收藏切换
Comparison of CPT liquefaction discrimination methods and analysis of liquefaction influencing factors based on machine learning
收藏切换
PDF
Chengcheng LI1, 2, Yiyi CUI2, Zhongxian LIU1, 2, Xiaoming YUAN3, 4, Lan XU2, Qingbin WEI2
Earthquake Engineering and Engineering Dynamics | 2025, 45(3) : 106 - 117
Less
收藏切换
Earthquake Engineering and Engineering Dynamics | 2025, 45(3): 106-117
Comparison of CPT liquefaction discrimination methods and analysis of liquefaction influencing factors based on machine learning
Full
Chengcheng LI1, 2, Yiyi CUI2, Zhongxian LIU1, 2, Xiaoming YUAN3, 4, Lan XU2, Qingbin WEI2
Affiliations
  • 1.Key Laboratory of Soft Soil Characteristics and Engineering Environment, Tianjin Chengjian University, Tianjin 300384, China
  • 2.School of Civil Engineering, Tianjin Chengjian University, Tianjin 300384, China
  • 3.Key Laboratory of Earthquake Engineering and Engineering Vibration, Institute of Engineering Mechanics, China Earthquake Administration, Harbin 150080, China
  • 4.Key Laboratory of Earthquake Disaster Mitigation, Ministry of Emergency Management, Harbin 150080, China
Published: 2025-06-30 doi: 10.13197/j.eeed.2025.0309
Outline
收藏切换

There are various liquefaction assessment methods empirically based on test data used both domestically and internationally. Among them, the cone penetration test (CPT) has become a common method due to its inherent advantages. This paper elaborates on four commonly used CPT-based liquefaction assessment methods from both domestic and international sources: the NCEER method, the Code for investigation of geotechnical engineering method, the Specification for geotechnical invesitgation in soft clay area method, and the General rules for performance-based seismic design of buildings method. It compares the assessment results of these methods and utilizes data-driven classification and regression tree (CART) and random forest (RF) algorithms to study and analyze the importance of liquefaction influencing factors and the interplay among them. A new set of standards for determining liquefaction occurrence was developed, showing that: The General Rules method proposed by YUAN Xiaoming et al. is balanced with the highest accuracy for liquefaction assessment, achieving over 94% accuracy in seismic intensity zones of 7, 8 and 9, which is higher than the NCEER method, and significantly better than the Geotechnical Specification and Soft Soil Procedure methods. The NCEER method, though ranking second best, tends to misclassify a large quantity of non-liquefaction data as liquefaction in deeper layers of intensity zone 9, which is not consistent with reality. The performance of the Geotechnical Specification and Soft Soil Procedure methods is the worst. The accuracies of the two machine learning methods are 97.6% and 97.5% respectively, with the importance ranking of predictive variables being largely consistent. Factors such as relative density (Dr), soil behavior type index (Ic), fines content (FC), and cover thickness (CT) have a significant impact on triggering liquefaction, whereas peak ground acceleration (PGA), groundwater table (GWT), and critical thickness of the liquefiable layer (CTL) have a lesser impact. The proposed new standards for liquefaction triggering are in line with the impact trends of various influencing factors, providing references and support for the prediction and assessment of liquefaction triggering.

static cone penetration test  /  liquefaction discrimination methods  /  CART decision tree  /  random forest  /  liquefaction triggering discrimination criteria
Chengcheng LI, Yiyi CUI, Zhongxian LIU, Xiaoming YUAN, Lan XU, Qingbin WEI. Comparison of CPT liquefaction discrimination methods and analysis of liquefaction influencing factors based on machine learning[J]. Earthquake Engineering and Engineering Dynamics, 2025 , 45 (3) : 106 -117 . DOI: 10.13197/j.eeed.2025.0309
Year 2025 volume 45 Issue 3
PDF
76
41
Cite this Article
BibTeX
Article Info
doi: 10.13197/j.eeed.2025.0309
  • Receive Date:2024-04-20
  • Online Date:2026-03-20
  • Published:2025-06-30
Article Data
Affiliations
History
  • Received:2024-04-20
  • Revised:2024-05-20
Funding
Affiliations
    1.Key Laboratory of Soft Soil Characteristics and Engineering Environment, Tianjin Chengjian University, Tianjin 300384, China
    2.School of Civil Engineering, Tianjin Chengjian University, Tianjin 300384, China
    3.Key Laboratory of Earthquake Engineering and Engineering Vibration, Institute of Engineering Mechanics, China Earthquake Administration, Harbin 150080, China
    4.Key Laboratory of Earthquake Disaster Mitigation, Ministry of Emergency Management, Harbin 150080, China
References
Share
https://castjournals.cast.org.cn/joweb/dzgcygczd/EN/10.13197/j.eeed.2025.0309
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT