Digital twin-based automated sonar signal simulation for training datasets
Bibliographic record
Abstract
The growing importance of sonar AI in maritime defense and target detection, tracking, and classification has created an urgent need for extensive training datasets. However, data collection in real marine environments remains costly and time-intensive. We present an automated sonar signal simulation based on Digital Twin technology. The system generates scenarios automatically using user-defined parameters, including data volume, environmental conditions, ownship and target maneuvers, target noise, and ambient noise characteristics. Acoustic propagation modeling utilizes oceanographic databases with parameters such as depth, temperature, and salinity profiles to account for the physical characteristics of sonar propagation. Target information databases include vessel characteristics—hull dimensions, screw, and engine parameters—enabling realistic simulation of both broadband and narrowband tonal signatures in targets. This simulation framework facilitates large-scale dataset generation for sonar AI applications. We describe the system architecture and signal generation process, with validation through CNN-based target classification experiments. Two datasets generated by our system achieved classification accuracies of 67.9% and 94.4%, respectively. Through analysis of performance differences based on dataset composition, we demonstrate the system's practical utility for sonar AI development. [Work supported by Korean Research Institute for defense Technology planning and advancement, KRIT-CT-22-023.]
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".