DOI:https://doi.org/10.3232/SJSS.2017.V7.N3.03

Application of artificial neural networks to estimate soil organic carbon in a high-organic-matter Mollisol

Rocío Moreno, Andrea Inés Irigoyen, María Gloria Monterubbianesi, Guillermo Alberto Studdert

Abstract

Soil organic carbon (SOC) has a key role in the global carbon (C) cycle. The complex relationships among the components of C cycle makes difficult the modelling of SOC variation. Artificial neural networks (ANN) are models capable to determine interrelationships based on information. The objective was to develop and evaluate models based on the ANN technique to estimate the SOC in Mollisols of the Southeastern of Buenos Aires Province, Argentina (SEBA). Data from three long term experiments was used. Management and meteorological variables were selected as input. Management information included numerical variables (initial SOC (SOCI); number of years from the beginning of the experiment (Year), proportion of soybean in the crop sequence; (Prop soybean); crop yields (Yield), proportion of cropping in the crop rotation (Prop agri), and categorical variables (Crop, Tillage). In addition, two meteorological inputs (minimum (Tmin) and mean air temperature (Tmed)), were selected. The ANNs were adequate to estimate SOC in the upper 0.20 m of Mollisols of the SEBA. The model with the best performance included six management variables (SOCI, Year, Prop soybean, Tillage, Yield, Prop agri) and one meteorological variable (Tmin), all of them easily available and with low level of uncertainty. Soil organic C changes related to soil use in the SEBA could be satisfactorily estimated using an ANN developed with simple and easily available input variables. Artificial neural network technique appears as a valuable tool to develop robust models to help predicting SOC changes.
Views: 267
Downloads PDF: 224

 

References


Agnusdei MG, Colabelli MR, Fernández Grecco RC. 2001. Crecimiento estacional de forraje de pasturas y pastizales naturales del Sudeste Bonaerense. Boletín Técnico N° 152. Estación Experimental INTA Balcarce, Argentina.

Álvarez R. 2008. Comparación de técnicas de regresión, arboles de regresión y redes neuronales para estimar el contenido de carbono orgánico de los suelos. In: Proceedings 21° “Congreso Argentino de la Ciencia del Suelo”. Potrero de los Funes, San Luis. May 2008. In CD.

Álvarez R, Steinbach HS, Bono A, Berhongaray G. 2009. Balance de carbono y nivel de materia orgánica en suelos agrícolas de la Región Pampeana. In: Proceedings “Efectos de la Agricultura, la lechería y la ganadería en el recurso natural suelo: impactos y propuestas”. Montevideo, Uruguay, August 2009. In CD.

Álvarez R, Steinbach HS, Bono A. 2011.An artificial neural network approach for predicting soil carbon budget in agroecosystems. Soil Sci. Soc. Am. J. 75:965-975.

Álvarez R, Berhongaray G, De Paepe J, Mendoza MR, Steinbach HS, Caride C, Cantet R. 2012. Productividad, fertilidad y secuestro de carbono en suelos pampeanos: efecto del uso agrícola. Anales Acad. Nac. Agron. Vet. LXVI:381-426.

Bélanger G, Gastal F, Warembourg FR. 1992. The effects of nitrogen fertilization and the growing season on carbon partitioning in a sward of tall fescue (Festuca arundinacea Schreb.). Ann Bot. 70:239-244.

Berhongaray G, Álvarez R, De Paepe J, Caride C, Cantet R. 2013. Land use effects on soil carbon in the Argentine Pampas. Geoderma 192:97-110.

Braga AP, Carvalho APL, Ludermir TB. 2007. Introdução. In: Braga, AP.; Carvalho, A.P.I.; Ludemir, T.B. (eds.). Redes Neurais Artificiais: Teoria e Aplicações. LCT editora. Rio de Janeiro, Brasil. pp. 67-85

De Paepe JL, Álvarez R. 2013. Desarrollo de un índice de productividad de suelo regional a través de una red neuronal artificial. Informaciones Agronómicas de Hispanoamérica 12:23-26.

Diovisalvi NV, Studdert GA, Domínguez GF, Eiza MJ. 2008. Fracciones de carbono y nitrógeno orgánicos y nitrógeno anaeróbico bajo agricultura continua con dos sistemas de labranza. Ciencia del Suelo 26:1-11.

Eiza MJ, Fioriti N, Studdert GA, Echeverría HE. 2005. Fracciones de carbono orgánico en la capa arable: efecto de los sistemas de cultivo y de la fertilización nitrogenada. Ciencia del Suelo 23:59-68.

Fox DG. 1981. Judging air quality model performance: a summary of the AMS workshop on dispersion model performance. Bull Am Meteorol Soc. 62:599-609.

Franko U, Oeschligel B, Schenk S. 1995. Simulation of temperature, water, and nitrogen dynamics using the model CANDY. Ecol Model. 81:213-222.

Hansen S, Jensen HE, Nielsen NE, Svendsen H. 1991. Simulation of nitrogen dynamics and biomass production in winter wheat using the Danish simulation model DAISY. Fert Res 27:245-259.

Haykin S. 2001. Redes Neurais: princípios e prática. Bookman, Porto Alegre, Brasil. 900 p.

Ingleby HR, Crowe TG. 2001. Neural network models for predicting organic matter content in Saskatchewan soils. Can Biosyst Eng. 43:1-5.

INTA. 1979. Carta de Suelos de la República Argentina. Buenos Aires (Argentina): Instituto Nacional de Tecnología Agropecuaria, Secretaría de Agricultura, Ganadería y Pesca

Levine ER, Kimes DS. 1998. Predicting soil carbon in mollisols using neural networks. In: Lal, R.; Kimble, J.M.; Follett, R.F; Stewart, B.A. (eds.). Soil Processes and the Carbon Cycle. CRC Press LLC, Florida, EEUU. pp. 473-484.

Maier HR, Dandy GC. 2000. Neural network for the prediction and forecasting of water resources variables: a review of modelling issues and applications. Environ Model Softw. 15:101-124.

Moreno R., Irigoyen AI., Studdert GA. 2014a. Aplicación de redes neuronales artificiales para estimar el carbono orgánico del suelo. In: Proceedings 24° Congreso Argentino de la Ciencia del Suelo y 2° Reunión Nacional “Materia Orgánica y Sustancias Húmicas”; 2014 May 5-9; Bahía Blanca, Buenos Aires, Argentina, In CD.

Moreno R., Irigoyen AI., Studdert GA. 2014b. Carbono orgánico del suelo: Extracción de conocimiento desde redes neuronales artificiales. In: Proceedings 24° Congreso Argentino de la Ciencia del Suelo y 2° Reunión Nacional “Materia Orgánica y Sustancias Húmicas”; 2014 May 5-9; Bahía Blanca, Buenos Aires, Argentina, In CD.

Moreno R, Studdert, GA, Monterubbianesi MG, Irigoyen AI. 2016. Soil organic carbon changes simulated with the AMG model in a high-organic-matter Mollisol. Spanish J Soil Sci 6: 212-229.

Parton W, Shimel D, Cole C, Ojima D. 1987. Analysis of factors controlling soil organic matter levels in Great Plains grasslands. Soil Sci Soc Am J. 51:1173-1179.

Quiroga RA, Studdert GA. 2015. Manejo del suelo e intensificación agrícola: agua y materia orgánica, dos aspectos clave. In: Echeverría HE, García FO, editors. Fertilidad de suelos y fertilización de cultivos. 2nd ed. Buenos Aires (Argentina): Ediciones INTA. p. 73-100.

R Core Team. 2015. R: A Language and Environment for Statistical Computing. Vienna (Austria): R Foundation for Statistical Computing.

Reussi Calvo NI, Studdert GA, Calandroni MB, Diovisalvi NV, Cabria FN, Berardo A. 2014. Nitrógeno incubado en anaerobiosis y carbono orgánico en suelos agrícolas de Buenos Aires. Ciencia del Suelo 32:189-196.

Rogers L, Dowla FU. 1994. Optimization of groundwater remediation using artificial neural networks with parallel solute transport modeling. Water Resour Res. 30:457-481.

Sainz Rozas H, Echeverría H, Angelini H. 2011. Niveles de materia orgánica y pH en suelos agrícolas de la Región Pampeana y Extrapampeana Argentina. Informaciones Agronómicas de Hispanoamérica 2:6-12.

Sánchez SR, Studdert GA, Echeverría HE. 1996. Descomposición de residuos de cosecha en un Argiudol típico. Ciencia del Suelo 14: 63-68.

Schlichting E, Blume HP, Stahr K. 1995. Bodenkundliches Praktikum. Paul Parey. Hamburg, Berlin. 209 p.

Smith P, Smith J, Powlson D, McGill W, Arah J, Chertov O, Coleman K, Franko U, Frolking S, Jenkinson D. 1997. A comparison of the performance of nine soil organic matter models using datasets from seven long-term experiments. Geoderma 81:153-225.

Soil Survey Staff. 2014. Keys to soil taxonomy. Washington (USA): USDA-Natural Resources Conservation Service.

Somaratne G, Seneviratne G, Coomaraswamy U. 2005. Prediction of soil organic carbon across different land-use patterns: a neural network approach. Soil Sci Soc Am J. 69:1580-1589.

Statsoft 2009. Statistica Neural Module [CD-ROM] version 9.0. Statsoft. Inc. Tulsa, EEUU. Computational software.

Studdert GA, Echeverría H. 2000. Crop rotations and nitrogen fertilization to manage soil organic carbon dynamics. Soil Sci Soc Am J. 64:1496-1503.

Studdert GA, Echeverría H, Casanovas EM. 1997. Crop pasture rotation for sustaining the quality and productivity of a Typic Argiudoll. Soil Sci Soc Am J. 61:1466-1472.

Studdert GA, Monterubbianesi MG, Domínguez GF. 2011. Use of RothC to simulate changes of organic carbon stock in the arable layer of a Mollisol of the Southeastern Pampas under continuous cropping. Soil Tillage Res. 117:191-200.





With the patronage of
Universia
Avda. de Cantabria, s/n - 28660, Boadilla del Monte
Madrid, España
EMail: info@sjss.universia.net