Forecasting Tsunami Hazards Using Ocean Bottom Sensor Data and Classification Predictive Modeling
Bibliographic record
Abstract
This study compares the results of analyzing tsunami simulations that are based on two approaches of characterizing earthquake slips, i.e., uniform (simplistic) and heterogeneous (complex) distributions. The aim of this study is to compare how heterogeneous and uniform distributed data affect the classification of tsunami maximum near-shore tsunami amplitudes. Due to the lack of historical earthquake and tsunami data to train the forecasting model, 4000 stochastic tsunami simulations are employed. The focused location is Iwanuma, Japan, where ocean bottom sensors (OBS) S-net network has been deployed. Multiple linear regression combined with Akaike Information Criterion (AIC) is applied to the simulated off-shore wave amplitude data to fit the model. The estimated tsunami amplitude is classified into four levels of warning classes. The performance of the models is quantified by the accuracy of the confusion matrices and is compared with the base model that only uses earthquake information. The forecasting accuracy can be improved by 30% when the wave amplitude data are used as additional information. The heterogeneous slip-based model reaches a higher accuracy than the uniform-slip based model. The result of this study is particularly valuable for setting up an OBS-based system for monitoring the physical phenomena of tsunamis and choosing heterogeneous as a preferable slip distribution when tsunami events are simulated.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| 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 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".