Dataset for 'A Deep Learning Approach for Infrasound Signal Detection for Snow-Covered Areas'
Summary & Purpose
Waveform and statistical data accompanying the journal article "A Deep Learning Approach for Infrasound Signal Detection in Snow-Covered Areas," submitted for consideration to Applied Acoustics.
The infrasound sensor array technique is an established method for detecting and monitoring rapid gravity-driven mass movements from infrasound waveform. This technique requires the deployment of two or more sensors at an infrasound station. By employing the array techniques, signals are isolated from various sources of noise by computing cross-correlation measures between recorded signals across spatially distributed sensors at a station. Using multiple sensors requires additional processing that potentially increases event alert time. In this study, we present a signal detection method utilizing deep learning to identify high-quality signals in infrasound waveforms with data from a single infrasound sensor in contrast to multiple sensors required by the array method. This method aims to eradicate the additional processing required by the array techniques. The process involves using audio signal processing techniques to extract discriminatory features from the waveforms, which are then used to train a deep learning model. Data collected over a month period from Little Cottonwood Canyon, Utah, USA was used in this study. The location provides a continuous dataset featuring diverse events that include potential avalanches. Our research is motivated by the goal of identifying snow avalanche signals using a single infrasound sensor. The first step demonstrated in this work involves the use of deep learning techniques to identify high quality signals in recorded infrasound waveforms, including potential avalanche signals. The performance of the resulting optimal model was evaluated across a temporal and spatial scale, consistently achieving a classifier effectiveness score of over 80%.
Date of Publication or Submission
4-23-2025
DOI
https://doi.org/10.18122/infrasound_data.16.boisestate
Funding Citation
This research was supported by Utah Department of Transport, Utah, USA; and Snowbound Solutions LLC, Boise ID.
Single Dataset or Series?
Single Dataset
Data Format
*.mat; *.txt
File Size
13.9GB
Data Attributes
The data was collected using infraBSU pressure transducers (infrasound sensors manufactured at the infrasound lab of BSU) from two infrasound stations located approximately 500 meters apart. Each station had an aperture of about 50 meters and was equipped with three microphones arranged in a triangular configuration. Each microphone was connected to a central logger via a cable, with the microphones spaced approximately 15 meters apart from one another. Each files in the dayfile directory contains a dictionary (key value pair), The waveform data has the key “acfilts” with the value being a 3D array representing [recorded waveform for the given day :sensor id: station id] The files in the statistics directory have the following headings and meanings "const" : Consistency measure between waveform data in a 10sec windows from 2 sensors in a stations "samples": midpoint of a given window, e.g 501 represent the const and xcth of the time interval 0-10sec, given that the data was samples at 100Hz as such each second has 100 measurements "xcth" : cross correlation metrics between waveform data in a 10sec windows from 2 sensors in a stations
Time Period
Mar 22, 2023 - April 15, 2023
Update Frequency
Unknown
Privacy and Confidentiality Statement
Boise State is explicitly compliant with federal and state laws surrounding data privacy including the protection of personal financial information through the Gramm-Leach-Bliley Act, personal medical information through HIPAA, HITECH and other regulations. All human subject data (e.g., surveys) has been collected and managed only by personnel with adequate human subject protection certification.
Use Restrictions
Users are free to share, copy, distribute and use the dataset; to create or produce works from the dataset; to adapt, modify, transform and build upon the dataset as long as the user attributes any public use of the dataset, or works produced from the dataset, referencing the author(s) and DOI link. For any use or redistribution of the dataset, or works produced from it, the user must make clear to others the license of the dataset and keep intact any notices on the original dataset.
Disclaimer of Warranty
BOISE STATE UNIVERSITY MAKES NO REPRESENTATIONS ABOUT THE SUITABILITY OF THE INFORMATION CONTAINED IN OR PROVIDED AS PART OF THE SYSTEM FOR ANY PURPOSE. ALL SUCH INFORMATION IS PROVIDED "AS IS" WITHOUT WARRANTY OF ANY KIND. BOISE STATE UNIVERSITY HEREBY DISCLAIMS ALL WARRANTIES AND CONDITIONS WITH REGARD TO THIS INFORMATION, INCLUDING ALL WARRANTIES AND CONDITIONS OF MERCHANTABILITY, WHETHER EXPRESS, IMPLIED OR STATUTORY, FITNESS FOR A PARTICULAR PURPOSE, TITLE AND NON-INFRINGEMENT.
IN NO EVENT SHALL BOISE STATE UNIVERSITY BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF INFORMATION AVAILABLE FROM THE SYSTEM.
THE INFORMATION PROVIDED BY THE SYSTEM COULD INCLUDE TECHNICAL INACCURACIES OR TYPOGRAPHICAL ERRORS. CHANGES ARE PERIODICALLY ADDED TO THE INFORMATION HEREIN. COMPANY AND/OR ITS RESPECTIVE SUPPLIERS MAY MAKE IMPROVEMENTS AND/OR CHANGES IN THE PRODUCT(S) AND/OR THE PROGRAM(S) DESCRIBED HEREIN AT ANY TIME, WITH OR WITHOUT NOTICE TO YOU.
BOISE STATE UNIVERSITY DOES NOT MAKE ANY ASSURANCES WITH REGARD TO THE ACCURACY OF THE RESULTS OR OUTPUT THAT DERIVES FROM USE OF THE SYSTEM.
Recommended Citation
Ofekeze, Evi; Johnson, Jeffrey B.; and Marshall, Hans-Peter, "Dataset for 'A Deep Learning Approach for Infrasound Signal Detection for Snow-Covered Areas'" (2025). Boise State University Infrasound Data Repository. 16.
https://scholarworks.boisestate.edu/infrasound_data/16
Comments
Additional Contributors
Scott Havens, Snowbound Solutions, LLC, scott@snowboundsolutions.com
Steven Clark, Utah Department of Transport, stevenclark@utah.gov
Due to the size of this dataset's component files, if you would prefer to access this data via Globus, please email ScholarWorks@boisestate.edu.