Comparisons between physics-based, engineering, and statistical learning models for outdoor sound propagation
Many outdoor sound propagation models exist, ranging from highly complex physics-based simulations to simplified engineering calculations, and more recently, highly flexible statistical learning methods. Several engineering and statistical learning models are evaluated by using a particular physics-based model, namely, a Crank-Nicholson parabolic equation (CNPE), as a benchmark. Narrowband transmission loss values predicted with the CNPE, based upon a simulated data set of meteorological, boundary, and source conditions, act as simulated observations. In the simulated data set sound propagation conditions span from downward refracting to upward refracting, for acoustically hard and soft boundaries, and low frequencies. Engineering models used in the comparisons include the ISO 9613-2 method, Harmonoise, and Nord2000 propagation models. Statistical learning methods used in the comparisons include bagged decision tree regression, random forest regression, boosting regression, and artificial neural network models. Computed skill scores are relative to sound propagation in a homogeneous atmosphere over a rigid ground. Overall skill scores for the engineering noise models are 0.6%, -7.1%, and 83.8% for the ISO 9613-2, Harmonoise, and Nord2000 models, respectively. Overall skill scores for the statistical learning models are 99.5%, 99.5%, 99.6%, and 99.6% for bagged decision tree, random forest, boosting, and artificial neural network regression models, respectively.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2016 |
---|---|
Erschienen: |
2016 |
Enthalten in: |
Zur Gesamtaufnahme - volume:139 |
---|---|
Enthalten in: |
The Journal of the Acoustical Society of America - 139(2016), 5 vom: 02. Mai, Seite 2640 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Hart, Carl R [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Completed 21.06.2018 Date Revised 21.06.2018 published: Print Citation Status PubMed-not-MEDLINE |
---|
doi: |
10.1121/1.4948757 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM260957194 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM260957194 | ||
003 | DE-627 | ||
005 | 20231224194518.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231224s2016 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1121/1.4948757 |2 doi | |
028 | 5 | 2 | |a pubmed24n0869.xml |
035 | |a (DE-627)NLM260957194 | ||
035 | |a (NLM)27250158 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Hart, Carl R |e verfasserin |4 aut | |
245 | 1 | 0 | |a Comparisons between physics-based, engineering, and statistical learning models for outdoor sound propagation |
264 | 1 | |c 2016 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 21.06.2018 | ||
500 | |a Date Revised 21.06.2018 | ||
500 | |a published: Print | ||
500 | |a Citation Status PubMed-not-MEDLINE | ||
520 | |a Many outdoor sound propagation models exist, ranging from highly complex physics-based simulations to simplified engineering calculations, and more recently, highly flexible statistical learning methods. Several engineering and statistical learning models are evaluated by using a particular physics-based model, namely, a Crank-Nicholson parabolic equation (CNPE), as a benchmark. Narrowband transmission loss values predicted with the CNPE, based upon a simulated data set of meteorological, boundary, and source conditions, act as simulated observations. In the simulated data set sound propagation conditions span from downward refracting to upward refracting, for acoustically hard and soft boundaries, and low frequencies. Engineering models used in the comparisons include the ISO 9613-2 method, Harmonoise, and Nord2000 propagation models. Statistical learning methods used in the comparisons include bagged decision tree regression, random forest regression, boosting regression, and artificial neural network models. Computed skill scores are relative to sound propagation in a homogeneous atmosphere over a rigid ground. Overall skill scores for the engineering noise models are 0.6%, -7.1%, and 83.8% for the ISO 9613-2, Harmonoise, and Nord2000 models, respectively. Overall skill scores for the statistical learning models are 99.5%, 99.5%, 99.6%, and 99.6% for bagged decision tree, random forest, boosting, and artificial neural network regression models, respectively | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Research Support, U.S. Gov't, Non-P.H.S. | |
700 | 1 | |a Reznicek, Nathan J |e verfasserin |4 aut | |
700 | 1 | |a Wilson, D Keith |e verfasserin |4 aut | |
700 | 1 | |a Pettit, Chris L |e verfasserin |4 aut | |
700 | 1 | |a Nykaza, Edward T |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t The Journal of the Acoustical Society of America |d 1962 |g 139(2016), 5 vom: 02. Mai, Seite 2640 |w (DE-627)NLM000324604 |x 1520-8524 |7 nnns |
773 | 1 | 8 | |g volume:139 |g year:2016 |g number:5 |g day:02 |g month:05 |g pages:2640 |
856 | 4 | 0 | |u http://dx.doi.org/10.1121/1.4948757 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 139 |j 2016 |e 5 |b 02 |c 05 |h 2640 |