/10.1016/S0893-6080(03)00169-2

    Article  Google Scholar 

  13. Cortes C, Vapnik V (1995) Photonit neural networks and learning mathines the role of electron-trapping materials. Support Netw 20:273–297. https://doi.org/10.1109/64.163674

    Article  Google Scholar 

  14. Dai F, Zhou Q, Lv Z et al (2014) Spatial prediction of soil organic matter content integrating artificial neural network and ordinary Kriging in Tibetan Plateau. Ecol Indic 45:184–194. https://doi.org/10.1016/j.ecolind.2014.04.003

    Article  Google Scholar 

  15. Durand MJ-H, Barbut MM (1938) Carte de reconnaissance des sols d’Algerie: Biskra. Service Geographique de l’Armée (in French)

  16. Erdik T, Savci ME, Şen Z (2009) Expert systems with applications artificial neural networks for predicting maximum wave runup on rubble mound structures. Expert Syst with Appl J 36:6403–6408. https://doi.org/10.1016/j.eswa.2008.07.049

    Article  Google Scholar 

  17. ESRI (2020) Soil Adjusted Vegetation Index (SAVI). https://pro.arcgis.com/en/pro-app/arcpy/spatial-analyst/savi.htm. Accessed in 05 Sept 2020

  18. Gorji T, Yildirim A, Hamzehpour N et al (2020) Soil salinity analysis of Urmia Lake Basin using Landsat-8 OLI and Sentinel- 2A based spectral indices and electrical conductivity measurements. Ecol Indic 112:106173. https://doi.org/10.1016/j.ecolind.2020.106173

    Article  Google Scholar 

  19. Gu Y, Bao Z, Lin Y et al (2017) The porosity and permeability prediction methods for carbonate reservoirs with extremely limited logging data: stepwise regression vs. N-way analysis of variance. J Nat Gas Sci Eng 42:99–119. https://doi.org/10.1016/j.jngse.2017.03.010

    Article  Google Scholar 

  20. Herceg S (2019) Chemical engineering research and design development of soft sensors for isomerization process based on support vector machine regression and dynamic polynomial models. Chem Eng Res Des 149:95–103. https://doi.org/10.1016/j.cherd.2019.06.034

    Article  Google Scholar 

  21. Huete AR (1988) A soil-adjusted vegetation index (SAVI) 295. Remote Sens Environ 25:295–309

    Article  Google Scholar 

  22. Jalal M, Arabali P, Grasley Z et al (2020) Behavior assessment, regression analysis and support vector machine (SVM) modeling of waste tire rubberized concrete. J Clean Prod 273:122960. https://doi.org/10.1016/j.jclepro.2020.122960

    Article  Google Scholar 

  23. Kisi O, Alizamir M, Zounemat-Kermani M (2017) Modeling groundwater fluctuations by three different evolutionary neural network techniques using hydroclimatic data. Nat Hazards 87:367–381. https://doi.org/10.1007/s11069-017-2767-9

    Article  Google Scholar 

  24. Koulla N, Mohammed A, Santos CAG, Abdelkader D (2019) Spatial modeling of soil salinity using multiple linear regression, ordinary kriging and artificial neural network methods in the Lower Cheliff plain, Algeria. J Urban Environ Eng 13:34–41. https://doi.org/10.4090/juee.2019.v13n1.034041

    Article  Google Scholar 

  25. Machado RMA, Serralheiro RP (2017) Soil salinity: effect on vegetable crop growth. Management practices to prevent and mitigate soil salinization. Horticulturae 3:1–13. https://doi.org/10.3390/horticulturae3020030

    Article  Google Scholar 

  26. Maroufpoor S, Fakhri-Fard A, Shiri J (2017) Study of the spatial distribution of groundwater quality using soft computing and geostatistical models. ISH J Hydraul Eng 25:232–238. https://doi.org/10.1080/09715010.2017.1474389

    Article  Google Scholar 

  27. Pouladi N, Asghar A, Farzin J et al (2019) Design and implementation of a hybrid MLP-FFA model for soil salinity prediction. Environ Earth Sci 78:159. https://doi.org/10.1007/s12665-019-8159-6

    Article  Google Scholar 

  28. Sakaa B, Brahmia N, Chaffai H, Hani A (2020) Desalination and Water Treatment Assessment of water quality index in unmonitored river basin using multilayer perceptron neural networks and principal component analysis. Desalin Water Treat. https://doi.org/10.5004/dwt.2020.26108

    Article  Google Scholar 

  29. Samui P (2008) Slope stability analysis: a support vector machine approach. Environ Geol 56:255–267. https://doi.org/10.1007/s00254-007-1161-4

    Article  Google Scholar 

  30. Santos CAG, Freire PKMM, da Silva RM, Akrami SA (2019) Hybrid wavelet neural network approach for daily inflow forecasting using Tropical Rainfall Measuring Mission data. J Hydrol Eng 24:1–13. https://doi.org/10.1061/(ASCE)HE.1943-5584.0001725

    Article  Google Scholar 

  31. Shahabi M, Jafarzadeh AA, Neyshabouri MR et al (2016) Spatial modeling of soil salinity using multiple linear regression, ordinary Kriging and artificial neural network methods Spatial modeling of soil salinity using multiple linear regression, ordinary kriging and artificial neural network methods. Arch Agron Soil Sci. https://doi.org/10.1080/03650340.2016.1193162

    Article  Google Scholar 

  32. Shen Q, Wang Y, Wang X et al (2019) Comparing interpolation methods to predict soil total phosphorus in the Mollisol area of Northeast China. CATENA 174:59–72. https://doi.org/10.1016/j.catena.2018.10.052

    Article  Google Scholar 

  33. Shrivastava P, Kumar R (2015) Soil salinity: A serious environmental issue and plant growth promoting bacteria as one of the tools for its alleviation. Saudi J Biol Sci 22:123–131. https://doi.org/10.1016/j.sjbs.2014.12.001

    Article  Google Scholar 

  34. Vapnik VN (1995) The nature of statistical learning theory. Springer, New York

    Google Scholar 

  35. Vapnik V (1998) The support vector method of function estimation. In: Nonlinear modeling: advanced black-box techniques. Springer, Boston, pp 55–85

  36. Wackernagel H (2003) Multivariate geostatistics: an introduction with applications, 3rd edn. Springer, Berlin

    Google Scholar 

  37. Wang K, Zhang C, Li W (2013) Predictive mapping of soil total nitrogen at a regional scale: a comparison between geographically weighted regression and cokriging. Appl Geogr 42:73–85. https://doi.org/10.1016/j.apgeog.2013.04.002

    Article  Google Scholar 

  38. Webster R, Oliver MA (2007) Geostatistics for environmental scientists. Wiley, Southern Gate

    Google Scholar 

  39. Were K, Bui DT, Dick ØB, Singh BR (2015) A comparative assessment of support vector regression, artificial neural networks, and random forests for predicting and mapping soil organic carbon stocks across an Afromontane landscape. Ecol Indic 52:394–403. https://doi.org/10.1016/j.ecolind.2014.12.028

    Article  Google Scholar 

  40. Wu YX, Guo L, Li Y, et al (2006) Multi-layer support vector machine and its application. In: Proceedings of the fifth international conference on machine learning and cybernetics, pp 3627–3631

  41. Yin CL, Meng F, Yu QR (2020) Infrared Physics & Technology Calculation of land surface emissivity and retrieval of land surface temperature based on a spectral mixing model. Infrared Phys Technol 108:103333. https://doi.org/10.1016/j.infrared.2020.103333

    Article  Google Scholar 

  42. Zounemat-kermani M, Scholz M (2014) Modeling of dissolved oxygen applying stepwise regression and a template-based fuzzy logic system. J Environ Eng 140:69–76. https://doi.org/10.1061/(ASCE)EE.1943-7870.0000780

    Article  Google Scholar 

  43. Zounemat-kermani M, Kisi O, Rajaee T (2014) Performance of radial basis and LM-feed forward artificial neural networks for predicting daily watershed runoff. Appl Soft Comput J. https://doi.org/10.1016/j.asoc.2013.07.007

    Article  Google Scholar 

  44. Zounemat-kermani M, Ramezani-charmahineh A, Razavi R et al (2020) Machine learning and water economy : a new approach to predicting dams water sales revenue. Water Resour Manag 34:1893–1911. https://doi.org/10.1007/s11269-020-02529-0

    Article  Google Scholar 

Download references

Acknowledgements

The corresponding author would like to thank Pr. Zekai Şen of Medipol University (Turkey) for his thoughtful and insightful comments on draft versions of this paper.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Samir Boudibi.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Boudibi, S., Sakaa, B., Benguega, Z. et al. Spatial prediction and modeling of soil salinity using simple cokriging, artificial neural networks, and support vector machines in El Outaya plain, Biskra, southeastern Algeria. Acta Geochim (2021). https://doi.org/10.1007/s11631-020-00444-0

Download citation

Keywords

  • Soil salinity
  • Cokriging
  • Multilayer perceptron
  • Machine learning
  • El-Outaya plain