Feasibility of Stochastic Gradient Boosting Approach for Evaluating Seismic Liquefaction Potential Based on SPT and CPT Case Histories
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".