A Deep Learning Approach of Artificial Neural Network With Attention Mechanism to Predicting Marine Biogeochemistry Data

IF 3.7 3区 环境科学与生态学 Q2 ENVIRONMENTAL SCIENCES
Mingzhi Liu, Yipeng Wang, Guoqiang Zhong, Yongxin Liu, Xiaoqing Liu, Jifan Shi, Yangli Che, Rui Bao
{"title":"A Deep Learning Approach of Artificial Neural Network With Attention Mechanism to Predicting Marine Biogeochemistry Data","authors":"Mingzhi Liu,&nbsp;Yipeng Wang,&nbsp;Guoqiang Zhong,&nbsp;Yongxin Liu,&nbsp;Xiaoqing Liu,&nbsp;Jifan Shi,&nbsp;Yangli Che,&nbsp;Rui Bao","doi":"10.1029/2024JG008386","DOIUrl":null,"url":null,"abstract":"<p>Predicting marine biogeochemical data is an effective method to solve the problem of marine data-scarcity and provides data support for fundamental research in marine science. Machine learning techniques are commonly used to improve the stability and accuracy of predicting biogeochemistry data. However, current methods based on Random Forest (RF) and Artificial Neural network (ANN) often struggle to effectively capture the intricate features of ocean data, resulting in suboptimal prediction accuracy. In this study, we develop a novel deep learning method called artificial neural network with attention mechanism (ANN-att) for predicting marine biogeochemistry data. We compare and evaluate the performance of RF, ANN, and ANN-att based on two widely used ocean data sets in marine biogeochemistry: GLODAP v2.2022 and MOSAIC 2.0. Our results show that the prediction accuracy of the ANN-att method is higher than other methods by 6% for GLODAP v2.2022 and 30% for MOSAIC v.2.0. Additionally, the prediction maps of surface ocean dissolved oxygen and Δ<sup>14</sup>C in the West Pacific demonstrate that ANN-att has a significant advantage in predicting marine biogeochemistry data with stronger nonlinear characteristics.</p>","PeriodicalId":16003,"journal":{"name":"Journal of Geophysical Research: Biogeosciences","volume":"130 3","pages":""},"PeriodicalIF":3.7000,"publicationDate":"2025-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Geophysical Research: Biogeosciences","FirstCategoryId":"93","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1029/2024JG008386","RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
引用次数: 0

Abstract

Predicting marine biogeochemical data is an effective method to solve the problem of marine data-scarcity and provides data support for fundamental research in marine science. Machine learning techniques are commonly used to improve the stability and accuracy of predicting biogeochemistry data. However, current methods based on Random Forest (RF) and Artificial Neural network (ANN) often struggle to effectively capture the intricate features of ocean data, resulting in suboptimal prediction accuracy. In this study, we develop a novel deep learning method called artificial neural network with attention mechanism (ANN-att) for predicting marine biogeochemistry data. We compare and evaluate the performance of RF, ANN, and ANN-att based on two widely used ocean data sets in marine biogeochemistry: GLODAP v2.2022 and MOSAIC 2.0. Our results show that the prediction accuracy of the ANN-att method is higher than other methods by 6% for GLODAP v2.2022 and 30% for MOSAIC v.2.0. Additionally, the prediction maps of surface ocean dissolved oxygen and Δ14C in the West Pacific demonstrate that ANN-att has a significant advantage in predicting marine biogeochemistry data with stronger nonlinear characteristics.

Abstract Image

基于注意力机制的人工神经网络深度学习方法在海洋生物地球化学数据预测中的应用
海洋生物地球化学数据预测是解决海洋数据稀缺问题的有效手段,为海洋科学基础研究提供数据支撑。机器学习技术通常用于提高生物地球化学数据预测的稳定性和准确性。然而,目前基于随机森林(RF)和人工神经网络(ANN)的方法往往难以有效捕获海洋数据的复杂特征,导致预测精度不理想。在这项研究中,我们开发了一种新的深度学习方法,称为具有注意机制的人工神经网络(ANN-att),用于预测海洋生物地球化学数据。基于GLODAP v2.2022和MOSAIC 2.0这两个广泛使用的海洋生物地球化学数据集,我们比较和评估了RF、ANN和ANN-att的性能。结果表明,对于GLODAP v2.2022和MOSAIC v.2.0, ANN-att方法的预测精度分别比其他方法高6%和30%。此外,西太平洋表层海洋溶解氧和Δ14C预测图表明,ANN-att在预测非线性特征较强的海洋生物地球化学数据方面具有显著优势。
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
Journal of Geophysical Research: Biogeosciences
Journal of Geophysical Research: Biogeosciences Earth and Planetary Sciences-Paleontology
CiteScore
6.60
自引率
5.40%
发文量
242
期刊介绍: JGR-Biogeosciences focuses on biogeosciences of the Earth system in the past, present, and future and the extension of this research to planetary studies. The emerging field of biogeosciences spans the intellectual interface between biology and the geosciences and attempts to understand the functions of the Earth system across multiple spatial and temporal scales. Studies in biogeosciences may use multiple lines of evidence drawn from diverse fields to gain a holistic understanding of terrestrial, freshwater, and marine ecosystems and extreme environments. Specific topics within the scope of the section include process-based theoretical, experimental, and field studies of biogeochemistry, biogeophysics, atmosphere-, land-, and ocean-ecosystem interactions, biomineralization, life in extreme environments, astrobiology, microbial processes, geomicrobiology, and evolutionary geobiology
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信