Abstract
The regional nature of liquefaction records and limited information available for a certain set of explanatories motivate the development of complex prediction techniques. Indirect methods are commonly applied to incidentally derive a hyperplane to this binary classification problem. Machine learning approaches offer evolutionary prediction models which can be used as direct prediction methods to liquefaction occurrence. Ensemble learning is a recent advancement in this field. According to a predefined ensemble architecture, a number of learners are trained and their inferences are integrated to produce stable and improved generalization ability. However, there is a need to consider several aspects of the ensemble learning frameworks when exploiting them for a particular application; a comprehensive evaluation of an ensemble learner’s generalization ability is required but usually overlooked. Also, the literature falls short on work utilizing ensemble learning in liquefaction prediction. To this extent, this work examines useful ensemble learning approaches for seismic-induced liquefaction prediction. A comprehensive analysis of fifteen ensemble models is performed. The results show improved prediction performance and diminishing uncertainty of ensembles, compared with single machine learning models.
Highlights
Seismic-induced liquefaction of soils is one of the major ground failure consequences of earthquakes
The focus of the current study is to demonstrate the application of ensemble learning approaches for liquefaction prediction
Ensemble models of Decision Trees are commonly known in the broad literature as Random Forests (RF)
Summary
Seismic-induced liquefaction of soils is one of the major ground failure consequences of earthquakes. Liquefaction is the transformation of soil from a solid to a liquefied state as a result of increased pore water pressure, which commonly occurs during sudden and massive shaking of the ground. This phenomenon leads to catastrophic loss of lives and irreversible damage to critical infrastructure. We use the terms direct and indirect modeling approaches to refer to empirical and deterministic studies, respectively. The motivation behind this nomenclature is related to the classification objective (Fig. 1). More advanced prediction methods are required to provide better generalization ability over a wide range of liquefaction observations, rather than local thresholding of the phenomenon through filtering already limited datasets
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
