A New Compressional Wave Speed Inversion Method Based on Granularity Parameters
How to improve the prediction accuracy of compressional wave speed has always been one of the basic research subjects in geoacoustics study field. Due to the stability of granularity, whether in the laboratory or in the seabed environment, the regression relationship between compressional wave speed...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8937724/ |
id |
doaj-a50f0dee99984971bf66da7127533f11 |
---|---|
record_format |
Article |
spelling |
doaj-a50f0dee99984971bf66da7127533f112021-03-29T23:12:32ZengIEEEIEEE Access2169-35362019-01-01718584918585610.1109/ACCESS.2019.29611158937724A New Compressional Wave Speed Inversion Method Based on Granularity ParametersJingqiang Wang0https://orcid.org/0000-0002-5597-1352Zhengyu Hou1https://orcid.org/0000-0003-1741-8473Guanbao Li2https://orcid.org/0000-0003-0527-6922Guangming Kan3https://orcid.org/0000-0002-1229-5390Xiangmei Meng4https://orcid.org/0000-0002-4561-7130Baohua Liu5https://orcid.org/0000-0002-8065-9723School of Marine Sciences, Sun Yat-sen University, Guangdong, ChinaSchool of Marine Sciences, Sun Yat-sen University, Guangdong, ChinaKey Laboratory of Seafloor Sedimentology and Environmental Geology, First Institute of Oceanography, MNR, Qingdao, ChinaKey Laboratory of Seafloor Sedimentology and Environmental Geology, First Institute of Oceanography, MNR, Qingdao, ChinaKey Laboratory of Seafloor Sedimentology and Environmental Geology, First Institute of Oceanography, MNR, Qingdao, ChinaNational Deep Sea Center, MNR, Qingdao, ChinaHow to improve the prediction accuracy of compressional wave speed has always been one of the basic research subjects in geoacoustics study field. Due to the stability of granularity, whether in the laboratory or in the seabed environment, the regression relationship between compressional wave speed and granularity is an important sound speed inversion method. Machine Learning (ML) provides a new solution for more efficient sound speed prediction systems. In this study, two ML algorithm, Random forest (RF) and Support Vector Regression (SVR), combined with nine granularity parameters (mean grain size, median grain size, skewness, kurtosis, sorting coefficient, gravel, sand, silt, and clay content respectively.) to analysis the effect of granularity property on sound speed. As a result, the sound speed-granularity predictive models were established, and the sound speed accuracy obtained based on the predictive models are higher than that of the regression equations, and the RF model has a higher accuracy than the SVR model. Based on the RF predictive model, the feature selection was conducted and the results show that the most influential parameter of granularity is mean grain size. Furthermore, the RF model can also predict the sound speed with high precision in the absence of partial parameters, which can be a useful tool for ocean engineering and seismic inversion.https://ieeexplore.ieee.org/document/8937724/Geoacoustic inversiongranularitymachine learningrandom forestsound speed |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jingqiang Wang Zhengyu Hou Guanbao Li Guangming Kan Xiangmei Meng Baohua Liu |
spellingShingle |
Jingqiang Wang Zhengyu Hou Guanbao Li Guangming Kan Xiangmei Meng Baohua Liu A New Compressional Wave Speed Inversion Method Based on Granularity Parameters IEEE Access Geoacoustic inversion granularity machine learning random forest sound speed |
author_facet |
Jingqiang Wang Zhengyu Hou Guanbao Li Guangming Kan Xiangmei Meng Baohua Liu |
author_sort |
Jingqiang Wang |
title |
A New Compressional Wave Speed Inversion Method Based on Granularity Parameters |
title_short |
A New Compressional Wave Speed Inversion Method Based on Granularity Parameters |
title_full |
A New Compressional Wave Speed Inversion Method Based on Granularity Parameters |
title_fullStr |
A New Compressional Wave Speed Inversion Method Based on Granularity Parameters |
title_full_unstemmed |
A New Compressional Wave Speed Inversion Method Based on Granularity Parameters |
title_sort |
new compressional wave speed inversion method based on granularity parameters |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
How to improve the prediction accuracy of compressional wave speed has always been one of the basic research subjects in geoacoustics study field. Due to the stability of granularity, whether in the laboratory or in the seabed environment, the regression relationship between compressional wave speed and granularity is an important sound speed inversion method. Machine Learning (ML) provides a new solution for more efficient sound speed prediction systems. In this study, two ML algorithm, Random forest (RF) and Support Vector Regression (SVR), combined with nine granularity parameters (mean grain size, median grain size, skewness, kurtosis, sorting coefficient, gravel, sand, silt, and clay content respectively.) to analysis the effect of granularity property on sound speed. As a result, the sound speed-granularity predictive models were established, and the sound speed accuracy obtained based on the predictive models are higher than that of the regression equations, and the RF model has a higher accuracy than the SVR model. Based on the RF predictive model, the feature selection was conducted and the results show that the most influential parameter of granularity is mean grain size. Furthermore, the RF model can also predict the sound speed with high precision in the absence of partial parameters, which can be a useful tool for ocean engineering and seismic inversion. |
topic |
Geoacoustic inversion granularity machine learning random forest sound speed |
url |
https://ieeexplore.ieee.org/document/8937724/ |
work_keys_str_mv |
AT jingqiangwang anewcompressionalwavespeedinversionmethodbasedongranularityparameters AT zhengyuhou anewcompressionalwavespeedinversionmethodbasedongranularityparameters AT guanbaoli anewcompressionalwavespeedinversionmethodbasedongranularityparameters AT guangmingkan anewcompressionalwavespeedinversionmethodbasedongranularityparameters AT xiangmeimeng anewcompressionalwavespeedinversionmethodbasedongranularityparameters AT baohualiu anewcompressionalwavespeedinversionmethodbasedongranularityparameters AT jingqiangwang newcompressionalwavespeedinversionmethodbasedongranularityparameters AT zhengyuhou newcompressionalwavespeedinversionmethodbasedongranularityparameters AT guanbaoli newcompressionalwavespeedinversionmethodbasedongranularityparameters AT guangmingkan newcompressionalwavespeedinversionmethodbasedongranularityparameters AT xiangmeimeng newcompressionalwavespeedinversionmethodbasedongranularityparameters AT baohualiu newcompressionalwavespeedinversionmethodbasedongranularityparameters |
_version_ |
1724190017870364672 |