Deep Learning-Based Approach for Acoustic Source Localization in Turbulent Flows
Bibliographic record
Abstract
Detection of acoustic sources in turbulent flows is an important part of the study of aeroacoustic noise. Passive Acoustic Source Localization is a method that uses the pressure fluctuations recorded by a microphone array to triangulate the location of the source. An application of Passive Acoustic Source Localization in the area of aeroacoustics is the detection of aircraft wakes. Aircraft wakes are responsible for causing wake turbulence thus airports must factor in the time it takes for the wakes to dissipate. A robust and accurate method for the detection of these wakes could result in increased efficiency and throughput for airports all around the world. Aircraft wakes are characterized by wake vortices that have been shown to emit characteristic noise that generally lies in the low-frequency range (100-500 Hz). The low-frequency nature of the noise causes traditional methods such as Acoustic Beamforming to fail. In this work, we tackled the problem of low-frequency, Passive Acoustic Source Localization using a Deep Learning-based approach. Deep Learning algorithms have found application in a wide range of domains including Acoustic Source Localization (ASL) due to their ability to extract features from limited or unstructured data. We simulated various test cases and models to test the viability of this approach. The architectures used in the models were Convolutional Neural Networks (CNN) and feed-forward Artificial Neural Networks (ANN). The choice of architecture was governed by the nature of the input feature. The test cases included two-dimensional ASL for detecting sources on the horizon or on a scanning plane parallel to the microphone array plane, three-dimensional ASL, and moving source detection. The results show much promise and are testimony to the viability of the approach, thus giving the incentive to build a real-life ASL framework for the detection of acoustic sources in turbulent flows.
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 | 0.001 |
| 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) | 0.006 | 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".