TY - JOUR
T1 - Residual soil nitrate prediction from imagery and non-imagery information using neural network technique
AU - Gautam, Ramesh
AU - Panigrahi, Suranjan
AU - Franzen, David
AU - Sims, Albert
N1 - Funding Information:
The authors appreciate Agri-Images Inc, Fargo for providing satellite images and USDA-IFAFS program for financial support of this study.
PY - 2011/9
Y1 - 2011/9
N2 - Textural features extracted from LANDSAT satellite image and non-imagery information like soil electrical conductivity, crop yield, topography, and crop dry residue matter etc., were used to develop residual soil nitrate prediction models using three neural networks; back propagation, modular, and radial basis function architectures. Statistical parameters were compared to evaluate the performance of three neural network models. The residual soil nitrate prediction model based on back propagation neural network (BPNN) architecture depicted the highest average accuracy of 83.29% and the lowest root mean square error of 10.61%. The corresponding correlation coefficient of 91% was the highest among those provided by all three NN models. Sensitivity analysis showed equal importance of both imagery and non-imagery variables for predicting residual soil nitrate content in field conditions.
AB - Textural features extracted from LANDSAT satellite image and non-imagery information like soil electrical conductivity, crop yield, topography, and crop dry residue matter etc., were used to develop residual soil nitrate prediction models using three neural networks; back propagation, modular, and radial basis function architectures. Statistical parameters were compared to evaluate the performance of three neural network models. The residual soil nitrate prediction model based on back propagation neural network (BPNN) architecture depicted the highest average accuracy of 83.29% and the lowest root mean square error of 10.61%. The corresponding correlation coefficient of 91% was the highest among those provided by all three NN models. Sensitivity analysis showed equal importance of both imagery and non-imagery variables for predicting residual soil nitrate content in field conditions.
UR - http://www.scopus.com/inward/record.url?scp=80051786979&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80051786979&partnerID=8YFLogxK
U2 - 10.1016/j.biosystemseng.2011.06.002
DO - 10.1016/j.biosystemseng.2011.06.002
M3 - Article
AN - SCOPUS:80051786979
SN - 1537-5110
VL - 110
SP - 20
EP - 28
JO - Biosystems Engineering
JF - Biosystems Engineering
IS - 1
ER -