Artificial neural networks in the prediction of soil chemical attributes using apparent electrical conductivity

  • Samuel A. Silva Federal University of Espírito Santo, Dept. Rural Engineering, Alegre, Espírito Santo
  • Julião S. S. Lima Federal University of Espírito Santo, Dept. Rural Engineering, Alegre, Espírito Santo
  • Daniel M. Queiroz Federal University of Viçosa, Dept. Agricultural Engineering, Viçosa, Minas Gerais,
  • Arlicélio Q. Paiva State University of Santa Cruz, Post Graduation in Plant Production, Ilhéus, Bahia
  • Caique C. Medauar Federal University of Espírito Santo, Dept. Rural Engineering, Alegre, Espírito Santo
  • Railton O. Santos State University of Santa Cruz, Post Graduation in Plant Production, Ilhéus, Bahia
Keywords: precision agriculture, computational intelligence, remote sensing, predictive models, digital soil mapping

Abstract

Aim of study: To use artificial neural networks (ANN) to predict the values and spatial distribution of soil chemical attributes from apparent soil electrical conductivity (ECa) and soil clay contents.

Area of study: The study was carried out in an area of 1.2-ha cultivated with cocoa, located in the state of Bahia, Brazil.

Material and methods: Data collections were performed on a sampling grid containing 120 points. Soil samples were collected to determine the attributes: clay, silt, sand, P, K+, Ca2+, Mg2+, S, pH, H+Al, SB, CTC, V, OM and P-rem. ECa was measured using the electrical resistivity method in three different periods related to soil sampling: 60 days before (60ECa), 30 days before (30ECa) and when collecting soil samples (0ECa). For the prediction of chemical and physical-chemical attributes of the soil, models based on ANN were used. As input variables, the ECa and the clay contents were used. The quality of ANN predictions was determined using different statistical indicators. Thematic maps were constructed for the attributes determined in the laboratory and those predicted by the ANNs and the values were grouped using the fuzzy k-means algorithm. The agreement between classes was performed using the kappa coefficient.

Main results: Only P and K+ attributes correlated with all ANN input variables. ECa and clay contents in the soil proved to be good variables for predicting soil attributes.

Research highlights: The best results in the prediction process of the P and K+ attributes were obtained with the combination of ECa and the clay content.

Downloads

Download data is not yet available.

References

Aitkenhead MJ, Coull MC, 2016. Mapping soil carbon stocks across Scotland using a neural network model. Geoderma 262: 187-198. https://doi.org/10.1016/j.geoderma.2015.08.034

Blackmore S, Godwin RJ, Fountas S, 2003. The analysis of spatial and temporal trends in yield map data over six years. Biosyst Eng 84 (4): 455-466. https://doi.org/10.1016/S1537-5110(03)00038-2

Bottega EL, Queiroz DM, Pinto FAC, Souza CMA, Valente DSM, 2017. Precision agriculture applied to soybean: Part I - Delineation of management zones. Aust J Crop Sci 11 (5): 573-579. https://doi.org/10.21475/ajcs.17.11.05.p381

Braga AP, Carvalho APLF, Ludermir TB, 2011. Redes neurais artificiais: Teoria e aplicações, 2nd ed, Ed. LTC, Rio de Janeiro, 226p.

Brevik E, Fenton T, Lazari A, 2006. Soil electrical conductivity as a function of soil water content and implications for soil mapping. Precis Agr 7 (6): 393-404. https://doi.org/10.1007/s11119-006-9021-x

Carvalho Filho R, Melo AAO, Santana SO, Leão AC, 1987. Solos do município de Ilhéus. Boletim Técnico nº 147, 90 pp.

Chepote RE, Sodré GA, Reis EL, Pacheco RG, Marrocos PCL, Valle RR, 2013. Recomendações de corretivos e fertilizantes na cultura do cacaueiro no sul da Bahia. CEPLAC/CEPEC. Ilhéus, BA. Boletim Técnico n° 203, 44 pp.

Corwin DL, Hendrickx JMH, 2002. Electrical resistivity: wenner array. In: Methods of soil analysis, Part 4, Physical methods n. 5; Silva JS, (ed.). pp: 1282-1287. SSSA Book Series, Madison, Wi, USA.

Corwin D, Lesch S, 2003. Application of soil electrical conductivity to precision agriculture. Agron J 95 (3): 455-471. https://doi.org/10.2134/agronj2003.4550

Daniel KW, Tripathi NK, Honda K, 2003. Artificial neural network analysis of laboratory and in situ spectra for the estimation of macronutrients in soils of Lop Buri (Thailand). Aust J Soil Res 41 (1): 47-59. https://doi.org/10.1071/SR02027

EMBRAPA, 2017. Manual de métodos de análise de solos, 3ª ed. Empresa Brasileira de Pesquisa Agropecuária - Solos. Rio de Janeiro, Brasil. 574 pp.

EMBRAPA, 2018. Sistema brasileiro de classificação de solos, 5 ª ed. Empresa Brasileira de Pesquisa Agropecuária - Centro Nacional de Pesquisas de Solos. Brasília, Brasil. 356 pp.

Ernani PR, Almeida JA, Santos FC, 2007. Potássio. In: Fertilidade do solo; Novais RF et al. (eds.). pp: 551-594. Viçosa, Brasil.

Fortes R, Millan S, Prieto MH, Campillo CA, 2015. A methodology based on apparent electrical conductivity and guided soil samples to improve irrigation zoning. Precis Agr 16 (4): 441-454. https://doi.org/10.1007/s11119-015-9388-7

Grego CR, Coelho RM, Vieira SR, 2011. Critérios morfológicos e taxonômicos de latossolo e nitossolo validados por propriedades físicas mensuráveis analisadas em parte pela geoestatística. Rev Bras Ciênc do Solo 35 (2): 337-350. https://doi.org/10.1590/S0100-06832011000200005

Grubbs RA, Straw CM, Bowling WJ, Radcliffe DE, Taylor Z, Henry GM, 2019. Predicting spatial structure of soil physical and chemical properties of golf course fairways using an apparent electrical conductivity sensor. Precis Agr 20 (3): 496-519. https://doi.org/10.1007/s11119-018-9593-2

Guastaferro F, Castrignanã A, Benedetto D, Sollitto D, Troccoli A, Cafarelli B, 2010. A comparison of different algorithms for the delineation of management zones. Precis Agr 11 (6): 600-620. https://doi.org/10.1007/s11119-010-9183-4

Guo PT, Wu W, Sheng QK, Li MF, Lui HB, Wang ZY, 2013. Prediction of soil organic matter using artificial neural network and topographic indicators in hilly áreas. Nutr Cyc Agro 95 (3): 333-344. https://doi.org/10.1007/s10705-013-9566-9

Haykin S, 1999. Neural networks: A comprehensive foundation. MacMillan Coll Publ Co, NY.

Jafarzadeh AA, Pal M, Servati M, Fazelifard MH, Ghorbani MA, 2016. Comparative analysis of support vector machine and artificial neural network models for soil cation exchange capacity prediction. Int J Environ Sci Techn 13 (1): 87-96. https://doi.org/10.1007/s13762-015-0856-4

Kitchen NR, Sudduth KA, Myers DB, Drummond ST, Hong SY, 2005. Delineating productivity zones on claypan soil filds using apparent soil electrical conductivity. Comp Elec Agr 46 (1-3): 285-308. https://doi.org/10.1016/j.compag.2004.11.012

Kolassa J, Reichle RH, Liu Q, Alemohammad SH, Gentine P, Aida K, 2018. Estimating surface soil moisture from SMAP observations using a neural network technique. Rem Sens Environ 204: 43-59. https://doi.org/10.1016/j.rse.2017.10.045

Köppen W, Geiger R, 1928. Die Klimate der Rrde. Gotha, Verlag Justus Perthes. Wall-map 150cm x 200 cm.

Leal AJF, Miguel EP, Baio FHR, Neves DC, Leal UAS, 2015. Redes neurais artificiais na predição da produtividade de milho e definição de sítios de manejo diferenciado por meio de atributos do solo. Brag 74 (4): 436-444. https://doi.org/10.1590/1678-4499.0140

Lück E, Gebbers R, Ruehlmann J, Spangenberg U, 2009. Electrical conductivity mapping for precision farming. Near Surf Geoph 7 (1): 15-25. https://doi.org/10.3997/1873-0604.2008031

Medauar CC, Silva SA, Carvalho LCC, Tiburcio RAS, Medauar PAS, 2020. Using unmanned aerial vehicle for identifying the vegetative vigor and quantify the area occupied by eucalyptus sprouts after chemical weeding in the state of Bahia, Brazil. Emir J Food Agr 32 (3): 165-171. https://doi.org/10.9755/ejfa.2020.v32.i3.2083

Medeiros WN, Valent, DSM, Queiroz DM, Pinto FAC, Assis IR, 2018. Apparent soil electrical conductivity in two different soil types. Rev Ciên Agr 49 (1): 43-52. https://doi.org/10.5935/1806-6690.20180005

Moral F, Terrón J, Silva JM, 2010. Delineation of management zones using mobile measurements of soil apparent electrical conductivity and multivariate geostatistical techniques. Soil Till Res 106 (2): 335-343. https://doi.org/10.1016/j.still.2009.12.002

Moral JN, Serrano JM, 2019. Using low‑cost geophysical survey to map soil properties and delineate management zones on grazed permanente pastures. Precis Agr 20 (5): 1000-1014. https://doi.org/10.1007/s11119-018-09631-9

Ng W, Minasny B, Montazerolghaem M, Padarian J, Ferguson R, Bailey S, 2019. Convolutional neural network for simultaneous prediction of several soil properties using visible/near-infrared, mid-infrared, and their combined spectra. Geoderma 352: 251-267. https://doi.org/10.1016/j.geoderma.2019.06.016

Sanches GM, Magalhães PSG, Remacre AZ, Franco HCJ, 2018. Potential of apparent soil electrical conductivity to describe the soil pH and improve lime application in a clayey soil. Soil Till Res 175: 217-225. https://doi.org/10.1016/j.still.2017.09.010

Sanches GM, Paula MTN, Magalhães PSG, Duft DG, Vitti AC, Kolln OT, 2019. Precision production environments for sugarcane felds. Scien Agr 76 (1): 10-17. https://doi.org/10.1590/1678-992x-2017-0128

Santos RO, Franco LB, Silva SA, Sodre GA, Menezes AA, 2017. Spatial variability of soil fertility and its relation with cocoa yield. Rev Bras Eng Agríc Amb 21 (2): 88-93. https://doi.org/10.1590/1807-1929/agriambi.v21n2p88-93

Serrano JM, Shahifian S, Silva JM, 2017. Spatial variability and temporal stability of apparent soil electrical conductivity in a Mediterranean pasture. Precis Agr 18 (2): 245-263. https://doi.org/10.1007/s11119-016-9460-y

Silva SA, Lima JSS, 2012. Multivariate analysis and geostatistics of the fertility of a humic rhodic hapludox under coffee cultivation. Ciênc do Solo 36 (2): 467-474. https://doi.org/10.1590/S0100-06832012000200016

Silva SA, Lima JSS, 2014. Spatial estimation of foliar phosphorus in different species of the genus Coffea based on soil properties. Ciênc do Solo 38 (5): 1439-1447. https://doi.org/10.1590/S0100-06832014000500009

Silva IN, Spatti DH, Flauzino RA, 2010. Redes neurais artificiais para engenharia e ciências aplicadas, 1ª ed. Artliber, São Paulo. 399 pp.

Silva SA, Lima JSS, Souza GS, Oliveira RB, Silva AF, 2010a. Variabilidade espacial do fósforo e das frações granulométricas de um Latossolo Vermelho Amarelo. Ciênc Agron 41 (1): 1-8. https://doi.org/10.12702/I-SGEA-a01

Silva SA, Lima JSS, Souza GS, 2010b. Estudo da fertilidade de um Latossolo Vermelho-Amarelo húmico sob cultivo de café arábica por meio de geoestatística. Ceres 57 (4): 560-567. https://doi.org/10.1590/S0034-737X2010000400020

Singh G, Williard KWJ, Schoonover JE, 2016. Spatial relation of apparent soil electrical conductivity with crop yields and soil properties at different topographic positions in a small agricultural watershed. Agron 6 (4): 57. https://doi.org/10.3390/agronomy6040057

Stadler A, Rudolph S, Kupisch M, Langensiepen M, Van der kruk J, Ewert F, 2015. Quantifying the efects of soil variability on crop growth using apparent soil electrical conductivity measurements. Eur J Agron 64: 8-20. https://doi.org/10.1016/j.eja.2014.12.004

Terrón JM, Marques JRS, Moral FJ, Garcíaferrer A, 2011. Soil apparent electrical conductivity and geographically weighted regression for mapping soil. Precis Agr 12 (5): 750-761. https://doi.org/10.1007/s11119-011-9218-5

Uribeetxebarria A, Arnó J, Escolà A, Casasnovas JAM, 2018. Apparent electrical conductivity and multivariate analysis of soil properties to assess soil constraints in orchards affected by previous parcelling. Geoderma 319: 185-193. https://doi.org/10.1016/j.geoderma.2018.01.008

Valckx J, Cockx L, Wauters J, Van M, Gevers G, Hermy M, Muys B, 2009. Within-feld spatial distribution of earthworm populations related to species interactions and soil apparent electrical conductivity. Appl Soil Ecol 41 (3): 315-328. https://doi.org/10.1016/j.apsoil.2008.12.005

Valente DSM, Queiroz DM, Pinto FAC, Santos FL, Santos NT, 2014. Spatial variability of apparent electrical conductivity and soil properties in a coffee production field. Eng Agríc 34 (6): 1224-1233. https://doi.org/10.1590/S0100-69162014000600017

Willmott CJ, Ckleson SG, Davis RE, 1985. Statistics for evaluation and comparisons of models. J Geoph Res 90 (5): 8995-9005. https://doi.org/10.1029/JC090iC05p08995

Published
2021-08-12
How to Cite
SilvaS. A., LimaJ. S. S., QueirozD. M., PaivaA. Q., MedauarC. C., & SantosR. O. (2021). Artificial neural networks in the prediction of soil chemical attributes using apparent electrical conductivity. Spanish Journal of Agricultural Research, 19(3), e0208. https://doi.org/10.5424/sjar/2021193-17600
Section
Agricultural engineering