Prediction of soil macronutrients using fractal parameters and artificial intelligence methods

  • Ali A. Zolfaghari Semnan University, Faculty of Desert Studies, Semnan
  • Meysam Abolkheiryan Semnan University, Faculty of Desert Studies, Semnan
  • Ali A. Soltani-Toularoud University of Mohaghegh Ardabili, Dept. of Soil Science and Engineering, Ardabil
  • Ruhollah Taghizadeh-Mehrjardi Ardakan University, Faculty of Agriculture and Natural Resources, Ardakan, Iran University of Tübingen, Dept. of Geosciences, Soil Science and Geomorphology, Tübingen, Germany
  • Amanuel O. Weldeyohannes University of Alberta, Dept. of Renewable Resource, Alberta
Keywords: artificial neural networks, Gamma test, k-Nearest Neighbor, support vector regression

Abstract

Aim of study: To evaluate artificial neural networks (ANN), and k-Nearest Neighbor (k-NN) to support vector regression (SVR) models for estimation of available soil nitrogen (N), phosphorous (P) and available potassium (K).

Area of study: Two separate agricultural sites in Semnan and Gorgan, in Semnan and Golestan provinces of Iran, respectively.

Material and methods: Complete data set of soil properties was used to evaluate the models’ performance using a k-fold test data set scanning procedures. Soil property measures including clay, sand and silt content, soil organic carbon (SOC), electrical conductivity (EC), lime content as well as fractal dimension (D) were used for the prediction of soil macronutrients. A Gamma test was utilized for defining the optimum combination of the input variables.

Main results: The sensitivity analysis showed that OC, EC, and clay were the most significant variables in the prediction of soil macronutrients. The SVR model was more accurate compared to the ANN and k-NN models. N values were estimated more accurately than K and P nutrients, in all the applied models.

Research highlights: The accuracy of models among the test stages illustrated that using a single data set for investigation of model performance could be misleading. Therefore, the complete data set would be necessary for suitable evaluation of the model.

Downloads

Download data is not yet available.

References

Adviento-Borbe M, Doran J, Drijber R, Dobermann A, 2006. Soil electrical conductivity and water content affect nitrous oxide and carbon dioxide emissions in intensively managed soils. J Environ Qual 35: 1999-2010. https://doi.org/10.2134/jeq2006.0109

Aimrun W, Amin M S, Rusnam M, Ahmad D, Hanafi M, Anuar A, 2009. Bulk soil electrical conductivity as an estimator of nutrients in the maize cultivated land. Eur J Sci Res 31: 37-51.

Amini M, Abbaspour K C, Khademi H, Fathianpour N, Afyuni M, Schulin R, 2005. Neural network models to predict cation exchange capacity in arid regions of Iran. Eur J Soil Sci 56: 551-559. https://doi.org/10.1111/j.1365-2389.2005.0698.x

Ayoubi S, Sahrawat KL, 2011. Comparing multivariate regression and artificial neural network to predict barley production from soil characteristics in northern Iran. Arch Agron Soil Sci 57: 549-565. https://doi.org/10.1080/03650341003631400

Ballabio C, 2009. Spatial prediction of soil properties in temperate mountain regions using support vector regression. Geoderma 151: 338-350. https://doi.org/10.1016/j.geoderma.2009.04.022

Bayat H, Davatgar N, Jalali M, 2014. Prediction of CEC using fractal parameters by artificial neural networks. Int Agrophys 28: 143-152. https://doi.org/10.2478/intag-2014-0002

Babaei F, Zolfaghari A A, Yazdani M R, Sadeghipour A, 2018. Spatial analysis of infiltration in agricultural lands in arid areas of Iran. Catena 170: 25-35. https://doi.org/10.1016/j.catena.2018.05.039

Bird N, Perrier E, Rieu M, 2000. The water retention function for model of soil structure with pore and solid fractal distribution. Eur J Soil Sci 51: 55-56. https://doi.org/10.1046/j.1365-2389.2000.00278.x

Botula Y, Nemes A, Mafuka P, Ranst E, Cornelis W, 2013. Prediction of water retention of soils from the humid tropics by the nonparametric k-nearest neighbor approach. Vadose Zone J 12: 1-17. https://doi.org/10.2136/vzj2012.0123

Bronson KF, Booker J, Keeling JW, Boman RK, Wheeler TA, Lascano RJ, Nichols RL, 2005. Cotton canopy reflectance at landscape scale as affected by nitrogen fertilization. Agron J 97: 654-660. https://doi.org/10.2134/agronj2004.0093

Chaudhari P, Ahire D, Ahire VD, 2012. Correlation between physico-chemical properties and available nutrients in sandy loam soils of haridwar. J Chem Biol Phys Sci 2: 1493.

Cherkassky V, Mulier FM, 2007. Learning from data: concepts, theory, and methods. John Wiley & Sons, NJ, USA. https://doi.org/10.1002/9780470140529

Foth H, 1982. Soil resources and food: A global view. In: Principles and applications of soil geography; Bridges EM & Davidson DA (eds), pp: 48-61. Longman, NY.

Fu W, Tunney H, Zhang C, 2010. Spatial variation of soil nutrients in a dairy farm and its implications for site-specific fertilizer application. Soil Till Res 106: 185-193. https://doi.org/10.1016/j.still.2009.12.001

Gee G, Bauder J, 1986. Particle size analysis. In: Methods of soil analysis, part 1; Klute A (ed), pp: 383-411. Agron. Monogr. No. 9. Am Soc Agron, Madison, WI, USA. https://doi.org/10.2136/sssabookser5.1.2ed.c15

Haykin S, 1994. Neural networks: a comprehensive foundation. Prentice Hall PTR.

Jackson ML, 2005. Soil chemical analysis: Advanced course. UW-Madison Libraries Parallel Press.

Jeong G, Oeverdieck H, Park SJ, Huwe B, Ließ M, 2017. Spatial soil nutrients prediction using three supervised learning methods for assessment of land potentials in complex terrain. Catena 154: 73-84. https://doi.org/10.1016/j.catena.2017.02.006

Keshavarzi A, Sarmadian F, Omran ESE, Iqbal M, 2015. A neural network model for estimating soil phosphorus using terrain analysis. Egypt J Remote Sens Space Sci 18: 127-135. https://doi.org/10.1016/j.ejrs.2015.06.004

Kovačević M, Bajat B, Gajić B, 2010. Soil type classification and estimation of soil properties using support vector machines. Geoderma 154: 340-347. https://doi.org/10.1016/j.geoderma.2009.11.005

Kuhn M, Johnson K, 2013. Applied predictive modeling. Springer. https://doi.org/10.1007/978-1-4614-6849-3

Li QQ, Yue TX, Wang CQ, Zhang WJ, Yu Y, Li B, Yang J, Bai GC, 2013. Spatially distributed modeling of soil organic matter across china: An application of artificial neural network approach. Catena 104: 210-218. https://doi.org/10.1016/j.catena.2012.11.012

Li QQ, Zhang X, Wang CQ, Li B, Gao XS, Yuan DG, Luo YL, 2016. Spatial prediction of soil nutrient in a hilly area using artificial neural network model combined with kriging. Arch Agron Soil Sci 62: 1541-1553. https://doi.org/10.1080/03650340.2016.1154543

Marti E, Jofre J, Balcazar JL, 2013. Prevalence of antibiotic resistance genes and bacterial community composition in a river influenced by a wastewater treatment plant. PLoS One 8 (10): e78906. https://doi.org/10.1371/journal.pone.0078906

Mathworks, 2010. Matlab Version 7.0. The Mathworks Inc., Natick, MA, USA.

Moghaddamnia A, Gousheh MG, Piri J, Amin S, Han D, 2009. Evaporation estimation using artificial neural networks and adaptive neuro-fuzzy inference system techniques. Adv Water Resour 32: 88-97. https://doi.org/10.1016/j.advwatres.2008.10.005

Moosavi AA, Sepaskhah A, 2012. Artificial neural networks for predicting unsaturated soil hydraulic characteristics at different applied tensions. Arch Agron Soil Sci 58: 125-153. https://doi.org/10.1080/03650340.2010.512289

Nemes A, Rawls WJ, Pachepsky YA, 2006. Use of the nonparametric nearest neighbor approach to estimate soil hydraulic properties. Soil Sci Soc Am J 70: 327-336. https://doi.org/10.2136/sssaj2005.0128

Olsen SR, Khasawneh FE, 1980. Use and limitations of physical-chemical criteria for assessing the status of phosphorus in soils. In: The role of phosphorus in agriculture; Khasawneh FE, Sample EC & Kamprath EC (eds), pp: 361-410. ASA, CSSA, and SSSA Books. https://doi.org/10.2134/1980.roleofphosphorus.c15

Peralta NR, Costa JL, 2013. Delineation of management zones with soil apparent electrical conductivity to improve nutrient management. Comput Electron Agric 99: 218-226. https://doi.org/10.1016/j.compag.2013.09.014

Raheb A, Heidari A, 2012. Effects of clay mineralogy and physico-chemical properties on potassium availability under soil aquic conditions. J Soil Sci Plant Nutr 12: 747-761. https://doi.org/10.4067/S0718-95162012005000029

Safaa M, Maxwellb TMR, 2015. Predicting pasture nitrogen content using ANN models and thermal images. 21st Int Congr on Modelling and Simulation, Gold Coast, Australia.

Shiri J, Nazemi AH, Sadraddini AA, Landeras G, Kisi O, Fard AF, Marti P, 2014. Comparison of heuristic and empirical approaches for estimating reference evapotranspiration from limited inputs in Iran. Comput Electron Agric 108: 230-241. https://doi.org/10.1016/j.compag.2014.08.007

Shiri J, Keshavarzi A, Kisi O, Iturraran-Viveros U, Bagherzadeh A, Mousavi R, Karimi S, 2017. Modeling soil cation exchange capacity using soil parameters: Assessing the heuristic models. Comput Electron Agric 135: 242-251. https://doi.org/10.1016/j.compag.2017.02.016

Simon HA, 1995. Artificial intelligence: An empirical science. Artif Intell 77: 95-127. https://doi.org/10.1016/0004-3702(95)00039-H

Skaggs T, Arya L, Shouse P, Mohanty B, 2001. Estimating particle-size distribution from limited soil texture data. Soil Sci Soc Am J 65: 1038-1044. https://doi.org/10.2136/sssaj2001.6541038x

Smola AJ, Schölkopf B, 2004. A tutorial on support vector regression. Stat Comp 14 (3): 199-222. https://doi.org/10.1023/B:STCO.0000035301.49549.88

Taghizadeh‐Mehrjardi R, Toomanian N, Khavaninzadeh A, Jafari A, Triantafilis J, 2016. Predicting and mapping of soil particle‐size fractions with adaptive neuro‐fuzzy inference and ant colony optimization in central Iran. Eur J Soil Sci 67: 707-725. https://doi.org/10.1111/ejss.12382

Vapnik V, 1995. The nature of statistical learning theory. Springer, NY. https://doi.org/10.1007/978-1-4757-2440-0

Walkley A, Black IA, 1934. An examination of the degtjareff method for determining soil organic matter, and a proposed modification of the chromic acid titration method. Soil Sci 37: 29-38. https://doi.org/10.1097/00010694-193401000-00003

Wang H, Shi X, Yu D, Weindorf DC, Huang B, Sun W, Ritsema CJ, Milne E, 2009. Factors determining soil nutrient distribution in a small-scaled watershed in the purple soil region of Sichuan province, China. Soil Till Res 105: 300-306. https://doi.org/10.1016/j.still.2008.08.010

Were K, Bui DT, Dick ØB, Singh BR, 2015. A comparative assessment of support vector regression, artificial neural networks, and random forests for predicting and mapping soil organic carbon stocks across an afromontane landscape. Ecol Indic 52: 394-403. https://doi.org/10.1016/j.ecolind.2014.12.028

Yazdani MR, Zolfaghari AA, 2017. Monthly river forecasting using instance-based learning methods and climatic parameters. J Hydrol Eng 22 (6): 04017002. https://doi.org/10.1061/(ASCE)HE.1943-5584.0001490

Zolfaghari A, Taghizadeh-Mehrjardi R, Moshki A, Malone B, Weldeyohannes A, Sarmadian F, Yazdani M, 2016. Using the nonparametric k-nearest neighbor approach for predicting cation exchange capacity. Geoderma 265: 111-119. https://doi.org/10.1016/j.geoderma.2015.11.012

Published
2020-09-22
How to Cite
ZolfaghariA. A., AbolkheiryanM., Soltani-ToularoudA. A., Taghizadeh-MehrjardiR., & WeldeyohannesA. O. (2020). Prediction of soil macronutrients using fractal parameters and artificial intelligence methods. Spanish Journal of Agricultural Research, 18(2), e1104. https://doi.org/10.5424/sjar/2020182-15460
Section
Soil science