Mutation-aware hybrid model for prediction of long-term ground settlement with uncertainty incorporated
Bibliographic record
Abstract
Accurate prediction of long-term ground settlement is essential for protecting existing structures and ensuring the safe progress of filling works. However, most existing methods fail to accurately predict the long-term deformation evolution following unexpected mutations. The paper proposes a mutation-aware hybrid model (MAHM) for forecasting long-term settlement with uncertainty quantified. The MAHM comprises two components: an ensemble empirical equation that supplies prior physical and engineering basis, and a modified long short-term memory network (LSTM) that refines the empirical model. The modified LSTM is constrained by a time-aware loss and employs mutation-aware bootstrap training to capture abrupt deformation features and to quantify predictive uncertainty. The method is validated in four challenging case studies and compared with three existing models. Results show that, on average, MAHM reduces the relative L 2 error by approximately 58.2%, 13.6%, and 22.1% relative to the ensemble empirical equation, LSTM, and an alternative multi-fidelity model, respectively; the mean prediction error of MAHM across scenarios remains within 20%, and the average coverage of actual values within the 95% confidence interval exceeds 80%. Additionally, MAHM's accuracy improves over time as it is dynamically updated. The model offers a practical and data-efficient approach for predicting long-term deformation, facilitating the timely implementation of mitigation measures.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".