Abstract
Laborious and time-consuming tests are required for the determination of the soil–water characteristic curve (SWCC), often leading to the adoption of estimation methods. To answer the challenge of SWCC prediction, numerous pedotransfer functions (PTF) have been developed. Yet, previous studies have not considered the special behavior of bimodal tropical soils. These materials present dual porosity that is generally attributed to particle aggregation. This paper presents a novel PTF, specifically designed for bimodal tropical soils and based on artificial neural networks (ANNs). The model was trained and tested utilizing a database that was assembled containing soils from tropical regions of Brazil and featuring data for the grain-size distribution (GSD), consistency limits, and SWCC. Natural and remolded soils were included in the training database, but no distinction between soil conditions was made in the ANN. GSDs in the aggregated and disaggregated states were used to offer information to the ANN regarding the effect of particle aggregation on the water retention. The developed model was able to reproduce the typical SWCC shape of bimodal soils. Predictions for the degree of saturation were moderately correlated with directly measured data, with a coefficient of determination of 0.69. The air-entry value and residual suction of the macropores proved to be the most difficult SWCC attributes to be estimated. The ANN presented superior performance when compared to other PTFs not designed specifically for bimodal tropical soils, such as the Arya-Paris and ROSETTA models. It can be concluded from the obtained results that the developed ANN architecture and general approach showed a high capability to capture the main features of the SWCC.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
The datasets generated during and/or analyzed during the current study are available from the corresponding author upon reasonable request.
References
ABNT—Associação Brasileira de Normas Técnicas (2016) NBR 6459—soil—determination of the liquid limit. Rio de Janeiro (in Portuguese)
ABNT—Associação Brasileira de Normas Técnicas (2016) NBR 7180—soil—determination of the plastic limit. Rio de Janeiro (in Portuguese).
Achieng KO (2019) 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
Aguiar LA (2010) Contributions to the analysis of the mechanical behavior of compacted soils for use in dams. Dissertation, Universidade de Brasilia (in Portuguese)
Aguiar LA (2014) Analysis of the mechanical behavior of compacted and chemically stabilized soils for use in dams. Thesis, Universidade de Brasilia (in Portuguese)
Albuquerque EAC, Borges LPF, Cavalcante ALB, Machado SB (2022) Prediction of soil water retention curve based on physical characterization parameters using machine learning. Soils Rocks. https://doi.org/10.28927/SR.2022.000222
Almeida JGR, Romão PA, Mascarenha MMA, Sales MM (2015) Erodibility of unsaturated tropical soils in the municipalities of Senador Canedo and Bonfinópolis (GO). Revista Geociências 34(3):441–451 (in Portuguese)
Alves RD, Gitirana GFN Jr, Vanapalli SK (2020) Advances in the modeling of the soil–water characteristic curve using pore-scale analysis. Comput Geotech 127:103766. https://doi.org/10.1016/j.compgeo.2020.103766
Amadi AA, Osinubi KJ, Okoro JI (2023) Hydraulic conductivity of unsaturated specimens of lateritic soil-bentonite mixtures. Geotech Geol Eng. https://doi.org/10.1007/s10706-023-02524-3
Amanabadi S, Vazirinia M, Vereecken H, Vakilian KA, Mohammadi MH (2019) Comparative study of statistical, numerical and machine learning-based pedotransfer functions of water retention curve with particle size distribution data. Eurasian Soil Sci 52:1555–1571. https://doi.org/10.1134/S106422931930001X
Angelim RR, Cunha RP, Sales MM (2016) Determining the elastic deformation modulus from a compacted earth embankment via laboratory and Ménard pressuremeter tests. Soils Rocks 39(3):285–300. https://doi.org/10.28927/SR.393285
Araujo AG (2010) Performance analysis of infiltration wells in the city of Goiânia-GO. Dissertation, Universidade Federal de Goiás (in Portuguese)
Araujo AG, Souza JC, Alves EC, Silva IL, Correchel V (2017) Application of models of adjustments of soil water characteristics curves in tropical soils. Revista Mirante 10(5a) (in Portuguese)
Arya LM, Paris JF (1981) A physicoempirical model to predict soil moisture characteristics from particle-size distribution and bulk density data. Soil Sci Soc Am J 45:1023–1030. https://doi.org/10.2136/sssaj1981.03615995004500060004x
Aubertin M, Mbonimpa M, Bussière B, Chapuis RP (2003) A model to predict the water retention curve from basic geotechnical properties. Can Geotech J 40(6):1104–1122. https://doi.org/10.1139/t03-054
Ayala RJL (2020) Soil improvement with fibers from the poultry industry. Thesis, Universidade de Brasilia (in Portuguese)
Bayat H, Neyshaburi MR, Mahammadi K, Nariman-Zadeh N, Irannejad M, Gregory AS (2013) Combination of artificial neural networks and fractal theory to predict soil water retention curve. Comput Electron Agric 92:92–103. https://doi.org/10.1016/j.compag.2013.01.005
Bayat H, Mazaheri B, Mohanty BP (2019) Estimating soil water characteristic curve using landscape features and soil thermal properties. Soil Tillage Res 189:1–14. https://doi.org/10.1016/j.still.2018.12.018
Belik AA, Bolotov AG, Shein EV, Kokoreva AA, Levin AA, Patrushev VY (2019) Application of neural network pedotransfer functions to calculate soil water retention curve. In: IOP conference series: earth and environmental science. IOP Publishing, p 012008
Borges CR (2014) Microstructural study of the hydromechanical behavior of the soil of Brasília-DF. Thesis, Universidade de Brasilia (in Portuguese)
Campos-Guereta I, Dawson A, Thom N (2021) An alternative continuous form of Arya and Paris model to predict the soil water retention curve of a soil. Adv Water Resour 154:103968. https://doi.org/10.1016/j.advwatres.2021.103968
Carducci CE, Oliveira GC, Severiano EC, Zeviani WM (2011) Modeling the water retention curve in Oxisols using the Double Van Genuchten Equation. Revista Brasileira de Ciência do Solo 35(1):77–86. https://doi.org/10.1590/S0100-06832011000100007. (in Portuguese)
Camapum de Carvalho J, Gitirana GFN Jr (2021) Unsaturated soils in the context of tropical soils. Soils Rocks. https://doi.org/10.28927/SR.2021.068121
Carvalho RB (2014) Geotechnical evaluation of stormwater infiltration wells. Universidade de Brasilia (in Portuguese), Thesis
D’Emilio A, Aiello R, Consoli S, Vanella D, Iovino M (2018) Artificial neural networks for predicting the water retention curve of sicilian agricultural soils. Water 10(10):1431. https://doi.org/10.3390/w10101431
Dias MCC (2014) Feasibility of using tropical soil and construction waste in landfill cover systems. Dissertation, Universidade Federal de Goiás (in Portuguese)
Diemer F (2014) Characterization of the strength of a tropical soil from the dynamic cone penetration test with variable energy (PANDA). Dissertation, Universidade Federal de Goiás (in Portuguese)
Ebrahimi E, Bayat H, Neyshaburi MR, Abyaneh HZ (2014) Prediction capability of different soil water retention curve models using artificial neural networks. Arch Agron Soil Sci 60(6):859–879. https://doi.org/10.1080/03650340.2013.837219
Falcão PR, Baroni M, Masutti GC, Pinheiro RJB, Fagundes DF (2023) Assessment of the impact of inundation on the strength of a lateritic and collapsible soil. Geotech Geol Eng 41(8):4761–4773. https://doi.org/10.1007/s10706-023-02545-y
Farias WM (2012) Evolutionary processes of chemical weathering and their action on the hydromechanical behavior of soils from the central plateau. Thesis, Universidade de Brasilia (in Portuguese)
Foko Tamba C, Kengni L, Tematio P, Manefouet BI, Kenfack JV (2022) Assessment of lateritic gravelled materials for use in road pavements in Cameroon. Geotech Geol Eng 40(8):4195–4215. https://doi.org/10.1007/s10706-022-02151-4
Franco VH, Gitirana GFN Jr, Assis AP (2019) Probabilistic assessment of tunneling-induced building damage. Comput Geotech 113:103097. https://doi.org/10.1016/j.compgeo.2019.103097
Fredlund DG (2000) The 1999 RM Hardy Lecture: The implementation of unsaturated soil mechanics into geotechnical engineering. Can Geotech J 37(5):963–986. https://doi.org/10.1139/t00-026
Fredlund DG, Xing A (1994) Equations for the soil-water characteristic curve. Can Geotech J 31(4):521–532. https://doi.org/10.1139/t94-061
Fredlund DG, Xing A, Huang S (1994) Predicting the permeability function for unsaturated soils using the soil–water characteristic curve. Can Geotech J 31(4):533–546. https://doi.org/10.1139/t94-062
Fredlund DG, Xing A, Fredlund MD, Barbour SL (1996) The relationship of the unsaturated soil shear strength to the soil–water characteristic curve. Can Geotech J 33(3):440–448. https://doi.org/10.1139/t96-065
Fredlund DG, Rahardjo H, Fredlund MD (2012) Unsaturated soil mechanics in engineering practice. John Wiley & Sons Inc
Freitas JB, Rezende LR, Gitirana GFN Jr (2020) Prediction of the resilient modulus of two tropical subgrade soils considering unsaturated conditions. Eng Geol 270:105580. https://doi.org/10.1016/j.enggeo.2020.105580
Garg A, Wani I, Zhu H, Kushvaha V (2022) Exploring efficiency of biochar in enhancing water retention in soils with varying grain size distributions using ANN technique. Acta Geotech 17:1315–1326. https://doi.org/10.1007/s11440-021-01411-6
Gitirana Jr GFN (2005) Weather-related geo-hazard assessment model for railway embankment stability. Thesis, University of Saskatchewan
Gitirana GFN Jr, Fredlund DG (2004) Soil–water characteristic curve equation with independent properties. J Geotech Geoenviron Eng 130(2):209–212. https://doi.org/10.1061/(ASCE)1090-0241(2004)130:2(209)
Gitirana GFN Jr, Fredlund DG (2016) Statistical assessment of hydraulic properties of unsaturated soils. Soils Rocks 39(1):81–95. https://doi.org/10.28927/SR.391081
Grau EDA (2014) Effect of moisture variation on thrust in tropical soils. Dissertation, Universidade de Brasilia (in Portuguese).
Gomes AC (2015) Monitoring of a spaced pile retaining wall considering suction profile. Dissertation, Universidade Federal de Goiás (in Portuguese).
Haghverdi A, Cornelis WM, Ghahraman B (2012) A pseudo-continuous neural network approach for developing water retention pedotransfer functions with limited data. J Hydrol 442:46–54. https://doi.org/10.1016/j.jhydrol.2012.03.036
Haghverdi A, Öztürk HS, Durner W (2018) Measurement and estimation of the soil water retention curve using the evaporation method and the pseudo continuous pedotransfer function. J Hydrol 563:251–259. https://doi.org/10.1016/j.jhydrol.2018.06.007
Haykin S (1999) Neural networks: a comprehensive foundation. Delhi, India
Jain SK, Singh VP, van Genuchten MT (2004) Analysis of soil water retention data using artificial neural networks. J Hydrol Eng 9(5):415–420. https://doi.org/10.1061/(ASCE)1084-0699(2004)9:5(415)
Javanshir S, Bayat H, Gregory AS (2020) Effect of free swelling index on improving estimation of the soil moisture retention curve by different methods. CATENA 189:104479. https://doi.org/10.1016/j.catena.2020.104479
Jesus AC (2013) Multidisciplinary investigation of linear erosive processes: a case study of the city of Anápolis-GO. Universidade de Brasilia (in Portuguese), Thesis
KERAS (2022) Keras. https://keras.io/. Acessed 13 March 2022
Koekkoek EJW, Booltink H (1999) Neural network models to predict soil water retention. Eur J Soil Sci 50(3):489–495. https://doi.org/10.1046/j.1365-2389.1999.00247.x
Leong EC, He L, Rahardjo H (2002) Factors affecting the filter paper method for total and matric suction measurements. Geotech Test J 25(3):322–333. https://doi.org/10.1520/GTJ11094J
Li Y, Vanapalli SK (2021) Prediction of soil-water characteristic curves using two artificial intelligence (AI) models and AI aid design method for sands. Can Geotech J 59(1):129–143. https://doi.org/10.1139/cgj-2020-0562
Lopera JFB (2016) Influence of microstructure on the mechanical behavior of natural and compacted tropical soils. Dissertation, Universidade de Brasilia (in Portuguese)
Luiz GC (2012) Influence of the soil-atmosphere relationship on the hydromechanical behavior of unsaturated tropical soils: case study—municipality of Goiânia-GO. Thesis, Universidade de Brasilia (in Portuguese)
Matos THC (2011) Hydro-mechanical characterization of phosphogypsum and soil-phosphogypsum mixtures. Dissertation, Universidade de Brasilia (in Portuguese)
Melo TM, Pedrollo OC (2015) Artificial neural networks for estimating soil water retention curve using fitted and measured data. Appl Environ Soil Sci. https://doi.org/10.1155/2015/535216
Mendes TA, Pereira SAS, Souza WAR, Rebolledo JFR, Gitirana GFN Jr, Sales MM, Luz MP (2022) Physical and numerical modelling of infiltration and runoff in unsaturated exposed soil using a rainfall simulator. Soil Res 61(3):267–283. https://doi.org/10.1071/SR22181
Miguel MG, Bonder BH (2012) Soil–water characteristic curves obtained for a colluvial and lateritic soil profile considering the macro and micro porosity. Geotech Geol Eng 30:1405–1420. https://doi.org/10.1007/s10706-012-9545-y
Minasny B, McBratney AB (2002) The neuro-m method for fitting neural network parametric pedotransfer functions. Soil Sci Soc Am J 66(2):352–361. https://doi.org/10.2136/sssaj2002.3520
Minasny B, Mcbratney AB, Bristow KL (1999) Comparison of different approaches to the development of pedotransfer functions for water-retention curves. Geoderma 93(3–4):225–253. https://doi.org/10.1016/S0016-7061(99)00061-0
Neves JP, Alves RD, Gitirana Jr. GFN, Mendes TA (2022) Application of a soil-water characteristic curve prediction model to bimodal tropical soils. In: XX Congresso Brasileiro de Mecânica dos Solos e Engenharia Geotécnica, Campinas, Brazil (in Portuguese)
Ng CW, Pang YW (2000) Influence of stress state on soil-water characteristics and slope stability. J Geotech Geoenviron Eng 126(2):157–166. https://doi.org/10.1061/(ASCE)1090-0241(2000)126:2(157)
Ottoni MV, Ottoni Filho TB, Schaap MG, Lopes-Assad MLRC, Rotunno Filho OC (2018) Hydrophysical database for Brazilian soils (HYBRAS) and pedotransfer functions for water retention. Vadose Zone J 17(1):1–17. https://doi.org/10.2136/vzj2017.05.0095
Pachepsky YA, Timlin D, Varallyay GY (1996) Artificial neural networks to estimate soil water retention from easily measurable data. Soil Sci Soc Am J 60(3):727–733. https://doi.org/10.2136/sssaj1996.03615995006000030007x
Pham K, Kim D, Yoon Y, Choi H (2019) Analysis of neural network based pedotransfer function for predicting soil water characteristic curve. Geoderma 351:92–102. https://doi.org/10.1016/j.geoderma.2019.05.013
Pham TA, Sutman M, Medero GM (2023) Validation, reliability, and performance of shear strength models for unsaturated soils. Geotech Geol Eng 41(7):4271–4309. https://doi.org/10.1007/s10706-023-02520-7
Queiroz ACG (2015) Study of the microstructural behavior of compacted tropical soils. Thesis, Universidade de Brasilia (in Portuguese)
Qian J, Lin Z, Shi Z (2022) Experimental and modeling study of water-retention behavior of fine-grained soils with dual-porosity structures. Acta Geotech 17(8):3245–3258. https://doi.org/10.1007/s11440-022-01483-y
Rahardjo H, Satyanaga A, D’Amore GAR, Leong EC (2012) Soil–water characteristic curves of gap-graded soils. Eng Geol 125:102–107. https://doi.org/10.1016/j.enggeo.2011.11.009
Rastgou M, Bayat H, Gregory MMAS (2022) Estimating soil water retention curve by extreme learning machine, radial basis function, M5 tree and modified group method of data handling approaches. Water Resour Res. https://doi.org/10.1029/2021WR031059
Rudiyanto MB, Chaney NW, Maggi F, Giap SGE, Shah RM, Fiantis D, Setiawan BI (2021) Pedotransfer functions for estimating soil hydraulic properties from saturation to dryness. Geoderma 403:115194. https://doi.org/10.1016/j.geoderma.2021.115194
Saha S, Gu F, Luo X, Lytton RL (2018) Prediction of soil-water characteristic curve for unbound material using Fredlund–Xing equation-based ANN approach. J Mater Civ Eng 30(5):06018002. https://doi.org/10.1061/(ASCE)MT.1943-5533.0002241
Satyanaga A, Rahardjo H, Leong EC, Wang JY (2013) Water characteristic curve of soil with bimodal grain-size distribution. Comput Geotech 48:51–61. https://doi.org/10.1016/j.compgeo.2012.09.008
Satyanaga A, Rahardjo H, Zhai Q, Moon S-W, Kim J (2023) Modelling particle-size distribution and estimation of soil–water characteristic curve utilizing modified lognormal distribution function. Geotech Geol Eng. https://doi.org/10.1007/s10706-023-02638-8
Schaap MG, Bouten W (1996) Modeling water retention curves of sandy soils using neural networks. Water Resour Res 32(10):3033–3040. https://doi.org/10.1029/96WR02278
Schaap MG, Leij FJ (1998) Using neural networks to predict soil water retention and soil hydraulic conductivity. Soil Tillage Res 47(1–2):37–42. https://doi.org/10.1016/S0167-1987(98)00070-1
Schaap MG, Leij FJ, van Genuchten MT (2001) Rosetta: a computer program for estimating soil hydraulic parameters with hierarchical pedotransfer functions. J Hydrol 251(3–4):163–176. https://doi.org/10.1016/S0022-1694(01)00466-8
Skalová J, Čistý M, Bezák J (2011) Comparison of three regression models for determining water retention curves. J Hydrol Hydromech 59(4):275–284. https://doi.org/10.2478/v10098-011-0023-7
Sillers WS, Fredlund DG, Zakerzadeh N (2001) Mathematical attributes of some soil–water characteristic curve models. Geotech Geol Eng. https://doi.org/10.1023/A:1013109728218
Silva MTMG (2009) Methodology for determining parameters for unsaturated soils using tests with known moisture. Dissertation, Universidade de Brasilia (in Portuguese)
Silva AP, Tormena CA, Fidalski J, Imhoff S (2008) Funções de pedotransferência para as curvas de retenção de água e de resistência do solo à penetração. Rev Bras Ciênc Solo 32(1):1–10. https://doi.org/10.1590/S0103-84782007000500015
Silva AC, Armindo RA, Prevedello CL (2020) Splintex 2.0: a physically-based model to estimate water retention and hydraulic conductivity parameters from soil physical data. Comput Electron Agric 169:105157. https://doi.org/10.1016/j.compag.2019.105157
Sobotkova M, Snehota M, Dohnal M, Ray C (2011) Determination of hydraulic properties of a tropical soil of Hawaii using column experiments and inverse modeling. Rev Bras Ciênc Solo 35(4):1229–1239. https://doi.org/10.1590/S0100-06832011000400016
Souza WAR, Pereira SAS, Mendes TA, Costa RF, Gitirana GFN Jr, Rebolledo JF (2022) Statistical evaluation of testing conditions on the saturated hydraulic conductivity of Brazilian lateritic soils using artificial intelligence approaches. Sci Rep 12:20381. https://doi.org/10.1038/s41598-022-24779-1
Tomasella J, Hodnett MG (1998) Estimating soil water retention characteristics from limited data in Brazilian Amazonia. Soil Sci 163(3):190–202. https://doi.org/10.1097/00010694-199803000-00003
Tomasella J, Hodnett MG, Rossato L (2000) Pedotransfer functions for the estimation of soil water retention in Brazilian soils. Soil Sci Soc Am J 64(1):327–338. https://doi.org/10.2136/sssaj2000.641327x
van Genuchten MT (1980) A closed-form equation for predicting the hydraulic conductivity of unsaturated soils. Soil Sci Soc Am J 44(5):892–898. https://doi.org/10.2136/sssaj1980.03615995004400050002x
Vanapalli SK, Fredlund DG, Pufahl DE, Clifton AW (1996) Model for the prediction of shear strength with respect to soil suction. Can Geotech J 33(3):379–392. https://doi.org/10.1139/t96-060
Wanderley Neto RV (2020) Experimental study of soil-concrete interfaces in the context of unsaturated soils. Dissertation, Universidade de Brasilia (in Portuguese)
Xu X, Li H, Sun C, Ramos TB, Darouich H, Xiong Y, Qu Z, Huang G (2021) Pedotransfer functions for estimating soil water retention properties of northern China agricultural soils: development and needs. Irrig Drain 70(4):593–608. https://doi.org/10.1002/ird.2584
Yan W, Birle E, Cudmani R (2021) A new framework to determine general multimodal soil water characteristic curves. Acta Geotech 16(10):3187–3208. https://doi.org/10.1007/s11440-021-01245-2
Zhai Q, Rahardjo H, Satyanaga A, Dai G (2020) Estimation of tensile strength of sandy soil from soil–water characteristic curve. Acta Geotech 15:3371–3381. https://doi.org/10.1007/s11440-020-01013-8
Zhai Q, Zhu Y, Rahardjo H, Satyanaga A, Dai G, Gong W, Zhao X, Ou Y (2023) Prediction of the soil–water characteristic curves for the fine-grained soils with different initial void ratios. Acta Geotechnica. https://doi.org/10.1007/s11440-023-01833-4
Zhao Y, Rahardjo H, Satyanaga A, Zhai Q, He J (2023) A general best-fitting equation for the multimodal soil–water characteristic curve. Geotech Geol Eng. https://doi.org/10.1007/s10706-023-02447-z
Zhang Y, Schaap MG (2017) Weighted recalibration of the Rosetta pedotransfer model with improved estimates of hydraulic parameter distributions and summary statistics (Rosetta3). J Hydrol 547:39–53. https://doi.org/10.1016/j.jhydrol.2017.01.004
Zhou AN, Sheng D, Carter JP (2012) Modelling the effect of initial density on soil-water characteristic curves. Géotechnique 62(8):669–680. https://doi.org/10.1680/geot.10.P.120
Acknowledgements
The authors are thankful for the financial support provided by FAPEG (Fundação de Amparo à Pesquisa do Estado de Goiás, in English: Goias State Research Support Foundation).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
dos Santos Pereira, S.A., Silva Junior, A.C., Mendes, T.A. et al. Prediction of Soil–Water Characteristic Curves in Bimodal Tropical Soils Using Artificial Neural Networks. Geotech Geol Eng (2023). https://doi.org/10.1007/s10706-023-02716-x
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10706-023-02716-x