Abstract
Knowledge about the spatial distribution of the soil physical and mechanical properties is crucial for soil management, water yield, and sustainability at the watershed scale; however, the lack of soil data hinders the application of this tool, thus urging the need to estimate soil properties and consequently, to perform the spatial distribution. This research attempted to examine the proficiency of three machine learning methods (RF: Random Forest; Cubist: Regression Tree; and SVM: Support Vector Machine) to predict soil physical and mechanical properties, saturated hydraulic conductivity (Ks), Cohesion measured by fall-cone at the saturated (Psat) and dry (Pdry) states, hardness index (HI) and dry shear strength (SS) by integrating environmental variables and soil features in the Zayandeh-Rood dam watershed, central Iran. To determine the best combination of input variables, three scenarios were examined as follows: scenario I, terrain attributes derivative from a digital elevation model (DEM) + remotely sensed data; scenario II, covariates of scenario I + selected climatic data and some thematic maps; scenario III, covariates in scenario II + intrinsic soil properties (Clay, Silt, Sand, bulk density (BD), soil organic matter (SOM), calcium carbonate equivalent (CCE), mean weight diameter (MWD) and geometric weight diameter (GWD)). The results showed that for Ks, Psat Pdry and SS, the best performance was found by the RF model in the third scenario, with R2= 0.53, 0.32, 0.31 and 0.41, respectively, while for soil hardness index (HI), Cubist model in the third scenario with R2= 0.25 showed the highest performance. For predicting Ks and Psat, soil characteristics (i.e. clay and soil SOM and BD), and land use were the most important variables. For predicting Pdry, HI, and SS, some topographical characteristics (Valley depth, catchment area, mlti-resolution of ridge top flatness index), and some soil characteristics (i.e. clay, SOM and MWD) were the most important input variables. The results of this research present moderate accuracy, however, the methodology employed provides quick and cost-effective information serving as the scientific basis for decision-making goals.
Data Availability: The datasets generated during this study are available from the corresponding author upon reasonable request and within the framework of cooperation agreements and scientific research projects
Abbreviations
- DEM:
-
Digital elevation model
- RF:
-
Random forest
- SVM:
-
Support vector machine
- K s :
-
Soil saturated hydraulic conductivity
- P sat :
-
Cohesion measured by fall-cone at saturated state
- P dry :
-
Cohesion at dry (Pdry) state
- SS:
-
Shear strength
- HI:
-
Soil hardness index
- DSM:
-
Digital soil mapping
- cLHS:
-
Conditional Latin hypercube sampling
- CNBL:
-
Channel network base level
- CSC:
-
Cross-sectional curvature
- TPI:
-
Topographic position index
- RSP:
-
Relative slope position
- MRRTF:
-
Multi-resolution of ridge top flatness index
- MRVBF:
-
Multi-resolution valley bottom flatness index
- TWI:
-
Topographic wetness index
- VDCN:
-
Vertical distance to channel network
- CA:
-
Catchment area
- BD:
-
Bulk density
- SOM:
-
Soil organic matter
- CCE:
-
Calcium carbonate equivalent
- MWD:
-
Mean weight diameter
- GWD:
-
Geometric mean diameter
- MAE:
-
Mean absolute error
- RMSE:
-
Root mean square error
References
Abutaleb MM, Arafat SM (2022) Geomatics-Based Mapping of Hydraulic Soil Properties for Agricultural Management. Ann Agric Sci Moshtohor 60(1): 225–238. https://assjm.journals.ekb.eg
Afyuni M, Mosaddeghi MR (2001) Impact of Tillage System on Soil Physical Properties and Bromide Leaching. J Crop Prod Proc 5(2): 39–53. http://jcpp.iut.ac.ir/article-1-164-en.html
Arthur E, Schjønning P, Moldrup P, et al. (2013) Density and permeability of a loess soil: long-term organic matter effect and the response to compressive stress. Geoderma 193: 236–245. https://doi.org/10.1016/j.geoderma.2012.09.001
Behrens T, Schmidt K, Viscarra Rossel RA, et al. (2018) Spatial modelling with Euclidean distance fields and machine learning. Eur J Soil Sci 69(5): 757–770. https://doi.org/10.1111/ejss.12687
Besalatpour A, Hajabbasi MA, Ayoubi S, et al. (2012) Soil shear strength prediction using intelligent systems: artificial neural networks and an adaptive neuro-fuzzy inference system. J Soil Sci Plant Nutr 58(2): 149–160. https://doi.org/10.1080/00380768.2012.661078
Blake GR, Hartge KH (1986) Particle density. Methods of soil analysis: Part 1 physical and mineralogical methods, 5. pp 377–382.
Bouyoucos GJ (1962) Hydrometer method improved for making particle size analyses of soils 1. J Agron 54(5): 464–465.
Breiman L (2001) Random forests. Mach Learn 45: 5–32. https://doi.org/10.1023/A:1010933404324
Chen S, Arrouays D, Mulder VL (2022) Digital mapping of GlobalSoilMap soil properties at a broad scale: A review. Geoderma 409: 115567. https://doi.org/10.1016/j.geoderma.2021.115567
Coquet Y, Vachier P, Labat C (2005) Vertical variation of near-saturated hydraulic conductivity in three soil profiles. Geoderma 126(3–4): 181–191. https://doi.org/10.1016/j.geoderma.2004.09.014
Czyz EA, Dexter AR, Terelak H, et al. (2002) Content of readily-dispersible clay in the arable layer of some Polish soils. Sustainable Land Management-Environmental Protection-A Soil Physical Approach. Advances in Geoecology. Catena Verlag, Germany, pp.115–124.
Dexter AR (2004) Soil physical quality: Part II. Friability, tillage, tilth and hard-setting. Geoderma 120(3–4): 215–225. https://doi.org/10.1016/j.geoderma.2003.09.005
Dexter AR, Czyz EA, Richard G, Reszkowska A (2008) A user-friendly water retention function that takes account of the textural and structural pore spaces in soil. Geoderma 143: 243–253. https://doi.org/10.1016/j.geoderma.2007.11.010
Diaz-Gonzalez FA, Vuelvas J, Correa CA, et al. (2022) Machine learning and remote sensing techniques applied to estimate soil indicators-Review. Ecol Indic 135, 108517. https://doi.org/10.1016/j.ecolind.2021.108517
Fan CC, Su CF (2008) Role of roots in shear strength of root-reinforced soils and with high moisture content. Ecol Eng 33: 157–166. https://doi.org/10.1016/j.ecoleng.2008.02.013
Farahani E, Mosaddeghi MR, Mahboubi AA, et al. (2019) Prediction of soil hard-setting and physical quality using water retention data. Geoderma, 338: 343–354. https://doi.org/10.1016/j.geoderma.2018.12.012
Giertz S, Junge B, Diekkruger B (2005) Assessing the effects of land use change on soil physical properties and hydrological processes in the sub-humid tropical environment of West Africa. Phys Chem Earth 30(8–10): 485–496. https://doi.org/10.1016/j.pce.2005.07.003
Gilley JE, Elliot WJ, Laflen JM, et al. (1993) Critical shear stress and critical flow rates for initiation of rilling. J Hydrol 142(1–4): 251–271. https://doi.org/10.1016/0022-1694(93)90013-Y
Goebel MO, Bachmann J, Woche SK, et al. (2005) Soil wettability, aggregate stability, and the decomposition of soil organic matter. Geoderma 128(1–2): 80–93. https://doi.org/10.1016/j.geoderma.2004.12.016
González Costa JJ, Reigosa MJ, Matías JM, et al. (2017) Soil Cd, Cr, Cu, Ni, Pb and Zn sorption and retention models using SVM: Variable selection and competitive model. Sci Total Environ 593: 508–522. https://doi.org/10.1016/j.scitotenv.2017.03.195
Guo L, Fu P, Shi T, et al. (2020) Mapping field-scale soil organic carbon with unmanned aircraft system-acquired time series multispectral images. Soil Tillage Res 196: 104477. https://doi.org/10.1016/j.still.2019.104477
Gülser C, Ekberli I, Candemir F (2016) Spatial variability of soil physical properties in a cultivated field. Eurasian J Soil Sci 5(3): 192–200. https://doi.org/10.18393/ejss.2016.3.192-200
Gupta S, Lehmann P, Bonetti S, et al. (2021) Global prediction of soil saturated hydraulic conductivity using random forest in a covariate - based geoTransfer function (CoGTF) framework. J Adv Model Earth Syst 13(4): e2020MS002242. https://doi.org/10.1029/2020MS002242
Hansbo S (1957) A new approach to the determination of the shear strength of clay by the fall-cone test. Royal Swedish geotechnical institute, Proc. No. 14 (Stockholm)
Hatibu N, Hettiaratchi DRP (1993) The transition from ductile flow to brittle failure in unsaturated soils. J Agric Eng Res 54(4): 319–328. https://doi.org/10.1006/jaer.1993.1024
Havaee S, Mosaddeghi MR, Ayoubi S (2015) In situ surface shear strength as affected by soil characteristics and land use in calcareous soils of central Iran. Geoderma 237: 137–148. https://doi.org/10.1016/j.geoderma.2014.08.016
Imhoff S, Da Silva AP, Fallow D (2004) Susceptibility to compaction, load support capacity, and soil compressibility of Hapludox. Soil Sci Soc Am J 68(1): 17–24. https://doi.org/10.2136/sssaj2004.0017
Julien P (1995) Erosion and Sedimentation. Cambridge University Press, UK.
Kalhoro SA, Xu X, Chen W, et al. (2017) Effects of different land-use systems on soil aggregates: a case study of the loess plateau (northern China). Sustainability 9(8): 1349. https://doi.org/10.3390/su9081349
Kamamia AW, Vogel C, Mwangi HM, et al. (2021) Mapping soil aggregate stability using digital soil mapping: A case study of Ruiru reservoir catchment, Kenya. Geoderma Reg 24: e00355. https://doi.org/10.1016/j.geodrs.2020.e00355
Kelishadi H, Mosaddeghi MR, Hajabbasi MA, et al. (2014) Near-saturated soil hydraulic properties as influenced by land use management systems in Koohrang region of central Zagros, Iran. Geoderma 213: 426–434. https://doi.org/10.1016/j.geoderma.2013.08.008
Kemper WD, Rosenau RC (1986) Aggregate stability and size distribution. Methods of soil analysis: Part 1 Physical and mineralogical methods 5: 425–442.
Khalilmoghadam B, Afyuni M, Abbaspour KC, et al. (2009) Estimation of surface shear strength in Zagros region of Iran — a comparison of artificial neural networks and multiple-linear regression models. Geoderma 153: 29–36. https://doi.org/10.1016/j.geoderma.2009.07.008
Klute A. (1986) Water retention: laboratory methods. Methods of soil analysis: part 1 physical and mineralogical methods 5: 635–662.
Kotlar AM, Iversen BV, Jong van Lier Q (2019) Evaluation of parametric and nonparametric machine - learning techniques for prediction of saturated and near - saturated hydraulic conductivity. Vadose Zone J 18(1): 1–13. https://doi.org/10.2136/vzj2018.07.0141
McBratney AB, Mendonça Santos ML, Minasny B, (2003) On digital soil mapping. Geoderma 117: 3–52. https://doi.org/10.1016/S0016-7061(03)00223-4
McNeill SJ, Lilburne LR, Carrick S, et al. (2018) Pedotransfer functions for the soil water characteristics of New Zealand soils using S-map information. Geoderma 326: 96–110. https://doi.org/10.1016/j.geoderma.2018.04.011
Menezes MDD, Silva SHG, Mello CRD, et al. (2018) Knowledge-based digital soil mapping for predicting soil properties in two representative watersheds. Sci Agric 75: 144–153. https://doi.org/10.1590/1678-992X-2016-0097
Minasny B, McBratney AB (2006) A conditioned Latin hypercube method for sampling in the presence of ancillary information. Comput Geosci 32(9): 1378–1388. https://doi.org/10.1016/j.cageo.2005.12.009
Minasny B, McBratney AB, Malone BP, et al. (2013) Digital mapping of soil carbon. Adv Agron 118: 1–47. https://doi.org/10.1016/B978-0-12-405942-9.00001-3
Moayedi H, Tien Bui D, Dounis A, et al. (2019) Novel nature-inspired hybrids of neural computing for estimating soil shear strength. Appl Sci 9(21): 4643. https://doi.org/10.3390/app9214643
Morgan RPC. (2005) Soil Erosion and Conservation. Eur J Soil Sci 56: 681–687. https://doi.org/10.1111/j.1365-2389.2005.0756f.x
Naimi S, Ayoubi S, Zeraatpisheh M, et al. (2021) Ground observations and environmental covariates integration for mapping of soil salinity: a machine learning-based approach. Remote Sens 13(23): 4825. https://doi.org/10.3390/rs13234825
Nelson RE. (1982) Carbonate and gypsum. A S A: 181–197.
Nelson DW, Sommer LE (1982) Total Carbon, Organic Carbon and Organic Matter. Methods of Soil Analysis, Part 2. Chemical and Microbiological Properties, 2nd Edition. ASA-SSSA, Madison. pp 595–579.
R Core Team. (2022) R: A language and environment for statistical computing. R Foundation for Statistical Computing Vienna Austria. URL. https://www.R-project.org
Raiesi F. (2007) The conversion of overgrazed pastures to almond orchards and alfalfa cropping systems may favor microbial indicators of soil quality in Central Iran. Agric Ecosyst Environ 121(4): 309–318. https://doi.org/10.1016/j.agee.2006.11.002
Satyanaga A, Bairakhmetov N, Kim JR, et al. (2022) Role of bimodal water retention curve on the unsaturated shear strength. Appl Sci 12(3): 1266. https://doi.org/10.3390/app12031266
Shahab H, Emami H, Haghnia GH, et al. (2013) Pore size distribution as a soil physical quality index for agricultural and pasture soils in northeastern Iran. Pedosphere 23(3): 312–320. https://doi.org/10.1016/S1002-0160(13)60021-1
Simon A, Geitner C, Katzensteiner K (2020) A framework for the predictive mapping of forest soil properties in mountain areas. Geoderma 371: 114383. https://doi.org/10.1016/j.geoderma.2020.114383
Soil Survey Staff. (2014) Keys to soil taxonomy. U S Department of Agriculture (USDA).
Stefanow D, Dudziñski PA (2021) Soil shear strength determination methods-State of the art. Soil Tillage Res 208: 104881. https://doi.org/10.1016/j.still.2020.104881
Szabó B, Szatmári G, Takács K, et al. (2019) Mapping soil hydraulic properties using random-forest-based pedotransfer functions and geostatistics. Hydrol Earth Syst Sci 23(6): 2615–2635. https://doi.org/10.5194/hess-23-2615-2019
Taghizadeh-Mehrjardi R, Minasny B, Toomanian N, et al. (2019) Digital mapping of soil classes using ensemble of models in Isfahan region, Iran. Soil Syst 3(2): 37. https://doi.org/10.3390/soilsystems3020037
Tajik S, Ayoubi S, Zeraatpisheh M (2020) Digital mapping of soil organic carbon using ensemble learning model in Mollisols of Hyrcanian forests, northern Iran. Geoderma Reg 20: e00256. https://doi.org/10.1016/j.geodrs.2020.e00256
Torri D, Santi E, Marignani M, et al. (2013) The recurring cycles of biancana badlands: Erosion, vegetation and human impact. Catena 106: 22–30. https://doi.org/10.1016/j.catena.2012.07.001
Tóth B, Weynants M, Pásztor L, et al. (2017) 3D soil hydraulic database of Europe at 250 m resolution. Hydrol Process 31(14): 2662–2666. https://doi.org/10.1002/hyp.11203
Van Looy K, Bouma J, Herbst M, et al. (2017) Pedotransfer functions in Earth system science: challenges and perspectives. Rev Geophys 55(4) 1199–1256. https://doi.org/10.1002/2017RG000581
Wadoux AMJ, Samuel-Rosa A, Poggio L, et al. (2020) A note on knowledge discovery and machine learning in digital soil mapping. Eur J Soil Sci 71: 133–136. https://doi.org/10.1111/ejss.12909
Wang C, Zheng M, Song, W, et al. (2017) Impact of 25 years of inorganic fertilization on diazotrophic abundance and community structure in an acidic soil in southern China. Soil Biol Biochem 113: 240–249. https://doi.org/10.1016/j.soilbio.2017.06.019
Wilding L. (1985) Spatial variability: its documentation, accommodation and implication to soil surveys. In: Soil Spatial Variability. Workshop: 166–194. https://doi.org/10.12691/env-3-1-4
Zeraatpisheh M, Jafari A, Bodaghabadi MB, et al. (2020) Conventional and digital soil mapping in Iran: Past, present, and future. Catena 188: 104424. https://doi.org/10.1016/j.catena.2019.104424
Zhang G, Liu F, Song X (2017) Recent progress and future prospect of digital soil mapping: a review. J Integr Agric 16(12): 2871–2885. https://doi.org/10.1016/S2095-3119(17)61762-3
Zhang X, Chen S, Xue J (2023) Improving model parsimony and accuracy by modified greedy feature selection in digital soil mapping. Geoderma 432: 116383. https://doi.org/10.1016/j.geoderma.2023.116383
Zhou X, Lin HS, White EA (2008) Surface soil hydraulic properties in four soil series under different land uses and their temporal changes. Catena 73(2): 180–188. https://doi.org/10.1016/j.catena.2007.09.009
Zhu L, Liao Q, Wang Z, et al. (2022) Prediction of soil shear strength parameters using combined data and different machine learning models. Appl Sci 12(10): 5100. https://doi.org/10.3390/app12105100
Zolfaghari Z, Mosaddeghi MR, Ayoubi S (2016) Relationships of soil shrinkage parameters and indices with intrinsic soil properties and environmental variables in calcareous soils. Geoderma 277: 23–34. https://doi.org/10.1016/j.geoderma.2016.04.022
Acknowledgments
Authors greatly acknowledged the Iranian National Science Foundation (INSF) for the financial support of this research under Project Number 4004169 and Isfahan University of Technology.
Author information
Authors and Affiliations
Contributions
Mohammad Sajjad Ghavami: Filed work, Laboratory analyses, writing original draft; Shamsollah Ayoubi: Methodology, Funding, Conceptualization, Writing-review & editing, Supervision; Mohamamd Reza Mosaddeghi: Conceptualization, Writing-review & editing; Salman Naimi: Data analysis and modeling, visualization.
Corresponding author
Ethics declarations
Conflict of interest: The authors declare no conflict of interest.
Rights and permissions
About this article
Cite this article
Ghavami, M.S., Ayoubi, S., Mosaddeghi, M.R. et al. Digital mapping of soil physical and mechanical properties using machine learning at the watershed scale. J. Mt. Sci. 20, 2975–2992 (2023). https://doi.org/10.1007/s11629-023-8056-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11629-023-8056-z