Atmospheric Structure Prediction for Infrasound Propagation Modeling Using Deep Learning
Abstract Infrasound is generated by a variety of natural and anthropogenic sources. Infrasonic waves travel through the dynamic atmosphere, which can change on the order of minutes to hours. Infrasound propagation largely depends on the wind and temperature structure of the atmosphere. Numerical wea...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Geophysical Union (AGU)
2022-08-01
|
| Series: | Earth and Space Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2022EA002233 |
| _version_ | 1828354111315116032 |
|---|---|
| author | S. A. Albert |
| author_facet | S. A. Albert |
| author_sort | S. A. Albert |
| collection | DOAJ |
| description | Abstract Infrasound is generated by a variety of natural and anthropogenic sources. Infrasonic waves travel through the dynamic atmosphere, which can change on the order of minutes to hours. Infrasound propagation largely depends on the wind and temperature structure of the atmosphere. Numerical weather prediction models are available to provide atmospheric specifications, but uncertainties in these models exist and they are computationally expensive to run. Machine learning has proven useful in predicting tropospheric weather using Long Short‐Term Memory (LSTM) networks. An LSTM network is utilized to make atmospheric specification predictions up to ∼30 km for three different training and testing scenarios: (a) the model is trained and tested using only radiosonde data from the Albuquerque, NM, USA station, (b) the model is trained on radiosonde stations across the contiguous US, excluding the Albuquerque, NM, USA station, which was reserved for testing, and (c) the model is trained and tested on radiosonde stations across the contiguous US. Long Short‐Term Memory predictions are compared to a state‐of‐the‐art reanalysis model and show cases where the LSTM outperforms, performs equally as well, or underperforms in comparison to the state‐of‐the‐art. Regional and temporal trends in model performance across the US are also discussed. Results suggest that the LSTM model is a viable tool for predicting atmospheric specifications for infrasound propagation modeling. |
| first_indexed | 2024-04-14T02:19:19Z |
| format | Article |
| id | doaj.art-f0b92c21916a405590d2dacef71f4ea2 |
| institution | Directory Open Access Journal |
| issn | 2333-5084 |
| language | English |
| last_indexed | 2024-04-14T02:19:19Z |
| publishDate | 2022-08-01 |
| publisher | American Geophysical Union (AGU) |
| record_format | Article |
| series | Earth and Space Science |
| spelling | doaj.art-f0b92c21916a405590d2dacef71f4ea22022-12-22T02:18:06ZengAmerican Geophysical Union (AGU)Earth and Space Science2333-50842022-08-0198n/an/a10.1029/2022EA002233Atmospheric Structure Prediction for Infrasound Propagation Modeling Using Deep LearningS. A. Albert0Sandia National Laboratories Albuquerque NM USAAbstract Infrasound is generated by a variety of natural and anthropogenic sources. Infrasonic waves travel through the dynamic atmosphere, which can change on the order of minutes to hours. Infrasound propagation largely depends on the wind and temperature structure of the atmosphere. Numerical weather prediction models are available to provide atmospheric specifications, but uncertainties in these models exist and they are computationally expensive to run. Machine learning has proven useful in predicting tropospheric weather using Long Short‐Term Memory (LSTM) networks. An LSTM network is utilized to make atmospheric specification predictions up to ∼30 km for three different training and testing scenarios: (a) the model is trained and tested using only radiosonde data from the Albuquerque, NM, USA station, (b) the model is trained on radiosonde stations across the contiguous US, excluding the Albuquerque, NM, USA station, which was reserved for testing, and (c) the model is trained and tested on radiosonde stations across the contiguous US. Long Short‐Term Memory predictions are compared to a state‐of‐the‐art reanalysis model and show cases where the LSTM outperforms, performs equally as well, or underperforms in comparison to the state‐of‐the‐art. Regional and temporal trends in model performance across the US are also discussed. Results suggest that the LSTM model is a viable tool for predicting atmospheric specifications for infrasound propagation modeling.https://doi.org/10.1029/2022EA002233infrasoundpropagation modelingdeep learningLSTMacousticsatmosphere |
| spellingShingle | S. A. Albert Atmospheric Structure Prediction for Infrasound Propagation Modeling Using Deep Learning Earth and Space Science infrasound propagation modeling deep learning LSTM acoustics atmosphere |
| title | Atmospheric Structure Prediction for Infrasound Propagation Modeling Using Deep Learning |
| title_full | Atmospheric Structure Prediction for Infrasound Propagation Modeling Using Deep Learning |
| title_fullStr | Atmospheric Structure Prediction for Infrasound Propagation Modeling Using Deep Learning |
| title_full_unstemmed | Atmospheric Structure Prediction for Infrasound Propagation Modeling Using Deep Learning |
| title_short | Atmospheric Structure Prediction for Infrasound Propagation Modeling Using Deep Learning |
| title_sort | atmospheric structure prediction for infrasound propagation modeling using deep learning |
| topic | infrasound propagation modeling deep learning LSTM acoustics atmosphere |
| url | https://doi.org/10.1029/2022EA002233 |
| work_keys_str_mv | AT saalbert atmosphericstructurepredictionforinfrasoundpropagationmodelingusingdeeplearning |