An Ensemble Method for Soil Parameter Prediction Based on Multisource Data Fusion

Abstract

Site investigation is crucial in geotechnical engineering. The cone penetration test (CPT) and the multichannel analysis of surface waves (MASWs) are widely used as geotechnical and geophysical methods, respectively. CPT offers high precision but requires a high cost and only provides soil information at limited locations. In contrast, MASW covers a broad range of soil information but has less accuracy compared to CPT. This study proposes a novel ensemble prediction method that fuses both CPT and MASW data to overcome the limitations of using either dataset alone. The method employs random forest (RF) and gradient boosting decision tree (GBDT) to achieve the transformation between the shear velocity and cone tip resistance (Vs–qc) and the prediction of qc at unknown locations. Unlike traditional empirical regression models, this method provides more accurate and reliable predictions by leveraging the complementary strengths of CPT and MASW. The proposed RF-GBDT ensemble model is validated using data from the New Zealand Geotechnical Database. The results show that the established RF-GBDT ensemble model outperforms simple empirical regression models and various popular machine learning models in the Vs–qc transformation and in predicting qc at unknown locations. Specifically, integrating MASW data increases the R2 at location CPT3 from 0.477 to 0.758, demonstrating that the proposed method can improve the predictions of soil parameters in areas with sparse data.