Machine learning analysis of polymetallic nodules and cobalt-rich ferromanganese crusts distribution: A case study from the 16°30′N seamounts region of the Kyushu-Palau Ridge

IF 2.4 3区地球科学 Q2 OCEANOGRAPHY

Deep-Sea Research Part I-Oceanographic Research Papers Pub Date : 2025-12-01 Epub Date: 2025-10-30 DOI:10.1016/j.dsr.2025.104620

Panfeng Li , Bangqi Hu , Wei Huang , Kai Lu , Gang Hu , Yuan Yang , Jingtao Zhao , Xue Ding , Weiyu Song , Jing Kan , Fuyu Wu

{"title":"Machine learning analysis of polymetallic nodules and cobalt-rich ferromanganese crusts distribution: A case study from the 16°30′N seamounts region of the Kyushu-Palau Ridge","authors":"Panfeng Li , Bangqi Hu , Wei Huang , Kai Lu , Gang Hu , Yuan Yang , Jingtao Zhao , Xue Ding , Weiyu Song , Jing Kan , Fuyu Wu","doi":"10.1016/j.dsr.2025.104620","DOIUrl":null,"url":null,"abstract":"<div><div>The seafloor is a treasure trove of mineral resources, including polymetallic nodules (PMNs) and cobalt-rich ferromanganese crusts (CFCs). However, the complex seafloor terrain and the typical depths of 3000–6000 m at which these deposits are found pose significant challenges for conventional geological sampling methods, which tend to be both inefficient and costly. The Multibeam Echo Sounder (MBES) stands out for its ability to emit multiple narrow beams and cover a broad scanning area, thereby delivering high precision, efficiency, and comprehensive coverage in marine mapping. This system is adept at simultaneously capturing multibeam bathymetry (MB) and multibeam backscatter intensity (MBI) data, which significantly aids in a more nuanced understanding of seabed composition and sedimentation dynamics. By integrating MB with sampling data, one can discern seabed characteristics, thus substantially enhancing the efficiency and selectivity of exploration efforts. Despite the successful deployment of various cutting-edge acoustic technologies for the detection of seabed substrates, most research has focused on mapping PMNs and CFCs occurrences from MBI data. Moreover, previous studies typically employed a single classification model and did not incorporate multi-model comparisons or rigorous validation techniques. In our study, we utilized MB and MBI data derived from the EM302 system, a permanent fixture on the R/V No. 9 Hai Yang Di Zhi. We also considered topographic variables such as slope, slope of slope (SOS), and Bathymetric Position Index (BPI), calculated from the MB. These were combined with geological sampling to identify the type of seafloor. Utilizing this comprehensive dataset, we developed a supervised machine learning model to assess the spatial distribution of PMNs and CFCs in the 16°30′N seamounts region of the Kyushu-Palau Ridge (KPR).</div></div>","PeriodicalId":51009,"journal":{"name":"Deep-Sea Research Part I-Oceanographic Research Papers","volume":"226 ","pages":"Article 104620"},"PeriodicalIF":2.4000,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Deep-Sea Research Part I-Oceanographic Research Papers","FirstCategoryId":"89","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0967063725001785","RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/10/30 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"OCEANOGRAPHY","Score":null,"Total":0}

引用次数: 0

Abstract

The seafloor is a treasure trove of mineral resources, including polymetallic nodules (PMNs) and cobalt-rich ferromanganese crusts (CFCs). However, the complex seafloor terrain and the typical depths of 3000–6000 m at which these deposits are found pose significant challenges for conventional geological sampling methods, which tend to be both inefficient and costly. The Multibeam Echo Sounder (MBES) stands out for its ability to emit multiple narrow beams and cover a broad scanning area, thereby delivering high precision, efficiency, and comprehensive coverage in marine mapping. This system is adept at simultaneously capturing multibeam bathymetry (MB) and multibeam backscatter intensity (MBI) data, which significantly aids in a more nuanced understanding of seabed composition and sedimentation dynamics. By integrating MB with sampling data, one can discern seabed characteristics, thus substantially enhancing the efficiency and selectivity of exploration efforts. Despite the successful deployment of various cutting-edge acoustic technologies for the detection of seabed substrates, most research has focused on mapping PMNs and CFCs occurrences from MBI data. Moreover, previous studies typically employed a single classification model and did not incorporate multi-model comparisons or rigorous validation techniques. In our study, we utilized MB and MBI data derived from the EM302 system, a permanent fixture on the R/V No. 9 Hai Yang Di Zhi. We also considered topographic variables such as slope, slope of slope (SOS), and Bathymetric Position Index (BPI), calculated from the MB. These were combined with geological sampling to identify the type of seafloor. Utilizing this comprehensive dataset, we developed a supervised machine learning model to assess the spatial distribution of PMNs and CFCs in the 16°30′N seamounts region of the Kyushu-Palau Ridge (KPR).

查看原文本刊更多论文

多金属结核和富钴锰铁结壳分布的机器学习分析——以九州-帕劳海岭16°30′n海山地区为例

海底是矿产资源的宝库，包括多金属结核（pmn）和富钴锰铁结壳（CFCs）。然而，复杂的海底地形和发现这些矿床的典型深度为3000-6000米，这对传统的地质采样方法构成了重大挑战，这些方法往往既低效又昂贵。多波束回声探测仪（MBES）能够发射多个窄波束并覆盖广泛的扫描区域，从而在海洋测绘中提供高精度、高效率和全面的覆盖范围。该系统擅长同时捕获多波束测深（MB）和多波束后向散射强度（MBI）数据，这有助于更细致地了解海底成分和沉积动力学。通过将MB与采样数据相结合，可以识别海底特征，从而大大提高了勘探工作的效率和选择性。尽管已经成功地应用了各种尖端声学技术来探测海底基材，但大多数研究都集中在从MBI数据中绘制pmn和cfc的出现情况。此外，以往的研究通常采用单一的分类模型，没有纳入多模型比较或严格的验证技术。在我们的研究中，我们使用了来自EM302系统的MB和MBI数据，EM302系统是9号海洋地之号R/V的永久装置。我们还考虑了地形变量，如坡度、坡度的坡度（SOS）和水深位置指数（BPI），这些都是从MB计算出来的。这些变量与地质采样相结合，以确定海底的类型。利用这一综合数据集，我们开发了一个有监督的机器学习模型来评估九州-帕劳岭（KPR） 16°30′n海山地区PMNs和CFCs的空间分布。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Deep-Sea Research Part I-Oceanographic Research Papers 地学-海洋学

CiteScore

4.60

自引率

4.20%

发文量

144

审稿时长

18.3 weeks

期刊介绍： Deep-Sea Research Part I: Oceanographic Research Papers is devoted to the publication of the results of original scientific research, including theoretical work of evident oceanographic applicability; and the solution of instrumental or methodological problems with evidence of successful use. The journal is distinguished by its interdisciplinary nature and its breadth, covering the geological, physical, chemical and biological aspects of the ocean and its boundaries with the sea floor and the atmosphere. In addition to regular "Research Papers" and "Instruments and Methods" papers, briefer communications may be published as "Notes". Supplemental matter, such as extensive data tables or graphs and multimedia content, may be published as electronic appendices.