Comparative performance of multiple linear regression and artificial neural network models in estimating solute-transport parameters

Mohammad Abdul Mojid, A.B.M. Zahid Hossain

Abstract

Indirect estimate of solute-transport parameters through pedo-transfer functions (PTFs) is becoming important due to expensive and time-consuming direct measurement of the parameters for a large number of soils and solutes. This study evaluated the relative performance of PTFs of multiple linear regression (MLR) and Artificial Neural Network (ANN) models in predicting velocity (V), dispersion coefficient (D) and retardation factor (R) of CaCl2, NaAsO2, Cd(NO3)2, Pb(NO3)2 and C9H9N3O2 (carbendazim) in five agricultural soils. V, D and R of the solutes were determined in repacked soil columns under steady-state unsaturated water flow conditions. Textural class, particle size distribution, bulk density, organic carbon, relative pH, clay%, grain size, and uniformity coefficient of the soils were determined. MLR and ANN models were calibrated with the measured data of four soils and verified for another soil. Root-Mean Square Error (RMSE) is significantly smaller (0.015) and modelling efficiency (EF) is significantly larger (0.999) for ANN model than those (0.096 and 0.954, respectively) for MLR model. Negative Mean Absolute Error (MAE) (-0.0002) of MLR model indicates overestimation, while positive MAE (0.00003) of ANN model indicates minimal underestimation. The ANN model is less biased than the MLR model during prediction. Thus, the ANN model can significantly enhance pollution transport prediction through soils with good accuracy.

Keywords

ANN; MLR; Prediction; Soil; Solute

Full Text:

PDF

References

Achat, D. L., Pousse, N., Nicolas, M., Brédoire, F., & Augusto, L. (2016). Soil properties controlling inorganic phosphorus availability: general results from a national forest network and a global compilation of the literature. Biogeochemistry, 127(2), 255-272. https://doi.org/10.1007/s10533-015-0178-0

Alibuyog, N. R. (2007). Development of pedo-transfer functions for predicting soil hydraulic properties and solute-transport parameters using artificial neural network analysis [PhD Thesis, Agricultural Engineering, University of the Philippines Los Baños].

Almasri, M. N., & Kaluarachchi, J. J. (2005). Modular neural networks to predict the nitrate distribution in ground water using the on-ground nitrogen loading and recharge data. Environmental Modelling & Software, 20(7), 851-871. https://doi.org/10.1016/j.envsoft.2004.05.001

Amin Al Manmi, D. A. M., Abdullah, T. O., Al-Jaf, P. M., & Al-Ansari, N. (2019). Soil and Groundwater Pollution Assessment and Delineation of Intensity Risk Map in Sulaymaniyah City, NE of Iraq. Water, 11(10), 2158. https://www.mdpi.com/2073-4441/11/10/2158

Bardak, S., Tiryaki, S., Bardak, T., & Aydin, A. (2016). Predictive Performance of Artificial Neural Network and Multiple Linear Regression Models in Predicting Adhesive Bonding Strength of Wood. Strength of Materials, 48(6), 811-824. https://doi.org/10.1007/s11223-017-9828-x

Black, C. A. (1965). methods of Soil Analysis. Part-I and II. . American Society of Agronomy, Inc, Publisher, Madison, Wisconsin USA.

BS 1377. (1990). Methods of Test for Soils for Civil Engineering Purposes. Classification Tests. Parts 2 and 5.

Chegenizadeh, A., Ghadimi, B., & Nikraz, H. (2014). The prediction of contaminant Transport through Soil: A novel Two-Dimensional model Approach. Journal of Civil & Environmental Engineering, 4, 1-6. https://doi.org/10.4172/2165-784X.1000138

Geman, S., Bienenstock, E., & Doursat, R. (1992). Neural Networks and the Bias/Variance Dilemma. Neural Computation, 4(1), 1-58. https://doi.org/10.1162/neco.1992.4.1.1

Haykin, S. (1994). Neural Networks: A Comprehensive Foundation. Macmillan, New York: Macmillan College Publishing.

Ilaboya, I. (2019). Performance of Multiple Linear Regression (MLR) and Artificial Neural Network (ANN) for the Prediction of Monthly Maximum Rainfall in Benin City, Nigeria. International Journal of Engineering Science and Application, 3(1), 21-37.

Jackson, M. L. (1962). Soil chemical analysis: Advanced course. Inc. Englewood Chiffs, Ny, USA.

Minasny, B., Hopmans, J. W., Harter, T., Eching, S. O., Tuli, A., & Denton, M. A. (2004). Neural Networks Prediction of Soil Hydraulic Functions for Alluvial Soils Using Multistep Outflow Data. Soil Science Society of America Journal, 68(2), 417-429. https://doi.org/10.2136/sssaj2004.4170

Mojid, M. A., Hossain, A. B. M. Z., & Ashraf, M. A. (2019). Artificial neural network model to predict transport parameters of reactive solutes from basic soil properties. Environmental Pollution, 255, 113355. https://doi.org/10.1016/j.envpol.2019.113355

Mojid, M. A., Hossain, A. B. M. Z., Cappuyns, V., & Wyseure, G. C. L. (2016). Transport characteristics of heavy metals, metalloids and pesticides through major agricultural soils of Bangladesh as determined by TDR. Soil Research, 54(8), 970-984. https://doi.org/10.1071/SR15367

Mojid, M. A., Hossain, A. Z., Wyseure, G. C., & Ashraf, M. A. (2019). Pedo-transfer functions with multiple linear regressions to predict solute-transport parameters. Eurasian Journal of Soil Science, 8(3), 196-207.

Mojid, M. A., Rose, D. A., & Wyseure, G. C. L. (2004). A transfer-function method for analysing breakthrough data in the time domain of the transport process. European Journal of Soil Science, 55(4), 699-711. https://doi.org/10.1111/j.1365-2389.2004.00636.x

Morshed, J., & Kaluarachchi, J. J. (1998). Application of artificial neural network and genetic algorithm in flow and transport simulations. Advances in Water Resources, 22(2), 145-158. https://doi.org/10.1016/S0309-1708(98)00002-5

Perfect, E., Sukop, M. C., & Haszler, G. R. (2002). Prediction of Dispersivity for Undisturbed Soil Columns from Water Retention Parameters. Soil Science Society of America Journal, 66(3), 696-701. https://doi.org/10.2136/sssaj2002.6960

Phillips, I. R. (2006). Modelling water and chemical transport in large undisturbed soil cores using HYDRUS-2D. Soil Research, 44(1), 27-34. https://doi.org/10.1071/SR05109

Piegorsch, W. W., & Bailer, A. J. (2005). Quantitative Risk Assessment with Stimulus-Response Data. In Analyzing Environmental Data (pp. 171-214). https://doi.org/10.1002/0470012234.ch4

Sarmah, A. K., Close, M. E., Pang, L., Lee, R., & Green, S. R. (2005). Field study of pesticide leaching in a Himatangi sand (Manawatu) and a Kiripaka bouldery clay loam (Northland). 2. Simulation using LEACHM, HYDRUS-1D, GLEAMS, and SPASMO models. Soil Research, 43(4), 471-489. https://doi.org/10.1071/SR04040

Schaap, M. G., Leij, F. J., & van Genuchten, M. T. (1998). Neural Network Analysis for Hierarchical Prediction of Soil Hydraulic Properties. Soil Science Society of America Journal, 62(4), 847-855. https://doi.org/10.2136/sssaj1998.03615995006200040001x

Sihag, P. (2018). Prediction of unsaturated hydraulic conductivity using fuzzy logic and artificial neural network. Modeling Earth Systems and Environment, 4(1), 189-198. https://doi.org/10.1007/s40808-018-0434-0

Sihag, P., Tiwari, N. K., & Ranjan, S. (2019). Prediction of unsaturated hydraulic conductivity using adaptive neuro- fuzzy inference system (ANFIS). ISH Journal of Hydraulic Engineering, 25(2), 132-142. https://doi.org/10.1080/09715010.2017.1381861

Stangierski, J., Weiss, D., & Kaczmarek, A. (2019). Multiple regression models and Artificial Neural Network (ANN) as prediction tools of changes in overall quality during the storage of spreadable processed Gouda cheese. European Food Research and Technology, 245(11), 2539-2547. https://doi.org/10.1007/s00217-019-03369-y

Taşan, S., & Demir, Y. (2020). Comparative Analysis of MLR, ANN, and ANFIS Models for Prediction of Field Capacity and Permanent Wilting Point for Bafra Plain Soils. Communications in Soil Science and Plant Analysis, 51(5), 604-621. https://doi.org/10.1080/00103624.2020.1729374

Van Looy, K., Bouma, J., Herbst, M., Koestel, J., Minasny, B., Mishra, U., Montzka, C., Nemes, A., Pachepsky, Y. A., Padarian, J., Schaap, M. G., Tóth, B., Verhoef, A., Vanderborght, J., van der Ploeg, M. J., Weihermüller, L., Zacharias, S., Zhang, Y., & Vereecken, H. (2017). Pedotransfer Functions in Earth System Science: Challenges and Perspectives. Reviews of Geophysics, 55(4), 1199-1256. https://doi.org/10.1002/2017RG000581

Williams, C. G., & Ojuri, O. O. (2021). Predictive modelling of soils’ hydraulic conductivity using artificial neural network and multiple linear regression. SN Applied Sciences, 3(2), 152. https://doi.org/10.1007/s42452-020-03974-7

Xu, X., Li, H., Sun, C., Ramos, T. B., 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*. Irrigation and Drainage, n/a(n/a). https://doi.org/10.1002/ird.2584

Zare Abyaneh, H. (2014). Evaluation of multivariate linear regression and artificial neural networks in prediction of water quality parameters. Journal of Environmental Health Science and Engineering, 12(1), 40. https://doi.org/10.1186/2052-336X-12-40

Zhang, R., Qian, X., Yuan, X., Ye, R., Xia, B., & Wang, Y. (2012). Simulation of Water Environmental Capacity and Pollution Load Reduction Using QUAL2K for Water Environmental Management. International Journal of Environmental Research and Public Health, 9(12), 4504-4521. https://www.mdpi.com/1660-4601/9/12/4504

DOI: https://doi.org/10.20961/stjssa.v18i1.49207

Refbacks

  • There are currently no refbacks.