Abstract-Neural networks-based sensitivity analysis of parameters of geotechnical engineering systems has become a research focus of increasing interest. This study presents a neural network ensemble-based parameter sensitivity analysis method to investigate the sensitivity of variables leading to lateral deformation in an earth-retaining wall of foundation pit system. This method allows not only identification of the dominant variables of the foundation pit system but it also helps to reveal of the relationship between the explicative (input) and dependent (output) variables of the system. The effectiveness of the proposed method is validated by the typical case in geotechnical engineering system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.