Digital Mapping of Soil Texture Particles with Machine Learning Models and Environmental Covariates

آب و خاک

Article 7, Volume 37, Issue 6 - Serial Number 92, January and February 2024, Pages 923-942   

Document Type: Research Article

DOI: 10.22067/jsw.2023.84413.1331

Authors

P. Khosravani¹; M. Baghernejad^{* 1}; A.A. Moosavi¹; S.R. Fallah Shamsi²

¹Department of Soil Science, College of Agriculture, Shiraz University, Shiraz, Iran

²Department of Natural Resources and Environmental Engineering, College of Agriculture, Shiraz University, Shiraz, Iran

Abstract

Introduction
Understanding the particle size distribution (PSD) is of great importance for plant growth and soil management. In recent years, the science of soil has witnessed a significant increase in digital soil mapping (DSM) activities. In this regard, machine learning models (ML) have emerged as an alternative and tool for DSM, which are mainly used for data mining and pattern recognition purposes, and are now widely used for regression and classification tasks in all fields of science. Hence, this study was undertaken to spatially model sand, silt, and clay particles utilizing machine learning models such as Random Forest (RF), Support Vector Regression (SVR), and the Co-Kriging geostatistical model. Additionally, auxiliary variables with high spatial resolution were incorporated into the analysis. This investigation was conducted in a section of the Marvdasht plain, located in Fars province.
 
Materials and Methods
The present study was conducted in a part of Marvdasht plain located between 35.82´41°52' to 1.07´57°52' east longitude and 35.02´48°29' to 14.72´2°30' north latitude, and 40 km north of Shiraz with an area of about 50,000 hectares. After determining the study area boundaries, the positions of 200 sampling points were determined using the R software and the conditioned Latin hypercube sampling method. In other words, for soil feature modeling, 200 samples were taken from two depths of zero to 30 and 30 to 60 centimeters in the study area. Then, the samples were transferred to the laboratory, dried, and passed through a 2 mm sieve. Finally, the soil texture components were measured by the hydrometer method. The environmental variables used in this study are a wide range of representatives of soil-forming factors that were prepared as much as possible from sources with minimum cost and high accessibility. In total, 75 environmental variables were prepared, and the raster format related to all environmental variables, including 39 elevation and altitude variables and 36 remote sensing measurement variables, was extracted. Finally, the factor-tuning inflation variance and Boruta algorithm were used to select the optimal variables.
 
Results
The minimum amount of clay was measured at 10.21% and 10.45%, respectively, and the maximum amount was 32.65% and 36.35% at the surface and subsurface depths. The average amount of clay in all samples was 37.91% and 35.61%. The average amount of sand was measured at 25.65% and 26.02% at the surface and subsurface depths, respectively. The maximum amount of sand was observed in the northern and higher parts of the study area and was equal to 54.68% and the minimum amount was predicted in the low-lying areas of the study area. Low-lying areas and sedimentary plains in the central part of the study area contained high amounts of silt. Four depth variables valley depths (VD), texture (TE), topographic wetness index (TWI), and clay index (CI) related to geomorphometric parameters and the normalized difference vegetation index (NDVI) variable related to remote sensing indices were selected as optimal variables. The RF model with R² of 54.0% and 36.0% for predicting sand, 48.0% and 64.0% for predicting silt, and 52.0% and 49.0% for predicting clay at both surface and subsurface depths performed better than the SVR and Co-Kriging models. The most effective variable in predicting the spatial distribution of soil particles was VD with relative importance of 60% and 65% for predicting sand at the surface and subsurface depths, 70% for predicting silt at the surface depth, and 70% and 65% for predicting clay at both surface and subsurface depths, respectively. Only TE and TWI variables were more important than VD for predicting silt at subsurface depth. These results show that topographic variables are effective in the spatial variation of soil particles. Unlike clay, the highest amount of sand in both depths was observed in the northern part and the highest part of the study area, and the lowest amount was predicted in the low-lying areas of the study area.
 
Conclusion
In general, with the aim of this research, maps of the spatial distribution of soil texture components were prepared at both surface and subsurface depths using machine learning and geostatistical approaches along with environmental covariates in a part of Marvdasht plain. Among the selected environmental covariates, topographic attributes, especially the valley depth (VD), had the highest effect in justifying the spatial prediction of soil texture components. Also, the results of comparing the performance of machine learning models supported the higher efficiency of the RF model than other models. Therefore, the approach used in this study to prepare a map of soil texture components can be useful as a guide for mapping useful soil features in areas with similar climatic and topographic conditions.

Keywords

Co-Kriging; Digital soil mapping; Machine learning; Random Forest; Soil particle size distribution

References

1. Arrouays, D., McBratney, A., Bouma, J., Libohova, Z., Richer-de-Forges, A.C., Morgan, C.L., & Mulder, V.L. (2020). Impressions of digital soil maps: The good, the not so good, and making them ever better. Geoderma Regional, 20, e00255. https://doi.org/10.1016/j.geodrs.2020.e00255
2. Azizi, K., Garosi, Y., Ayoubi, S., & Tajik, S. (2023). Integration of Sentinel-1/2 and topographic attributes to predict the spatial distribution of soil texture fractions in some agricultural soils of western Iran. Soil and Tillage Research, 229, 105681. https://doi.org/10.1016/j.still.2023.105681
3. Breiman, L. (2001). Random forests. Machine learning, 45, 5-32. https://doi.org/10.1023/A:1010933404324
4. Bi, D., Li, Y.F., Tso, S.K., & Wang, G.L. (2004). Friction modeling and compensation for haptic display based on support vector machine. IEEE Transactions on Industrial Electronics, 51(2), 491-500. https://doi.org/10.1109/ TIE.2004.825277
5. 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
6. de Jesus Duarte, S., Glaser, B., & Pellegrino Cerri, C.E. (2019). Effect of biochar particle size on physical, hydrological and chemical properties of loamy and sandy tropical soils. Agronomy, 9(4), 165. https://doi.org/ 10.3390/agronomy9040165
7. Chen, T.L., Shi, Z.L., Wen, A.B., Yan, D.C., Guo, J., Chen, J.C., & Chen, R.Y. (2021). Multifractal characteristics and spatial variability of soil particle-size distribution in different land use patterns in a small catchment of the Three Gorges Reservoir Region, China. Journal of Mountain Science, 18(1), 111-125. https://doi.org/10.1007/s11629-020-6112-5
8. Chen, Y., Ma, L., Yu, D., Zhang, H., Feng, K., Wang, X., & Song, J. (2022). Comparison of feature selection methods for mapping soil organic matter in subtropical restored forests. Ecological Indicators, 135, 108545. https://doi.org/10.1016/j.ecolind.2022.108545
9. Faé, G.S., Montes, F., Bazilevskaya, E., Añó, R.M., & Kemanian, A.R. (2019). Making soil particle size analysis by laser diffraction compatible with standard soil texture determination methods. Soil Science Society of America Journal, 83(4), 1244-1252. http://doi.org/10.2136/sssaj2018.10.0385
10. Friedman, J.H., & Meulman, J.J. (2003). Multiple additive regression trees with application in epidemiology. Statistics in Medicine, 22(9), 1365-1381. https://doi.org/10.1002/sim.1501
11. Gessler, P.E., Chadwick, O.A., Chamran, F., Althouse, L., & Holmes, K. (2000). Modeling soil–landscape and ecosystem properties using terrain attributes. Soil Science Society of America Journal, 64(6), 2046-2056. https://doi.org/10.2136/sssaj2000.6462046x
12. Geology.com/news/2010/freelansatimages-from-USGS-2. http://glovis.usgs.gov.
13. Gomes, L.C., Faria, R.M., de Souza, E., Veloso, G.V., Schaefer, C.E.G., & Fernandes Filho, E.I. (2019). Modelling and mapping soil organic carbon stocks in Brazil. Geoderma, 340, 337-350. https://doi.org/10.1016/j.geoderma .2019.01.007
14. Hengl, T., Mendes de Jesus, J., Heuvelink, G.B., Ruiperez Gonzalez, M., Kilibarda, M., Blagotić, A., & Kempen, B. (2017). SoilGrids250m: Global gridded soil information based on machine learning. PLoS One, 12(2), e0169748. https://doi.org/10.1371/journal.pone.0169748
15. Hossain, M.S., Rahman, G.M., Alam, M.S., Rahman, M.M., Solaiman, A.R.M., & Mia, M.B. (2018). Modelling of soil texture and its verification with related soil properties. Soil Research, 56(4), 421-428. https://doi.org/10.1071/ sr17252
16. Jenny, H. (1994). Factors of soil formation: a system of quantitative pedology. Courier Corporation.
17. John, K., Abraham Isong, I., Michael Kebonye, N., Okon Ayito, E., Chapman Agyeman, P., & Marcus Afu, S. (2020). Using machine learning algorithms to estimate soil organic carbon variability with environmental variables and soil nutrient indicators in an alluvial soil. Land, 9(12), 487. https://doi.org/10.3390/land9120487
18. Kaya, F., & Başayiğit, L. (2022). Spatial prediction and digital mapping of soil texture classes in a Floodplain using multinomial Logistic regression. In Intelligent and Fuzzy Techniques for Emerging Conditions and Digital Transformation: Proceedings of the INFUS 2021 Conference, held August 24-26, 2021. Volume 2(pp. 463-473). Springer International Publishing. https://doi.org/10.1007/978-3-030-85577-2_55.
19. Khosravani, P., Baghernejad, M., Moosavi, A.A., & FallahShamsi, S.R. (2023). Digital mapping to extrapolate the selected soil fertility attributes in calcareous soils of a semiarid region in Iran. Journal of Soils and Sediments, 23(11), 4032-4054. https://doi.org/10.1007/s11368-023-03548-1
20. Khosravani, P., Baghernejad, M., Moosavi, A.A., & Rezaei, M. (2023). Digital mapping and spatial modeling of some soil physical and mechanical properties in a semi-arid region of Iran. Environmental Monitoring and Assessment, 195(11), 1367. https://doi.org/10.1007/s10661-023-11980-6
21. Lee, S., Baek, W.K., Jung, H.S., & Lee, S. (2020). Susceptibility mapping on urban landslides using deep learning approaches in Mt. Umyeon. Applied Sciences, 10(22), 8189. https://doi.org/10.3390/app10228189
22. Loiseau, T., Chen, S., Mulder, V.L., Dobarco, M.R., Richer-de-Forges, A.C., Lehmann, S., ... & Arrouays, D. (2019). Satellite data integration for soil clay content modelling at a national scale. International Journal of Applied Earth Observation and Geoinformation, 82, 101905. https://doi.org/10.1016/j.jag.2019.101905
23. Lucas, M., Schlüter, S., Vogel, H.J., & Vetterlein, D. (2019). Soil structure formation along an agricultural chronosequence. Geoderma, 350, 61-72. https://doi.org/10.1016/j.geoderma.2019.04.041
24. Ma, Y., Minasny, B., Malone, B.P., & Mcbratney, A.B. (2019). Pedology and digital soil mapping (DSM). European Journal of Soil Science, 70(2), 216-235. https://doi.org/10.1111/ejss.12790.
25. Mahler, P.J. (1970). Manual of Multipurpose Land Classification. Report no. 212. Soil and Water Research Institute, Tehran. Iran. (In Persian)
26. Mahmoudzadeh, H., Matinfar, H. R., Taghizadeh-Mehrjardi, R., Kerry, R. (2020). Spatial prediction of soil organic carbon using machine learning techniques in western Iran. Geoderma Regional, 21, e00260. https://doi.org/10.1016/j.geodrs.2020.e00260
27. Maleki, S., Karimi, A., Mousavi, A., Kerry, R., & Taghizadeh-Mehrjardi, R. (2023). Delineation of soil management zone maps at the regional scale using machine learning. Agronomy, 13(2), 445. https://doi.org/10.3390/agronomy 13020445
28. Malone, B., & Searle, R. (2021). Updating the Australian digital soil texture mapping (Part 1*): re-calibration of field soil texture class centroids and description of a field soil texture conversion algorithm. Soil Research, 59(5), 419-434. https://doi.org/10.1071/SR20283
29. McBratney, A.B., Santos, M.M., & Minasny, B. (2003). On digital soil mapping. Geoderma, 117(1-2), 3-52. https://doi.org/10.1016/S0016-7061(03)00223-4
30. Minasny, B., & McBratney, A.B. (2006). A conditioned Latin hypercube method for sampling in the presence of ancillary information. Computers & geosciences, 32(9), 1378-1388.https://doi.org/10.1016/j.cageo.2005.12.009
31. Mosleh, Z., Salehi, M. H., Jafari, A., Borujeni, I.E., & Mehnatkesh, A. (2016). The effectiveness of digital soil mapping to predict soil properties over low-relief areas. Environmental Monitoring and Assessment, 188, 1-13. https://doi.org/10.1007/s10661-016-5204-8
32. Mousavi, S.R., Sarmadian, F., Omid, M., & Bogaert, P. (2021). Digital modeling of three-dimensional soil salinity variation using machine learning algorithms in arid and semi-arid lands of Qazvin Plain. Iranian Journal of Soil and Water Research, 52(7), 1915-1929. https://doi.org/10.22059/ijswr.2021.323030.668957
33. Mousavi, S.R., Sarmadian, F., Angelini, M.E., Bogaert, P., & Omid, M. (2023). Cause-effect relationships using structural equation modeling for soil properties in arid and semi-arid regions. Catena, 232, 107392. https://doi.org/ 10.1016/j.catena.2023.107392
34. Mousavi, S.R., Parsayi, F., Rahmani, A., Sedri, M.H., & Kohsar Bostani, M. (2020). Spatial prediction some of the surface soil properties using interpolation and machine learning models. Journal of Soil Management and Sustainable Production, 10(3), 27-49. (In Persian with English abstract). https://doi.org/10.22069/EJSMS .2021.17251.1916
35. Mousavi, S.R., Sarmadian, F., Rahmani, A., & Khamoshi, S.E. (2019). Digital soil mapping with regression tree classification approaches by RS and geomorphometry covariate in the Qazvin Plain, Iran. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 42, 773-777.
36. Ließ, M., Glaser, B., & Huwe, B. (2012). Uncertainty in the spatial prediction of soil texture: comparison of regression tree and Random Forest models. Geoderma, 170, 70-79. https://doi.org/10.1016/j.geoderma.2011.10.010
37. Organization of Geology and Mineral Explorations of Ira, (1995). Geology map (1:100000) scale. Marvdasht, Fars,
38. Ostovari, Y., Moosavi, A.A., Mozaffari, H., & Pourghasemi, H.R. (2021). RUSLE model coupled with RS-GIS for soil erosion evaluation compared with T value in Southwest Iran. Arabian Journal of Geosciences, 14, 1-15. https:// doi.org/10.1007/s12517-020-06405-4
39. Olaya, V. I. C. T. O. R. . A gentle introduction to SAGA GIS. The SAGA User Group eV, Gottingen, Germany, 208.
40. Padarian, J., Minasny, B., & McBratney, A.B. (2019). Machine learning and soil sciences: A review aided by machine learning tools. SOIL, 6, 35-52. https://doi.org/10.5194/soil-6-35-2020.
41. 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.2017.10.002
42. Paramasivam, C.R. (2019). Merits and demerits of GIS and geostatistical techniques. GIS and Geostatistical Techniques for Groundwater Science, 17-21.
43. Poppiel, R.R., Lacerda, M.P., Demattê, J.A., Oliveira Jr, M.P., Gallo, B.C., & Safanelli, J.L. (2019). Pedology and soil class mapping from proximal and remote sensed data. Geoderma, 348, 189-206. https://doi.org/10.1016/ j.geoderma.2019.04.028
44. Parent, E.J., Parent, S.É., & Parent, L.E. (2021). Determining soil particle-size distribution from infrared spectra using machine learning predictions: Methodology and modeling. Plos One, 16(7), e0233242. https://doi.org/10.1371/journal.pone.0233242
45. Radočaj, D., Jurišić, M., Antonić, O., Šiljeg, A., Cukrov, N., Rapčan, I., Plaščak, I., & Gašparović, M. (2022). A multiscale cost–benefit analysis of digital soil mapping methods for sustainable land management. Sustainability, 14(19), 12170. https://doi.org/10.3390/su141912170
46. Riza, S., Sekine, M., Kanno, A., Yamamoto, K., Imai, T., & Higuchi, T. (2021). Modeling soil landscapes and soil textures using hyperscale terrain attributes. Geoderma, 402, 115177.
47. Rossel, R.V., & McBratney, A.B. (2008). Diffuse reflectance spectroscopy as a tool for digital soil mapping. In Digital soil mapping with limited data(pp. 165-172). Dordrecht: Springer Netherlands. https://doi.org/ 10.1007/978-1-4020-8592-5_13.
48. Sahraei, N., Landi, A., & Hojati, S. (2022). Digital mapping of soil texture components in part of Khuzestan plain lands using machine learning models. Iranian Journal of Soil and Water Research, 53(10), 2261-2276. https://doi.org/ 10.22059/ijswr.2022.348442.669360
49. 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, 104149. https://doi.org/10.1016/j.catena.2019.104149
50. Sahraei, N., Landi, A., & Hojati, S. (2022). Digital mapping of soil texture components in part of Khuzestan plain lands using machine learning models. Iranian Journal of Soil and Water Research, 53(10), 2261-2276. (In Persian with English abstract). https://doi.org/10.22059/ijswr.2022.348442.669360
51. Sørensen, H. (2004). RPD revisited – a mean to distinguish between poor and good predictions. Journal of Near Infrared Spectroscopy, 12(6), 321-327.
52. Swain, S.R., Chakraborty, P., Panigrahi, N., Vasava, H.B., Reddy, N.N., Roy, S., Majeed, I., & Das, B.S. (2021). Estimation of soil texture using Sentinel-2 multispectral imaging data: An ensemble modeling approach. Soil and Tillage Research, 213, 105134. https://doi.org/10.1016/j.still.2021.105134
53. Taghizadeh‐Mehrjardi, R., Toomanian, N., Khavaninzadeh, A. R., Jafari, A., & Triantafilis, J. (2016). Predicting and mapping of soil particle‐size fractions with adaptive neuro‐fuzzy inference and ant colony optimization in central I ran. European Journal of Soil Science, 67(6), 707-725. https://doi.org/10.1111/ejss.12382
54. Tashayo, B., Honarbakhsh, A., Akbari, M. & Eftekhari, M. (2020). Land suitability assessment for maize farming using a GIS-AHP method for a semi-arid region, Iran. Journal of the Saudi Society of Agricultural Sciences, 19(5), 332-338. https://doi.org/10.1016/j.jssas.2020.03.003
55. Tümsavaş, Z., Tekin, Y., Ulusoy, Y., & Mouazen, A.M. (2019). Prediction and mapping of soil clay and sand contents using visible and near-infrared spectroscopy. Biosystems Engineering, 177, 90-100. https://doi.org/ 10.1016/j.biosystemseng.2018.06.008
56. 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
57. Wallach, D., Makowski, D., Jones, J.W., & Brun, F. (2006). Working with dynamic crop models: evaluation, analysis, parameterization, and applications. Elsevier.
58. Wang, Z., Shi, W., Zhou, W., Li, X., & Yue, T. (2020). Comparison of additive and isometric log-ratio transformations combined with machine learning and regression kriging models for mapping soil particle size fractions. Geoderma, 365, 114214. https://doi.org/10.1016/j.geoderma.2020.114214
59. Wilding, L.P. (1985). Spatial variability: its documentation, accommodation and implication to soil surveys. In: Soil Spatial Variability, Las Vegas NV, pp. 166–194.
60. 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.2018.09.006
61. Ziadat, F.M., 2005. Analyzing digital terrain attributes to predict soil attributes for a relatively large area. Soil Science Society of America Journal, 69, 1590–1599. https://doi.org/10.2136/sssaj2003.0264
62. Zinck, J.A., Metternicht, G., Bocco, G., & Del Valle, H.F. (2015). Geopedology: An integration of geomorphology and pedology for soil and landscape studies. Springer.
63. Zhang, Y.Y., Wu, W., & Liu, H. (2019). Factors affecting variations of soil pH in different horizons in hilly regions. Plos One, 14(6), e0218563. https://doi.org/10.1371/journal.pone.0218563
64. Zhang, X., Zhang, W.C., Wu, W., & Liu, H.B. (2023). Horizontal and vertical variation of soil clay content and its controlling factors in China. Science of The Total Environment, 864, 161141.