Sound Velocity Predictive Model Based on Physical Properties
Sound Velocity Predictive Model Based on Physical Properties
复制标题
基于物理特性的声速预测模型
DOI：
10.1029/2018ea000545
复制
发表时间：
2019-08
影响因子：
3.1
通讯作者：
Tian Y. H.
中科院分区：
文献类型：
--
作者：
Hou Z. Y.;Wang J. Q.;Chen Z.;Yan W.;Tian Y. H.
60年来，人们一直在用经验公式研究沉积物声速（V）与物理性质之间的相关性，发现很难准确预测V。随机森林（RF）是一门科学学科，也是一种数据分析方法，可以自动构建分析模型。本文介绍了RF算法在钒预测和沉积物分类中的应用。这些数据库来自以前在南中国海北方收集的数据。本研究的目的是建立一个预测模型的基础上RF使用多个物理特性（平均粒径，孔隙度，湿体积密度，和水含量）。与经验公式相比，RF速度的平均误差仅为0.95%，范围为0.03%至2.73%，表明RF算法提高了V预测的准确性。我们还使用平均减少杂质重要性来评估变量的重要性，发现预测模型中最重要的特征是平均晶粒尺寸。我们还使用RF作为一个潜在的有用的工具，沉积物分类。分类模型在数据集中的准确率高达75%。沉积物的物理性质、沉积环境和沉积物来源等多种因素影响着沉积物的地声特性。下一步的目标是利用多个特征来改进模型，进一步提高声速预测和沉积物分类的准确性。
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.
登录
查看更多内容
影响因子：
2.9
作者：
M. Endler;R. Endler;J. Wunderlich;Bernd Bobertz;T. Leipe;M. Moros;J. Jensen;H. Arz
通讯作者：
M. Endler;R. Endler;J. Wunderlich;Bernd Bobertz;T. Leipe;M. Moros;J. Jensen;H. Arz
DOI：
10.1007/978-1-4684-0838-6_18
发表时间：
1974
期刊：
--
影响因子：
--
作者：
R. S. Anderson
通讯作者：
R. S. Anderson
影响因子：
2.1
作者：
T. Orsi;D. A. Dunn
通讯作者：
T. Orsi;D. A. Dunn
影响因子：
1.8
作者：
Archer, Kelfie J.;Kirnes, Ryan V.
通讯作者：
Kirnes, Ryan V.
影响因子：
2.2
作者：
Z. Hou;Changsheng Guo;Jingqiang Wang;Wenjing Chen;Tiegang Li;Yanxin Zhang;Yongtao Fu
通讯作者：
Z. Hou;Changsheng Guo;Jingqiang Wang;Wenjing Chen;Tiegang Li;Yanxin Zhang;Yongtao Fu