Inertinite in coal and its geoenvironmental significance: Insights from AI and big data analysis

被引:0
|
作者
Longyi SHAO [1 ]
Jiamin ZHOU [1 ]
Timothy P.JONES [2 ]
Fanghui HUA [1 ]
Xiaotao XU [3 ]
Zhiming YAN [4 ]
Haihai HOU [5 ]
Dongdong WANG [6 ]
Jing LU [1 ]
机构
[1] State Key Laboratory for Fine Exploration and Intelligent Development of Coal Resources and College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing)
[2] School of Earth and Environmental Sciences, Cardiff University
[3] General Prospecting Institute of China National Administration of Coal Geology
[4] Institute of Architectural Engineering, Weifang University
[5] College of Mining, Liaoning Technical University
[6] College of Earth Science and Engineering, Shandong University of Science and Technology
基金
中国国家自然科学基金;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论]; TP311.13 []; P532 [古气候学];
学科分类号
070903 ; 081104 ; 0812 ; 0835 ; 1201 ; 1405 ;
摘要
Inertinite, as an important and abundant maceral group in coal, is critical for the study of palaeowildfires and their roles in the Earth’s ecosystems. Recently, there has been a significant amount of research on the relationship between palaeowildfire, palaeoclimate change and palaeovegetation evolution based on inertinite data. The reflectance of fusinite and semifusinite has been used to estimate the combustion temperature and type of palaeowildfires, and then to evaluate the combustion characteristics of different types of palaeowildfires. The relative abundance of inertinite can be used to estimate the atmospheric oxygen contents. The rapid development of artificial intelligence(AI) and online tools to search scientific databases has presented an opportunity for us to find, collect, arrange, and analyse data from the earliest to latest publications on inertinite. The data extraction tool Deep Shovel is used to collect and analyse global inertinite data from the Silurian to the Neogene. The software programs such as Gplates, ArcGIS pro and Tableau are then applied to model the relative abundance of inertinite over geological time, which can be correlated with other parameters such as atmospheric oxygen contents, plant evolution and palaeoclimate changes. The distribution of inertinite in coals varied over different geological periods, being typified by the “high inertinite content-high atmospheric oxygen level” period in the Permian and the “low inertinite content-low atmospheric oxygen level” period in the Cenozoic. This study has proposed a possible model of the positive and negative feedbacks between inertinite characteristics and palaeoenvironmental factors, and has revealed the exceptional role of inertinite in palaeoenvironmental studies. Future research on inertinite will be focused on the integrated study of organic petrology and organic geochemistry of inertinite, the big data-driven research on the temporal and spatial distribution of the global inertinite, the exploration of the functions of palaeowildfires in the Earth systems in different climatic backgrounds, and the study of modern wildfires to better predict the future frequency and intensity of wildfires due to climate changes.
引用
收藏
页码:1779 / 1801
页数:23
相关论文
共 50 条
  • [21] Global reaction to the recent outbreaks of Zika virus: Insights from a Big Data analysis
    Bragazzi, Nicola Luigi
    Alicino, Cristiano
    Trucchi, Cecilia
    Paganino, Chiara
    Barberis, Ilaria
    Martini, Mariano
    Sticchi, Laura
    Trinka, Eugen
    Brigo, Francesco
    Ansaldi, Filippo
    Icardi, Giancarlo
    Orsi, Andrea
    PLOS ONE, 2017, 12 (09):
  • [22] From big data to big insights: statistical and bioinformatic approaches for exploring the lipidome
    Jessie R. Chappel
    Kaylie I. Kirkwood-Donelson
    David M. Reif
    Erin S. Baker
    Analytical and Bioanalytical Chemistry, 2024, 416 : 2189 - 2202
  • [23] From big data to big insights: statistical and bioinformatic approaches for exploring the lipidome
    Chappel, Jessie R.
    Kirkwood-Donelson, Kaylie I.
    Reif, David M.
    Baker, Erin S.
    ANALYTICAL AND BIOANALYTICAL CHEMISTRY, 2024, 416 (09) : 2189 - 2202
  • [24] Potential for Big Data Analysis Using AI in the Field of Clinical Pharmacy
    Kiryu, Yoshihiro
    YAKUGAKU ZASSHI-JOURNAL OF THE PHARMACEUTICAL SOCIETY OF JAPAN, 2021, 141 (02): : 179 - 185
  • [25] Big Data Analysis, AI, and Visualization Workshop: Road Mapping Infrastructures for Artificial Intelligence Supporting Advanced Visual Big Data Analysis
    Reis, Thoralf
    Bornschlegl, Marco X.
    Hemmje, Matthias L.
    PROCEEDINGS OF THE WORKING CONFERENCE ON ADVANCED VISUAL INTERFACES AVI 2020, 2020,
  • [26] The Chemical Space of Terpenes: Insights from Data Science and AI
    Hosseini, Morteza
    Pereira, David M.
    PHARMACEUTICALS, 2023, 16 (02)
  • [27] Intelligent Data Analysis and Its Challenges in Big Data Environment
    Kong, Weichang
    Wu, Qidi
    Li, Li
    Qiao, Fei
    2014 IEEE INTERNATIONAL CONFERENCE ON SYSTEM SCIENCE AND ENGINEERING (ICSSE), 2014, : 108 - 113
  • [28] Discovering AI adoption patterns from big academic graph data
    Kim, Sang Yoon
    Lee, Won Kyung
    Jee, Su Jung
    Sohn, So Young
    SCIENTOMETRICS, 2025, 130 (02) : 809 - 831
  • [29] Editorial: Evolution from AI, IoT and Big Data Analytics to Metaverse
    MengChu Zhou
    IEEE/CAAJournalofAutomaticaSinica, 2022, 9 (12) : 2041 - 2042
  • [30] On Big Data Driving Manufacturing from "Internet Plus" to "AI Plus"
    Yao X.
    Lei Y.
    Ge D.
    Ye J.
    Zhongguo Jixie Gongcheng/China Mechanical Engineering, 2019, 30 (02): : 134 - 142