View in EDS

Prediction of in situ seafloor sediment sound speed with machine learning.

Saved in:
Bibliographic Details
Title: Prediction of in situ seafloor sediment sound speed with machine learning.
Authors: Chen, Mujun1,2,3 (AUTHOR), Zhang, Linqing2,3 (AUTHOR), Hu, Xinfeng2,3,4 (AUTHOR), Meng, Xiangmei2,3 (AUTHOR), Kan, Guangming2,3,4,5 (AUTHOR) kgming135@fio.org.cn, Tong, Siyou1 (AUTHOR) tsy@ouc.edu.cn, Wang, Jingqiang2,3,5 (AUTHOR), Li, Guanbao2,3,5 (AUTHOR), Liu, Baohua5 (AUTHOR), Hua, Qingfeng2,3,5 (AUTHOR), Wu, Siqi2,3,4 (AUTHOR), Zhang, Xiaobo6 (AUTHOR)
Source: Journal of Oceanology & Limnology. May2026, Vol. 44 Issue 3, p963-977. 15p.
Subject Terms: *Machine learning, *Composition of sediments, *Ocean bottom, *Ensemble learning, *Optimization algorithms, *Physical acoustics, *Marine sediments
Geographic Terms: East China Sea
Abstract: The acoustic properties of seafloor sediments are crucial for accurate acoustic field prediction, seafloor resource exploration, and marine disaster prevention. However, traditional prediction equations, often based on laboratory-measured sound speeds, suffer from low precision and discrepancies with in situ measurements. To address these issues, we employed eXtreme Gradient Boosting (XGBoost) machine learning algorithms to develop high-precision in situ sound speed prediction models for seafloor sediments. The models were constructed using in situ sound speed and sediment physical property data (density, water content, porosity, median grain size, and grain group content) from 48 sites in the East China Sea shelf. Through feature parameter reduction and hyperparameter optimization, the optimal XGBoost model achieves training and validation R2 values of 0.989 and 0.977, respectively, having hyperparameters set at n_estimators=49 and max_depth=6. Compared to other machine learning models and empirical equations, the XGBoost model based on density, water content, sand content, and median grain size exhibited the lowest mean absolute error (MAE) and mean absolute percentage error (MAPE) at 5.603 m/s and 0.366%, respectively. This represents significant improvements over existing models, with MAE reductions ranging 2.165–118.903 m/s and MAPE reductions 0.137%–7.657%. This study thus provides an innovative and highly accurate method for predicting the in situ sound speed of seafloor sediments. [ABSTRACT FROM AUTHOR]
Database: Energy & Power Source
FullText Text:
  Availability: 0
Header DbId: enr
DbLabel: Energy & Power Source
An: 195072602
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Prediction of in situ seafloor sediment sound speed with machine learning.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Chen%2C+Mujun%22">Chen, Mujun</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Linqing%22">Zhang, Linqing</searchLink><relatesTo>2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Hu%2C+Xinfeng%22">Hu, Xinfeng</searchLink><relatesTo>2,3,4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Meng%2C+Xiangmei%22">Meng, Xiangmei</searchLink><relatesTo>2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Kan%2C+Guangming%22">Kan, Guangming</searchLink><relatesTo>2,3,4,5</relatesTo> (AUTHOR)<i> kgming135@fio.org.cn</i><br /><searchLink fieldCode="AR" term="%22Tong%2C+Siyou%22">Tong, Siyou</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> tsy@ouc.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Wang%2C+Jingqiang%22">Wang, Jingqiang</searchLink><relatesTo>2,3,5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Guanbao%22">Li, Guanbao</searchLink><relatesTo>2,3,5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liu%2C+Baohua%22">Liu, Baohua</searchLink><relatesTo>5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Hua%2C+Qingfeng%22">Hua, Qingfeng</searchLink><relatesTo>2,3,5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wu%2C+Siqi%22">Wu, Siqi</searchLink><relatesTo>2,3,4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Xiaobo%22">Zhang, Xiaobo</searchLink><relatesTo>6</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+Oceanology+%26+Limnology%22">Journal of Oceanology & Limnology</searchLink>. May2026, Vol. 44 Issue 3, p963-977. 15p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br />*<searchLink fieldCode="DE" term="%22Composition+of+sediments%22">Composition of sediments</searchLink><br />*<searchLink fieldCode="DE" term="%22Ocean+bottom%22">Ocean bottom</searchLink><br />*<searchLink fieldCode="DE" term="%22Ensemble+learning%22">Ensemble learning</searchLink><br />*<searchLink fieldCode="DE" term="%22Optimization+algorithms%22">Optimization algorithms</searchLink><br />*<searchLink fieldCode="DE" term="%22Physical+acoustics%22">Physical acoustics</searchLink><br />*<searchLink fieldCode="DE" term="%22Marine+sediments%22">Marine sediments</searchLink>
– Name: SubjectGeographic
  Label: Geographic Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22East+China+Sea%22">East China Sea</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The acoustic properties of seafloor sediments are crucial for accurate acoustic field prediction, seafloor resource exploration, and marine disaster prevention. However, traditional prediction equations, often based on laboratory-measured sound speeds, suffer from low precision and discrepancies with in situ measurements. To address these issues, we employed eXtreme Gradient Boosting (XGBoost) machine learning algorithms to develop high-precision in situ sound speed prediction models for seafloor sediments. The models were constructed using in situ sound speed and sediment physical property data (density, water content, porosity, median grain size, and grain group content) from 48 sites in the East China Sea shelf. Through feature parameter reduction and hyperparameter optimization, the optimal XGBoost model achieves training and validation R2 values of 0.989 and 0.977, respectively, having hyperparameters set at n_estimators=49 and max_depth=6. Compared to other machine learning models and empirical equations, the XGBoost model based on density, water content, sand content, and median grain size exhibited the lowest mean absolute error (MAE) and mean absolute percentage error (MAPE) at 5.603 m/s and 0.366%, respectively. This represents significant improvements over existing models, with MAE reductions ranging 2.165–118.903 m/s and MAPE reductions 0.137%–7.657%. This study thus provides an innovative and highly accurate method for predicting the in situ sound speed of seafloor sediments. [ABSTRACT FROM AUTHOR]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=195072602
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s00343-025-5119-8
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 15
        StartPage: 963
    Subjects:
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Composition of sediments
        Type: general
      – SubjectFull: Ocean bottom
        Type: general
      – SubjectFull: Ensemble learning
        Type: general
      – SubjectFull: Optimization algorithms
        Type: general
      – SubjectFull: Physical acoustics
        Type: general
      – SubjectFull: Marine sediments
        Type: general
      – SubjectFull: East China Sea
        Type: general
    Titles:
      – TitleFull: Prediction of in situ seafloor sediment sound speed with machine learning.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Chen, Mujun
      – PersonEntity:
          Name:
            NameFull: Zhang, Linqing
      – PersonEntity:
          Name:
            NameFull: Hu, Xinfeng
      – PersonEntity:
          Name:
            NameFull: Meng, Xiangmei
      – PersonEntity:
          Name:
            NameFull: Kan, Guangming
      – PersonEntity:
          Name:
            NameFull: Tong, Siyou
      – PersonEntity:
          Name:
            NameFull: Wang, Jingqiang
      – PersonEntity:
          Name:
            NameFull: Li, Guanbao
      – PersonEntity:
          Name:
            NameFull: Liu, Baohua
      – PersonEntity:
          Name:
            NameFull: Hua, Qingfeng
      – PersonEntity:
          Name:
            NameFull: Wu, Siqi
      – PersonEntity:
          Name:
            NameFull: Zhang, Xiaobo
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 05
              Text: May2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 20965508
          Numbering:
            – Type: volume
              Value: 44
            – Type: issue
              Value: 3
          Titles:
            – TitleFull: Journal of Oceanology & Limnology
              Type: main
ResultId 1