Skip to main content

Advertisement

SpringerLink
Log in

Parameterisation of infiltration models using neural network under simulated hillslope experiments for different land-uses and slopes

  • Published:
Journal of Earth System Science Aims and scope Submit manuscript

Abstract

The study focuses on the effects of slope on the infiltration process and runoff generation for the soil samples from landfill, agricultural and bare surfaces under similar simulated rainfall. Hillslope experimental setup was designed to conduct the experiments with the slope of 10, 20 and 30°. The results indicate that minimum and maximum infiltrated volumes were presented by landfill soil (at 30°) and agricultural soil (at 10°), respectively. Results also reported that, apart from the slope, the amount of induced runoff was significantly affected by land uses and type of surface erosion. The experimental observations were used to estimate empirical infiltration model parameters using nonlinear least square and Artificial Neural Network (ANN) two-layer back-propagation, describing the variation of infiltration rates with slope and soil samples, which showed a decent agreement with the observed data presenting an average R2 and NSE as 0.88 and 0.92, respectively. The efficiency of ANN performance was also found to be associated with a higher proportion of training data. The findings have extensive implications for evaluating the rainfall-runoff process and infiltration estimation for chosen land uses in the urban area.

Research highlights

  1. 1.

    The infiltration process was significantly affected by urban land uses (agricultural land, bare surface and solid waste landfill) as soil samples from landfill and agricultural soil samples showed the lowest and highest cumulative infiltration, respectively, for selected slope ranges 10, 20, 30°.

  2. 2.

    An increment in slope from 10° to 20° caused the reduction in cumulative infiltration by 10.1% and 17.2% and 3% for bare surface, landfill soil and agricultural soil, respectively. Similarly, an increment in slope from 10° to 30° caused the reduction of infiltrated volume by 23.9, 23.8 and 25.4% landfill soil, bare surface soil and agricultural soil, respectively.

  3. 3.

    An increment in slope from 10° to 20° caused 1.31, 1.13 and 1.27 times increment in the runoff for bare surface, landfill soil and agricultural soil, respectively. Similarly, an increment in slope from 10° to 30° caused a 1.65, 1.25, and 4.65 times rise in runoff volume at the downslope for bare surface, landfill soil and agricultural soil, respectively.

  4. 4.

    Experiments had shown no significant relation of slope variation with initial infiltration rate (fo) and constant infiltration rate (fc), although rates were found dependent on land uses and highly influenced by surface erosion mechanism.

  5. 5.

    The Horton model has demonstrated the most efficient results compared to other models for all focused inclined surfaces of soil samples extracted from targeted land uses.

  6. 6.

    The ANN model can be used for parameter estimation based on the field experimental inputs for different land uses with various slopes. The overall performance of the ANN model was found suitable for estimation of the model parameters by evaluating average R2 and NSE as 0.943 and 0.93, respectively, for all mentioned scenarios.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9

Similar content being viewed by others

Abbreviations

F :

Cumulative infiltration (cm)

α :

Multiplying constant

β :

Exponent parameter

t :

Time of observation (minutes)

f t :

Infiltration rate at time t (cm/min)

f c :

Constant (final) infiltration rate (cm/min)

a :

Multiplying constant (αβ)

b :

Exponent parameter (1 – β)

f o :

Initial infiltration rate (cm/min)

k :

Horton decay coefficient (cm/min)

P :

Precipitation (cm)

r :

Runoff (cm)

R :

Correlation coefficient

E :

Error (%)

O(i):

Observed value at i step

S(i):

Simulated value at i step

V :

Normalised variable

V i :

Value of variable at i time step

V min :

Minimum value of variable

V max :

Maximum value of variable

N :

Numbers of neurons in hidden layer (ANN)

\(\overline{O}\) :

Average observed value

\(\overline{S}\) :

Average simulated value

n :

Number of data points

w :

Moisture content (%)

K sat :

Saturated hydraulic conductivity (cm/hour)

References

  • Adams R et al. 2005 Using a rainfall simulator and a physically-based hydrological model to investigate runoff processes in a hillslope; Hydrol. Process. 19(11) 2209–2223, https://doi.org/10.1002/hyp.5670.

    Article  Google Scholar 

  • Angelaki A, Singh Nain S, Singh V and Sihag P 2021 Estimation of models for cumulative infiltration of soil using machine learning methods; ISH J. Hydraul. Eng. 27(2) 162–169, https://doi.org/10.1080/09715010.2018.1531274.

    Article  Google Scholar 

  • Babu R et al. 1979 Rainfall-intensity duration return period equations and nomographs of India; http://krishi.icar.gov.in/jspui/handle/123456789/38572.

  • Bai P, Song X, Wang J, Shi W and Wang Q 2010 A hillslope infiltration and runoff prediction model of neural networks optimised by genetic algorithm; In: 2010 International Conference on Mechanic Automation and Control Engineering, pp. 1256–1259.

  • Benavides I F, Solarte M E, Pabón V, Ordoñez A, Beltrán E, Rosero S and Torres C 2018 The variation of infiltration rates and physical-chemical soil properties across a land cover and land use gradient in a Paramo of southwestern Colombia; J. Soil Water Conserv. 73(4) 400–410, https://doi.org/10.2489/jswc.73.4.400.

    Article  Google Scholar 

  • Bhattacharyya R and Prasad S 2020 Water scarcity in Delhi: Mapping for solutions and the way forward; In: Urban health risk and resilience in Asian Cities (eds) Singh R B, Srinagesh B and Anand S, Springer, https://books.google.co.in/books?id=iajbDwAAQBAJ&dq=water+scarcity+in+delhi&lr=&source=gbs_navlinks_s.

  • Bowden G J, Maier H R and Dandy G C 2012 Real‐time deployment of artificial neural network forecasting models: Understanding the range of applicability; Water Resour. Res. 48(10).

  • Chaudhuri R R and Sharma P 2020 Addressing uncertainty in extreme rainfall intensity for semi-arid urban regions: Case study of Delhi, India; Nat. Hazards 104(3) 2307–2324, https://doi.org/10.1007/s11069-020-04273-5.

    Article  Google Scholar 

  • Chouksey A, Lambey V, Nikam B R, Aggarwal S P and Dutta S 2017 Hydrological modelling using a rainfall simulator over an experimental hillslope plot; Hydrology 4(1), https://doi.org/10.3390/hydrology4010017.

  • Chu X and Mariño M A 2005 Determination of ponding condition and infiltration into layered soils under unsteady rainfall; J. Hydrol. 313(3–4) 195–207.

    Article  Google Scholar 

  • Climatological tables of observations in India 1981–2010; Indian Meteorological Department: Pune, India, 2015, https://imdpune.gov.in/library/public/1981-2010%20CLIM%20NORMALS%20(STATWISE).pdf.

  • Code IS 1498–1970; Classification and identification of soils for general engineering purposes (first revision).

  • Customised rainfall information system 2021 India Meteorological Department: Delhi, India, http://hydro.imd.gov.in.

  • Dunne T and Black R D 1970 Partial area contributions to storm runoff in a small New England watershed; Water Resour. Res. 6(5) 1296–1311.

    Article  Google Scholar 

  • Ekhmaj A I 2010 Predicting soil infiltration rate using artificial neural network; In: 2010 International Conference on Environmental Engineering and Applications, pp. 117–121.

  • Elliott A H et al. 2002 Effect of cattle treading on interrill erosion from hill pasture: Modelling concepts and analysis of rainfall simulator data; Aust. J. Soil Res. 40(6) 963–976, https://doi.org/10.1071/SR01057.

    Article  Google Scholar 

  • Fox D M, Bryan R B and Price A G 1997 The influence of slope angle on final infiltration rate for interrill conditions; Geoderma 80(1–2) 181–194.

    Article  Google Scholar 

  • Gavin K and Xue J 2008 A simple method to analyse infiltration into unsaturated soil slopes; Comput. Geotech. 35(2) 223–230.

    Article  Google Scholar 

  • Ghorbani Dashtaki S, Homaee M, Mahdian M H and Kouchakzadeh M 2009 Site-dependence performance of infiltration models; Water Resour. Manag. 23(13) 2777–2790, https://doi.org/10.1007/s11269-009-9408-3.

    Article  Google Scholar 

  • Hanspal N S, Allison B A, Deka L and Das D B 2013 Artificial neural network (ANN) modeling of dynamic effects on two-phase flow in homogenous porous media; J. Hydroinform. 15(2) 540–554.

    Article  Google Scholar 

  • Horton R E 1933 The role of infiltration in the hydrologic cycle; Eos. Trans. Am. Geophys. Union 14(1) 446–460.

    Article  Google Scholar 

  • Huang J, Wu P and Zhao X 2013 Effects of rainfall intensity, underlying surface and slope gradient on soil infiltration under simulated rainfall experiments; Catena 104 93–102.

    Article  Google Scholar 

  • Indian Standard 1994; IS-2720 (PART 4)-1985-Indian Standard Methods of test for soils grain size analysis (second revision), https://civilengineer.co.in/indian-standard-codes/is-2720-part-4-1985-indian-standard-methods-of-test-for-soils-grain-size-analysissecond-revision/.

  • Jain A and Kumar A 2006 An evaluation of artificial neural network technique for the determination of infiltration model parameters; Appl. Soft Comput. 6(3) 272–282.

    Article  Google Scholar 

  • Jain A and Prasad Indurthy S K V 2004 Closure to ‘Comparative analysis of event-based rainfall-runoff modeling techniques – Deterministic, statistical, and artificial neural networks’ by Ashu Jain and SKV Prasad Indurthy; J. Hydrol. Eng. 9(6) 551–553.

    Article  Google Scholar 

  • Joshi V U and Tambe D T 2010 Estimation of infiltration rate, runoff and sediment yield under simulated rainfall experiments in upper Pravara Basin, India: Effect of slope angle and grass-cover; J. Earth Syst. Sci. 119(6) 763.

    Article  Google Scholar 

  • Kashi H, Emamgholizadeh S and Ghorbani H 2014 Estimation of soil infiltration and cation exchange capacity based on multiple regression, ANN (RBF, MLP), and ANFIS Models; Commun. Soil Sci. Plant Anal. 45(9) 1195–1213, https://doi.org/10.1080/00103624.2013.874029.

    Article  Google Scholar 

  • Khan M N, Gong Y, Hu T, Lal R, Zheng J, Justine M F et al. 2016 Effect of slope, rainfall intensity and mulch on erosion and infiltration under simulated rain on purple soil of south-western Sichuan province, China; Water 8(11) 528.

    Article  Google Scholar 

  • Kim S, Karahan G, Sharma M and Pachepsky Y 2021 Estimating parameters of empirical infiltration models from the global dataset using machine learning; Int. Agrophys. 35(1) 73–81, https://doi.org/10.31545/intagr/132922.

    Article  Google Scholar 

  • Kirkby M 1988 Hillslope runoff processes and models; J. Hydrol. 100(1–3) 315–339.

    Article  Google Scholar 

  • Langhans C, Govers G and Diels J 2013 Development and parameterisation of an infiltration model accounting for water depth and rainfall intensity; Hydrol. Process. 27(25) 3777–3790.

    Article  Google Scholar 

  • Legates D R and McCabe G J Jr 1999 Evaluating the use of ‘goodness-of-fit’ measures in hydrologic and hydroclimatic model validation; Water Resour. Res. 35(1) 233–241.

    Article  Google Scholar 

  • Liu C W, Cheng S W, Yu W S and Chen S K 2003 Water infiltration rate in cracked paddy soil; Geoderma 117(1–2) 169–181.

    Article  Google Scholar 

  • Mishra S K, Tyagi J V and Singh V P 2003 Comparison of infiltration models; Hydrol. Process. 17(13) 2629–2652.

    Article  Google Scholar 

  • Morbidelli R, Saltalippi C, Flammini A, Cifrodelli M, Corradini C and Govindaraju R S 2015 Infiltration on sloping surfaces: Laboratory experimental evidence and implications for infiltration modeling; J. Hydrol. 523 79–85, https://doi.org/10.1016/j.jhydrol.2015.01.041.

    Article  Google Scholar 

  • Morbidelli R, Saltalippi C, Flammini A and Govindaraju R S 2018 Role of slope on infiltration: A review; J. Hydrol. 557 878–886, https://doi.org/10.1016/j.jhydrol.2018.01.019.

    Article  Google Scholar 

  • Moriasi D N, Arnold J G, Van Liew M W, Bingner R L, Harmel R D and Veith T L 2007 Model evaluation guidelines for systematic quantification of accuracy in watershed simulations; Trans. ASABE 50(3) 885–900.

    Article  Google Scholar 

  • Morin J and Benyamini Y 1977 Rainfall infiltration into bare soils; Water Resour. Res. 13(5) 813–817.

    Article  Google Scholar 

  • Mu et al. 2015 Effects of Rainfall intensity and slope gradient on runoff and soil moisture content on different growing stages of spring maise; Water 7(6) 2990–3008, https://doi.org/10.3390/W7062990.

    Article  Google Scholar 

  • National Remote Sensing Centre 2016 Bhuvan – Thematic Data dissemination – Free GIS Data (OGC Services), https://bhuvan-app1.nrsc.gov.in/thematic/thematic/index.php.

  • Niemczynowicz J 1999 Urban hydrology and water management – present and future challenges; Urban Water 1(1) 1–14.

    Article  Google Scholar 

  • Nunes A N, De Almeida A C and Coelho C O 2011 Impacts of land use and cover type on runoff and soil erosion in a marginal area of Portugal; Appl. Geogr. 31(2) 687–699.

    Article  Google Scholar 

  • Parhi P K, Mishra S K and Singh R 2007 A modification to kostiakov and modified kostiakov infiltration models; Water Resour. Manag. 21 1973–1989, https://doi.org/10.1007/s11269-006-9140-1.

    Article  Google Scholar 

  • Rossi M J and Ares J O 2012 Depression storage and infiltration effects on overland flow depth-velocity-friction at desert conditions: Field plot results and model; Hydrol. Earth Syst. Sci. 16(9) 3293–3307.

    Article  Google Scholar 

  • Santra P, Kumar M and Kumawat R N 2021 Characterisation and modeling of infiltration characteristics of soils under major land use systems in hot arid region of India; Agric. Res. 10(3) 417–433, https://doi.org/10.1007/s40003-020-00511-1.

    Article  Google Scholar 

  • Sayari S, Mahdavi-Meymand A and Zounemat-Kermani M 2021 Irrigation water infiltration modeling using machine learning; Comput. Electron. Agric. 180 105921, https://doi.org/10.1016/j.compag.2020.105921.

    Article  Google Scholar 

  • Schoener G, Stone M C and Thomas C 2021 Comparison of seven simple loss models for runoff prediction at the plot, hillslope and catchment scale in the semi-arid southwestern U.S.; J. Hydrol. 598 126490, https://doi.org/10.1016/j.jhydrol.2021.126490.

    Article  Google Scholar 

  • Sepahvand A, Singh B, Ghobadi M and Sihag P 2021 Estimation of infiltration rate using data-driven models; Arab. J. Geosci. 14(1) 1–11, https://doi.org/10.1007/s12517-020-06245-2.

    Article  Google Scholar 

  • Shawul A A, Chakma S and Melesse A M 2019 The response of water balance components to land cover change based on hydrologic modeling and partial least squares regression (PLSR) analysis in the Upper Awash Basin; J. Hydrol. Regional Stud. 26 100640.

    Article  Google Scholar 

  • Shen H, Zheng F, Wen L, Han Y and Hu W 2016 Impacts of rainfall intensity and slope gradient on rill erosion processes at loessial hillslope; Soil Tillage Res. 155 429–436.

    Article  Google Scholar 

  • Shougrakpam S, Sarkar R and Dutta S 2010 An experimental investigation to characterise soil macroporosity under different land use and land covers of northeast India; J. Earth Syst. Sci. 119(5) 655–674.

    Article  Google Scholar 

  • Sihag P, Singh B, Sepah Vand A and Mehdipour V 2020 Modeling the infiltration process with soft computing techniques; ISH J. Hydraul. Eng. 26(2) 138–152, https://doi.org/10.1080/09715010.2018.1464408.

    Article  Google Scholar 

  • Sihag P, Kumar M and Singh B 2021 Assessment of infiltration models developed using soft computing techniques; Geol. Ecol. Landsc. 5(4) 241–251, https://doi.org/10.1080/24749508.2020.1720475.

    Article  Google Scholar 

  • Singh B, Sihag P, Parsaie A and Angelaki A 2021 Comparative analysis of artificial intelligence techniques for the prediction of infiltration process; Geol. Ecol. Landsc. 5(2) 109–118, https://doi.org/10.1080/24749508.2020.1833641.

    Article  Google Scholar 

  • Srinivasulu S and Jain A 2006 A comparative analysis of training methods for artificial neural network rainfall–runoff models; Appl. Soft Comput. 6(3) 295–306.

    Article  Google Scholar 

  • Sy Nestor L 2006 Modelling the infiltration process with a multilayer perceptron artificial neural network; Hydrol. Sci. J. 51(1) 3–20, https://doi.org/10.1623/hysj.51.1.3.

    Article  Google Scholar 

  • Tkáč M and Verner R 2016 Artificial neural networks in business: Two decades of research; Appl. Soft Comput. 38 788–804.

    Article  Google Scholar 

  • Tokar B A S and Johnson P A 1999 Rainfall-runoff modeling using artificial neural networks; J. Hydrol. Eng. 4(3) 232–239.

    Article  Google Scholar 

  • Wallace J S 2000 Increasing agricultural water use efficiency to meet future food production; Agric. Ecosyst. Environ. 82(1–3) 105–119, https://doi.org/10.1016/S0167-8809(00)00220-6.

    Article  Google Scholar 

  • Wischmeier W H 1966 Relation of field-plot runoff to management and physical factors; Soil Sci. Soc. Am. J. 30(2) 272–277.

    Article  Google Scholar 

  • Zison S W and Roqueta A 1984 U.S. Patent No. 4,469,176. Washington DC: U.S. Patent and Trademark Office.

Download references

Author information

Authors and Affiliations

  1. Civil Engineering Department, Indian Institute of Technology Delhi, Autonomous University of India, Delhi, 110 016, India

    Lohit Jain & Sumedha Chakma

Authors
  1. Lohit Jain
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sumedha Chakma
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Lohit Jain: Conceptualisation, methodology, investigation, formal analysis, writing – original draft. Sumedha Chakma: Resources, supervision.

Corresponding author

Correspondence to Lohit Jain.

Additional information

Communicated by Saibal Gupta

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jain, L., Chakma, S. Parameterisation of infiltration models using neural network under simulated hillslope experiments for different land-uses and slopes. J Earth Syst Sci 132, 20 (2023). https://doi.org/10.1007/s12040-022-02033-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s12040-022-02033-6

Keywords

Search

Navigation