基于机器学习的海陆过渡环境中陆源有机质分布预测模型——从沉积模拟实验到地质应用【水槽沉积模拟实验专辑】

邵俊哲; 李阳; 吴楠; 冯文杰; 魏薇

doi:10.14027/j.issn.1000-0550.2024.056

ISSN 1000-0550 CN 62-1038/P

高级搜索

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于机器学习的海陆过渡环境中陆源有机质分布预测模型——从沉积模拟实验到地质应用【水槽沉积模拟实验专辑】

邵俊哲, 李阳, 吴楠, 冯文杰, 魏薇

文章导航 > 沉积学报 > 2024 > 优先发表

邵俊哲, 李阳, 吴楠, 冯文杰, 魏薇. 基于机器学习的海陆过渡环境中陆源有机质分布预测模型——从沉积模拟实验到地质应用【水槽沉积模拟实验专辑】[J]. 沉积学报. doi: 10.14027/j.issn.1000-0550.2024.056

引用本文:

Machine Learning Based Model for Predicting the Distribution of Terrestrial Organic Matter in Marine-terrestrial Transitional Environmen—From Sedimentary Simulation Experiments to Geological Applications[J]. Acta Sedimentologica Sinica. doi: 10.14027/j.issn.1000-0550.2024.056

Citation:

Machine Learning Based Model for Predicting the Distribution of Terrestrial Organic Matter in Marine-terrestrial Transitional Environmen—From Sedimentary Simulation Experiments to Geological Applications[J]. Acta Sedimentologica Sinica. doi: 10.14027/j.issn.1000-0550.2024.056

引用本文:

Citation:

Machine Learning Based Model for Predicting the Distribution of Terrestrial Organic Matter in Marine-terrestrial Transitional Environmen—From Sedimentary Simulation Experiments to Geological Applications[J]. Acta Sedimentologica Sinica. doi: 10.14027/j.issn.1000-0550.2024.056

基于机器学习的海陆过渡环境中陆源有机质分布预测模型——从沉积模拟实验到地质应用【水槽沉积模拟实验专辑】

doi: 10.14027/j.issn.1000-0550.2024.056

1.
长江大学地球科学学院
2.
长江大学资源与环境学院

基金项目: 其它-海洋分散有机质沉积聚集模拟实验(CCL2021RCPS0231RSN)

计量

文章访问数: 183
HTML全文浏览量: 36
PDF下载量: 33
被引次数: 0

Machine Learning Based Model for Predicting the Distribution of Terrestrial Organic Matter in Marine-terrestrial Transitional Environmen—From Sedimentary Simulation Experiments to Geological Applications

摘要

摘要: 陆源海相烃源岩是我国多个近海盆地的主力烃源岩，其差异性展布特征制约着烃源岩的分布预测精度和油气勘探成效。而陆源有机质的搬运沉积过程决定着陆源海相烃源岩质量和分布。运用水槽沉积模拟结合三维激光扫描技术，从“正演”的角度动态记录并定量表征不同水体盐度条件下陆源分散有机质的搬运过程并运用机器学习算法建立TOC预测模型。结果表明，海陆过渡环境中的陆源有机质主要富集在三角洲前缘和前三角洲沉积相带内，随着搬运距离的增大，海陆过渡环境中的陆源有机质丰度呈现先增大后减小的趋势。在盐絮凝作用影响下，咸水环境中陆源有机质搬运距离更靠近物源区，沉积厚度更大。基于三种深度学习算法建立了实验条件下的TOC预测模型，最终优选出基于随机森林算法的预测模型为最优模型。将实验条件下的TOC预测模型与地质条件相结合，完成了崖南凹陷崖城组三角洲内烃源岩的TOC预测。结果显示，崖南凹陷陆源有机质搬运距离可达50 km，在距离物源区31 km左右处有机质富集程度最高。
- 海陆过渡相 /
- 陆源有机质 /
- 机器学习 /
- 沉积模拟 /
- 预测模型
Abstract: Marine-terrestrial transitional source rocks are the main source rocks in several offshore basins in China, and their differential distribution characteristics restrict the prediction accuracy of source rocks and the effectiveness of oil and gas exploration. And the transport and sedimentation process of terrestrial organic matter determines the quality and distribution of source rock in marine-terrestrial transitional environment. Using a combination of flume sedimentary simulation and 3D laser scanning technology, the dynamic recording and quantitative characterization of the transport process of terrestrial dispersed organic matter under different water salinity conditions are carried out from the perspective of forward modeling. Machine learning algorithms are used to establish a TOC prediction model. The results show that terrestrial organic matter in the marine-terrestrial transitional environment is mainly enriched in the delta front and prodelta. As the transportation distance increases, the abundance of terrestrial organic matter shows a trend of first increasing and then decreasing. Under the influence of salt flocculation, the transportation distance of terrestrial organic matter in saltwater environment is closer to the source area, and the sediment thickness is larger. A TOC prediction model was established under experimental conditions based on three deep learning algorithms, and ultimately selects the prediction model based on random forest algorithm with outlier removal and experience based sedimentary facies assignment as input features as the optimal model. The TOC prediction model under experimental conditions is combined with geological conditions to complete the TOC prediction of source rocks in the Yacheng Formation of the Yanan depression. The results show that the transportation distance of terrestrial organic matter in the Yanan Depression can reach 50 km, and the highest degree of organic matter enrichment occurs at a distance of about 31 km from the source area.
- Marine-terrestrial transitional environment /
- Terrestrial organic matter /
- Machine learing /
- Sedimentary simulation /
- Prediction model

HTML全文

[1]	于乐丹, 彭军, 许天宇, 韩浩东, 杨一茗. 陆相断陷咸化湖盆细粒沉积地层有机质富集特征及控制因素分析 . 沉积学报, doi: 10.14027/j.issn.1000-0550.2022.096
[2]	聂万才, 张廷山, 王铭伟, 吴玟, 谭秀成. 海陆过渡相煤系页岩孔隙分形特征及影响因素 . 沉积学报, doi: 10.14027/j.issn.1000-0550.2022.078
[3]	刘海, 徐耀辉, 李阳, 黄凌松, 吕奇奇, 刘忠保. 海陆过渡相三角洲沉积体系陆源有机质沉积特征及其影响因素的模拟实验研究 . 沉积学报, doi: 10.14027/j.issn.1000-0550.2023.047
[4]	刘彦锋, 段太忠, 龚伟, 廉培庆, 张文彪, 黄渊. 基于深度学习的地层沉积正演模拟代理模型构建与应用 . 沉积学报, doi: 10.14027/j.issn.1000-0550.2021.152
[5]	谷一凡, 蔡光银, 李树新, 蒋裕强, 邱振, 孙莎莎, 付永红. 不同岩相海陆过渡相页岩孔隙结构及控制因素 . 沉积学报, doi: 10.14027/j.issn.1000-0550.2021.070
[6]	刘翰林, 邹才能, 邱振, 尹帅, 杨智, 吴松涛, 张国生, 陈艳鹏, 马锋, 李士祥, 张岩. 陆相黑色页岩沉积环境及有机质富集机制 . 沉积学报, doi: 10.14027/j.issn.1000-0550.2023.118
[7]	王昕, 魏思源, 吕奇奇, 代榕, 呼焕, 毕宇航, 张丽雯, 梁岩, 张建坤. 基于物理模拟的三角洲前缘横向砂坝发育过程及形成机理 . 沉积学报, doi: 10.14027/j.issn.1000-0550.2021.150
[8]	屈童, 高岗, 徐新德, 黄志龙, 甘军, 梁刚, 游君君. 三角洲—浅海沉积体系陆源有机质沉积模拟实验研究 . 沉积学报, doi: 10.14027/j.issn.1000-0550.2021.085
[9]	张宇航, 时保宏, 张曰静, 石好果, 文雯, 张杨. 机器学习方法在浅层滩坝相薄储层孔隙度预测中的应用 . 沉积学报, doi: 10.14027/j.issn.1000-0550.2022.100
[10]	蔡光银, 蒋裕强, 李星涛, 孙莎莎, 付永红, 谷一凡, 王占磊, 季春海. 海陆过渡相与海相富有机质页岩储层特征差异 . 沉积学报, doi: 10.14027/j.issn.1000-0550.2021.069
[11]	邢淑晓, 窦衍光, 赵京涛, 蔡峰, 李清, 邹亮, 王利波. 17. 3 ka以来冲绳海槽中南部有机质来源 . 沉积学报, doi: 10.14027/j.issn.1000-0550.2020.117
[12]	彭思钟, 刘德勋, 张磊夫, 邱振, 王以城, 封从军, 孙萌思. 鄂尔多斯盆地东缘大宁—吉县地区山西组页岩岩相与沉积相特征 . 沉积学报, doi: 10.14027/j.issn.1000-0550.2021.058
[13]	董大忠, 邱振, 张磊夫, 李树新, 张琴, 李星涛, 张素荣, 刘翰林, 王玉满. 海陆过渡相页岩气层系沉积研究进展与页岩气新发现 . 沉积学报, doi: 10.14027/j.issn.1000-0550.2021.002
[14]	屈童, 高岗, 徐新德, 刘凤妍. 三角洲—浅海沉积体系陆源有机质分布控制因素 . 沉积学报, doi: 10.14027/j.issn.1000-0550.2019.057
[15]	朱筱敏, 葛家旺, 赵宏超, 袁立忠, 刘军. 陆架边缘三角洲研究进展及实例分析 . 沉积学报, doi: 10.14027/j.cnki.cjxb.2017.05.007
[16]	张慧芳, 吴欣松, 王斌, 段云江, 屈洋, 陈德飞. 陆相湖盆沉积有机质富集机理研究进展 . 沉积学报, doi: 10.14027/j.cnki.cjxb.2016.03.004
[17]	. 成熟度对陆相烃源岩可溶有机质Pr/Ph比值的影响 . 沉积学报,
[18]	赵林, 贾蓉芬, 刘德汉, 秦建中, 张文龙. 古生界海陆过渡相黑色泥质岩系显微组分特征及生气潜力评价 . 沉积学报,
[19]	赖志云, 周维. 舌状三角洲和鸟足状三角洲形成及演变的沉积模拟实验 . 沉积学报,
[20]	曹耀华, 赖志云, 刘怀波, 张昌民. 沉积模拟实验的历史现状及发展趋势 . 沉积学报,

施引文献

资源附件(1)

实验条件.xlsx

访问统计

点击查看大图

计量

文章访问数: 183
HTML全文浏览量: 36
PDF下载量: 33
被引次数: 0

基于机器学习的海陆过渡环境中陆源有机质分布预测模型——从沉积模拟实验到地质应用【水槽沉积模拟实验专辑】

doi: 10.14027/j.issn.1000-0550.2024.056

1. 长江大学地球科学学院

2. 长江大学资源与环境学院

基金项目: 其它-海洋分散有机质沉积聚集模拟实验(CCL2021RCPS0231RSN)

收稿日期: 2024-02-27
网络出版日期: 2024-06-21

关键词:

摘要: 陆源海相烃源岩是我国多个近海盆地的主力烃源岩，其差异性展布特征制约着烃源岩的分布预测精度和油气勘探成效。而陆源有机质的搬运沉积过程决定着陆源海相烃源岩质量和分布。运用水槽沉积模拟结合三维激光扫描技术，从“正演”的角度动态记录并定量表征不同水体盐度条件下陆源分散有机质的搬运过程并运用机器学习算法建立TOC预测模型。结果表明，海陆过渡环境中的陆源有机质主要富集在三角洲前缘和前三角洲沉积相带内，随着搬运距离的增大，海陆过渡环境中的陆源有机质丰度呈现先增大后减小的趋势。在盐絮凝作用影响下，咸水环境中陆源有机质搬运距离更靠近物源区，沉积厚度更大。基于三种深度学习算法建立了实验条件下的TOC预测模型，最终优选出基于随机森林算法的预测模型为最优模型。将实验条件下的TOC预测模型与地质条件相结合，完成了崖南凹陷崖城组三角洲内烃源岩的TOC预测。结果显示，崖南凹陷陆源有机质搬运距离可达50 km，在距离物源区31 km左右处有机质富集程度最高。

English Abstract

Machine Learning Based Model for Predicting the Distribution of Terrestrial Organic Matter in Marine-terrestrial Transitional Environmen—From Sedimentary Simulation Experiments to Geological Applications

Received Date: 2024-02-27
Available Online: 2024-06-21

Keywords:

Marine-terrestrial transitional environment /
Terrestrial organic matter /
Machine learing /
Sedimentary simulation /
Prediction model

Abstract: Marine-terrestrial transitional source rocks are the main source rocks in several offshore basins in China, and their differential distribution characteristics restrict the prediction accuracy of source rocks and the effectiveness of oil and gas exploration. And the transport and sedimentation process of terrestrial organic matter determines the quality and distribution of source rock in marine-terrestrial transitional environment. Using a combination of flume sedimentary simulation and 3D laser scanning technology, the dynamic recording and quantitative characterization of the transport process of terrestrial dispersed organic matter under different water salinity conditions are carried out from the perspective of forward modeling. Machine learning algorithms are used to establish a TOC prediction model. The results show that terrestrial organic matter in the marine-terrestrial transitional environment is mainly enriched in the delta front and prodelta. As the transportation distance increases, the abundance of terrestrial organic matter shows a trend of first increasing and then decreasing. Under the influence of salt flocculation, the transportation distance of terrestrial organic matter in saltwater environment is closer to the source area, and the sediment thickness is larger. A TOC prediction model was established under experimental conditions based on three deep learning algorithms, and ultimately selects the prediction model based on random forest algorithm with outlier removal and experience based sedimentary facies assignment as input features as the optimal model. The TOC prediction model under experimental conditions is combined with geological conditions to complete the TOC prediction of source rocks in the Yacheng Formation of the Yanan depression. The results show that the transportation distance of terrestrial organic matter in the Yanan Depression can reach 50 km, and the highest degree of organic matter enrichment occurs at a distance of about 31 km from the source area.

引用本文:

Citation:

Machine Learning Based Model for Predicting the Distribution of Terrestrial Organic Matter in Marine-terrestrial Transitional Environmen—From Sedimentary Simulation Experiments to Geological Applications[J]. Acta Sedimentologica Sinica. doi: 10.14027/j.issn.1000-0550.2024.056

全文HTML

补充材料:

实验条件.xlsx

下载: 全尺寸图片幻灯片

返回文章

用微信扫码二维码

分享至好友和朋友圈

留言板

基于机器学习的海陆过渡环境中陆源有机质分布预测模型——从沉积模拟实验到地质应用【水槽沉积模拟实验专辑】

doi: 10.14027/j.issn.1000-0550.2024.056

计量

Machine Learning Based Model for Predicting the Distribution of Terrestrial Organic Matter in Marine-terrestrial Transitional Environmen—From Sedimentary Simulation Experiments to Geological Applications

计量

目录

基于机器学习的海陆过渡环境中陆源有机质分布预测模型——从沉积模拟实验到地质应用【水槽沉积模拟实验专辑】

doi: 10.14027/j.issn.1000-0550.2024.056

1. 长江大学地球科学学院

2. 长江大学资源与环境学院

English Abstract

Machine Learning Based Model for Predicting the Distribution of Terrestrial Organic Matter in Marine-terrestrial Transitional Environmen—From Sedimentary Simulation Experiments to Geological Applications

全文HTML

目录

友情链接

期刊在线

联系我们

留言板

基于机器学习的海陆过渡环境中陆源有机质分布预测模型——从沉积模拟实验到地质应用【水槽沉积模拟实验专辑】

doi: 10.14027/j.issn.1000-0550.2024.056

计量

出版历程

Machine Learning Based Model for Predicting the Distribution of Terrestrial Organic Matter in Marine-terrestrial Transitional Environmen—From Sedimentary Simulation Experiments to Geological Applications

计量

出版历程

目录

基于机器学习的海陆过渡环境中陆源有机质分布预测模型——从沉积模拟实验到地质应用【水槽沉积模拟实验专辑】

doi: 10.14027/j.issn.1000-0550.2024.056

1. 长江大学地球科学学院 2. 长江大学资源与环境学院

English Abstract

Machine Learning Based Model for Predicting the Distribution of Terrestrial Organic Matter in Marine-terrestrial Transitional Environmen—From Sedimentary Simulation Experiments to Geological Applications

全文HTML

目录

友情链接

期刊在线

联系我们

1. 长江大学地球科学学院

2. 长江大学资源与环境学院