Earthquake Declustering Using Supervised Machine Learning
Bibliographic record
Abstract
ABSTRACT Earthquake catalog declustering is the procedure of separating event clusters from background seismicity, which is an important task in statistical seismology, earthquake forecasting, and probabilistic seismic hazard analysis. Several declustering methods have been introduced in the literature and operate under the supposition that background events occur independently whereas clusters are triggered by prior events. Here, we test the ability of supervised machine learning (SML) on the declustering problem by leveraging two popular statistical methods. First, the epidemic-type aftershock sequence model is fit to a target catalog and the parameters are used to generate synthetic earthquake data, which replicate the magnitude–space–time seismicity of the target catalog. Next, the nearest-neighbor distance (NND) metrics are computed between each simulated event and used as features to train the SML algorithm. Finally, the trained algorithm is applied to decluster synthetic testing data and then the original target catalog. Our results indicate that the SML method performs better than the NND-based and stochastic declustering methods on the test data and makes more nuanced selections of background and clustered events when applied to real seismicity. Although the vast majority of the SML technique’s predictive power appears to lie within the NND values of the “first” nearest neighbors, a machine learning analysis reveals that predictive accuracy can be improved by additional “next” nearest neighbors and differential magnitude features. The developed approach is applied to seismic catalogs in southern California and Italy to decluster them.
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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 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".