A polynomial model for predicting liquefaction potential from cone penetration test data

Liquefaction is a serious geotechnical hazard leading to catastrophic damageto life and property. in many instances, it may be preferable to predict liquefactionsusceptibility indirectly by common in-situ tests, such as the cone penetration test(cpt). a new approach for prediction of liquefaction susceptibility is proposed, whichpresents a polynomial model to correlate the cyclic resistance ratio (crr) predicatedon subsoil geotechnical properties from cpt tests, that is, normalized cone tip resistance(qc1) and friction resistance (fs). the derived model is applied to a total of 182 datasets, including eld investigation records from eighteen earthquakes. the performanceof the proposed approach is compared to other available methods within a quantitativevalidation framework (e.g., precision, recall, and f-score). results indicate the accuracyand generalization of the proposed new approach in predicting liquefaction susceptibility.