Acoustic characteristics of seafloor sediments in the abyssal areas of the South China Sea

Hou, Zhengyu; Chen, Zhong; Wang, Jingqiang; Zheng, Xiaoxu; Yan, Wen; Tian, Yuhang; Luo, Yunjian

doi:10.1016/j.oceaneng.2018.03.013

Cited by 17 publications

(11 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sediment cores were cut into standard cylinders (25 cm long), and we used a portable WSD-3 digital sonic instrument and the coaxial differential distance measurement method (Hou et al, 2015;Hou et al, 2018a) to measure the compressional wave velocity (sound velocity, V) of the standard cylinders in the standard condition (23°C, atmospheric pressure). The laboratory measurement values were calibrated to the seafloor values by using the sound velocity ratio method (Hamilton, 1971;Hou et al, 2018b).…”

Section: Sediment Samplingmentioning

confidence: 99%

Sound Velocity Predictive Model Based on Physical Properties

Hou

Wang

Chen

et al. 2019

Earth and Space Science

View full text Add to dashboard Cite

The correlation between sediment sound velocity (V) and physical properties has been studied for 60 years using empirical equations, and it has been found difficult to predict V accurately. Random Forest (RF) is a scientific discipline and a method of data analysis that automates analytical model building. Here we present the implementation of RF algorithm in V prediction and sediment classification. The databases were from previously collected data in the northern South China Sea. The goal of this study is to establish a predictive model based on RF using multiple physical properties (mean grain size, porosity, wet bulk density, and water content). Compared to empirical equations, the average error of RF velocity is only 0.95%, ranging from 0.03 to 2.73%, indicating that the RF algorithm has improved the accuracy of V prediction. We also used mean decrease impurity importance to evaluate the importance of a variable and found that the most important feature in the predictive model is mean grain size. We also used the RF as a potentially useful tool for sediment classification. The classification model has up to 75% accuracy in the dataset. Multiple features, such as physical properties, sedimentary environment, and sediment source, affect the geoacoustic properties of sediments. The next goal is to use multiple features to improve the model and further improve the accuracy of sound velocity prediction and sediment classification.

show abstract

Section: Sediment Samplingmentioning

confidence: 99%

Sound Velocity Predictive Model Based on Physical Properties

Hou

Wang

Chen

et al. 2019

Earth and Space Science

View full text Add to dashboard Cite

show abstract

“…Every cut section of the core needs to be measured. More details on the measuring procedure are described in Hou et al [17], [18]. The sound speed pulse was detected via wavelet transform methods, the calculation of uncertainty was performed using statistical methods.…”

Section: Data and Processingmentioning

confidence: 99%

“…Environmental factors (temperature, salinity and hydrostatic pressure) have a notable effect on the sound speed of seawater and on the acoustic properties of seafloor sediment [17], [42]. Before the model was established, the measured sound speed was corrected to in situ condition using the velocity ratio method [12], although the laboratory sound speed can not be entirely corrected.…”

Section: Data and Processingmentioning

confidence: 99%

“…The corrected data still can be used to establish various models and to analyze the prediction of different models. Detailed descriptions of the velocity ratio method also were reported in Hou et al [17].…”

Section: Data and Processingmentioning

confidence: 99%

“…and sediment structure. The physical properties are considered the most important [10], [17], especially the granularity, which is described by factors such as the mean grain size, median grain size, grain fraction, and sorting coefficient. As the grain size keep unchanged when the sediment was collected from the seafloor to the laboratory, the relationship between sound speed and granularity has long been an important topic of sediment acoustic study [2].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A New Compressional Wave Speed Inversion Method Based on Granularity Parameters

Wang

Hou

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

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.INDEX TERMS Geoacoustic inversion, granularity, machine learning, random forest, sound speed.

show abstract