An artificial neural network approach for predicting soil carbon budget in agroecosystems

Soil quality has been associated with its organic matter content. Additionally, much eff ort has gone into understanding the C cycle and generating models suitable for C fl ux prediction. We used published data from long-term tillage experiments performed in the Pampas of Argentina, where CO2–C emis...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autor principal: Alvarez, Roberto
Otros Autores: Steinbach, Haydée Sara, Bono, Angel Alfredo
Formato: Artículo
Lenguaje:Inglés
Materias:
SR
Acceso en línea:http://ri.agro.uba.ar/files/intranet/articulo/2011alvarez1.pdf
LINK AL EDITOR
Aporte de:Registro referencial: Solicitar el recurso aquí
LEADER 03015nab a22003137a 4500
001 20190904140800.0
003 AR-BaUFA
005 20220920130545.0
008 190904t2011 xxud||||o|||| 00| 0 eng d
999 |c 47590  |d 47590 
999 |d 47590 
999 |d 47590 
999 |d 47590 
022 |a 0361-5995 
024 |a 10.2136/sssaj2009.0427 
040 |a AR-BaUFA 
100 1 |9 7830  |a Alvarez, Roberto  |u Universidad de Buenos Aires. Facultad de Agronomía. Buenos Aires, Argentina. 
245 0 0 |a An artificial neural network approach for predicting soil carbon budget in agroecosystems 
520 |a Soil quality has been associated with its organic matter content. Additionally, much eff ort has gone into understanding the C cycle and generating models suitable for C fl ux prediction. We used published data from long-term tillage experiments performed in the Pampas of Argentina, where CO2–C emissions from organic C pools were determined in the fi eld, for developing empirical models suitable for C fl ux emission prediction. We also performed 113 fi eld experiments with corn (Zea mays L.), wheat (Triticum aestivum L.), and soybean [Glycine max (L.) Merr.] to determine crop C inputs to the soil. Two empirical modeling techniques were tested: polynomial regression and artificial neural networks. Both methodologies generated good models with R2 ranging from 0.70 to 0.86. Nevertheless, neural networks performed better than regressions, with signifi cantly lower RMSE values for both CO2–C emissions and C input prediction. Daily CO2–C emissions could be predicted by the neural network (R2 = 0.86) using soil C content, temperature, and moisture level as independent variables. Crop C inputs (R2 = 0.85) were estimated using crop type, yield, and rainfall during the growing cycle. Th e models were used for evaluating of the impact of soybean introduction in rotations during the 1970 to 1980 decade. Despite soybean C inputs to the soil being lower than those of wheat and corn, which were replaced in rotations, soil C budgets are similar compared with the 1970 to 1980 period, or changed from negative to positive at the present. These changes were associated with yield increases ascribed to technological improvement that resulted in greater C inputs from graminaceous crops. 
653 |a SR 
653 |a SENSITIVITY RATIO 
700 1 |9 7682  |a Steinbach, Haydée Sara  |u Universidad de Buenos Aires. Facultad de Agronomía. Buenos Aires, Argentina. 
700 |9 16055  |a Bono, Angel Alfredo  |u Instituto Nacional de Tecnología Agropecuaria (INTA). Estación Experimental Agropecuaria Anguil (EEA Anguil), Anguil), La Pampa. Argentina. 
773 0 |t Soil Science Society of America journal  |w SECS000170  |g vol.75, no.3 (2011), p.965-975, grafs. 
856 |f 2011alvarez1  |i En Reservorio:  |q application/pdf  |u http://ri.agro.uba.ar/files/intranet/articulo/2011alvarez1.pdf  |x ARTI201908 
856 |u http://www.soils.org/  |z LINK AL EDITOR 
942 |c ARTICULO 
942 |c ENLINEA 
976 |a AAG