Machine learning-enhanced soil classification by integrating borehole and CPTU data with noise filtering

Integrating borehole and piezocone penetration test (CPTU) data in site characterization helps to achieve a more comprehensive understanding of ground conditions. However, soil types at CPTU and nearby borehole locations may not always be consistent. The presence of noisy data or thin layers will mislead the interpretation of CPTU data in soil type classification and soil property evaluation. This study proposes a coupled machine learning method to integrate the borehole and CPTU data under a rigorous Bayesian framework and to identify and separate the noisy CPTU data without subjective judgment, which contributes to more reliable soil classification and property evaluation. The borehole-reported soil type and CPTU data are treated as two types of evidence of the authentic soil type. A lateral transition of soil type from the CPTU location to the borehole location is allowed to capture the discrepancy of soil types. The proposed approach is applied to the marine site characterization of the Hong Kong-Zhuhai-Macao Bridge that crosses the Pearl River Estuary of China. The soil seams embedded in the dominant soil strata are successfully detected, producing a more reliable soil profile and interpreting more compatible soil properties with engineering practice. Additionally, the integration of borehole and CPTU data significantly reduces the stratification uncertainty in site characterization.

Automated summary

Integrating borehole and CPTU data using a coupled machine learning method under a Bayesian framework can achieve more reliable soil classification and property evaluation. Applied to the marine site characterization of the Hong Kong-Zhuhai-Macao Bridge, this approach successfully detects soil seams, resulting in a more reliable soil profile and interpretation of compatible soil properties with engineering practice.