Journal
JOURNAL OF PERFORMANCE OF CONSTRUCTED FACILITIES
Volume 33, Issue 3, Pages -Publisher
ASCE-AMER SOC CIVIL ENGINEERS
DOI: 10.1061/(ASCE)CF.1943-5509.0001292
Keywords
Liquefaction potential; Stochastic gradient boosting; Cone penetration test (CPT); Standard penetration test (SPT)
Funding
- National Natural Science Foundation Project of China [41807259]
- State Key Laboratory Breeding Base for Mining Disaster Prevention and Control [MDPC201608]
- Natural Science Foundation of Hunan Province [2018JJ3693]
- China Postdoctoral Science Foundation [2017M622610]
- Sheng Hua Lie Ying Program of Central South University
Ask authors/readers for more resources
Earthquakes have always attracted civil and geotechnical engineers' attention, especially when it comes to the liquefaction potential of soil. This paper investigates the feasibility of classifier based on stochastic gradient boosting (SGB) to explore the liquefaction potential from actual cone penetration test (CPT) and standard penetration test (SPT) field data. SGB is composed of many classification and regression trees which meet the mechanism of ensemble learning and show strong predictive power compared with conventional statistical learning models in several engineering applications. The binary classifier was built by the database gathered from CPT and SPT filed data for predicting the non-liquefaction or liquefaction of soil, the SGB hyperparameters are optimized by grid search method with tenfolds cross validation methods. Three performance metric, namely Cohen's Kappa coefficient, classification accuracy rate and receiver operating characteristic curve, are used to evaluate the predictive performance of SGB approaches. With CPT and SPT test sets, highest classification accuracy rate of 88.62% and 95.45%, respectively, are achieved with SGB. It is confirmed that the SGB can be applied to characterize the complex relationship between the liquefaction potential and different soil and seismic parameters with great efficiency. Further, relative importance of influencing variables for each model are investigated and demonstrated that the SGB predictor is more sensitive to the indicators of initial soil friction angle for SPT data whereas cone tip resistance for CPT data.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available