Author
![]() |
KRUEGER, E - Russian Academy Of Sciences |
![]() |
Prior, Stephen - Steve |
![]() |
KURTENER, D - Russian Academy Of Sciences |
![]() |
Rogers Jr, Hugo |
![]() |
Runion, George |
Submitted to: Book Chapter
Publication Type: Book / Chapter Publication Acceptance Date: 7/9/2010 Publication Date: 7/9/2010 Citation: Krueger, E., Prior, S.A., Kurtener, D., Rogers Jr, H.H., Runion, G.B. 2010. Use of an adaptive neuro-fuzzy system to characterize root distribution patterns. In: Kurtener, D., Yakushev, V.P., Torbert, H.A., Prior, S.A., and Krueger, E., editors. Applications of Soft Computing in Agricultural Field Experimentations. St. Petersburg, Russia: Agrophysical Research Institute. p. 59-69. Interpretive Summary: Plant root systems are difficult to measure and high variation among field samples often leads to no significant differnce when standard statistics are employed. We applied the Adaptive Neuro-Fuzzy Inference System (ANFIS) method to vertical and horizontal root distribution data collected from a potato (Solanum tuberosum L.) cropping system. Simulations indicated that ANFIS gave plausible results. This indicates that ANFIS may offer a viable alternative to more traditional statistical techniques for evaluation of complex root distribution patterns. Technical Abstract: Root-soil relationships are pivotal to understanding crop growth and function in a changing environmental. Plant root systems are difficult to measure and remain understudied relative to above ground responses. High variation among field samples often leads to non-significance when standard statistics are employed. The Adaptive Neuro-Fuzzy Inference System (ANFIS) has been applied in many agricultural and environmental fields and may represent a viable means for dealing with complexities of root distribution in soil. We applied this method to vertical and horizontal root distribution data collected from a potato (Solanum tuberosum L.) cropping system. Simulations indicated that ANFIS gave plausible results. This indicates that ANFIS may offer a viable alternative to more traditional statistical techniques for evaluation of complex root distribution patterns. |