Efficient 3D geological modeling for offshore wind farm with sparse CPTU and borehole data
Bibliographic record
Abstract
Geological modeling of complex marine strata is critical for offshore wind farm development but faces two challenges: (1) inconsistent soil classification between two commonly used site investigation data, i.e., piezocone penetration tests (CPTU) and boreholes, posing a challenge for integrating multi-source information; (2) sparse distribution of investigation data horizontally, which makes 3D spatial interpolation difficult. To tackle these two issues, this study proposes a novel framework for geological modeling of offshore wind farms. The framework encompasses two crucial steps. First, a tailored CPTU-based soil classification model is trained to resolve interpretation discrepancies. Second, an advanced spatial interpolation model is developed for the 3D modeling of sparse investigation data. Both steps make uses of simple but efficient nonparametric machine learning algorithms, e.g., weighted kNN, for predictions, i.e., soil classification and 3D spatial interpolation, respectively. Sequential model-based optimization technique is employed to determine the optimal model hyperparameter. The proposed methodology is demonstrated and validated through benchmark examples and applied to two case studies of offshore wind farms with complex strata in East China Sea and Yellow Sea. It significantly improves soil classification accuracy, especially for silty soils dominated site, and enhances the capability of complex stratigraphy modeling despite sparse 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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 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".