Machine learning for automatic slump identification from 3D seismic data at convergent plate margins

Machine learning for automatic slump identification from 3D seismic data at convergent plate margins
复制标题

机器学习可根据会聚板块边缘的 3D 地震数据自动识别坍落度

DOI:
10.1016/j.marpetgeo.2021.105290
复制
发表时间:
2021
影响因子:
4.2
通讯作者:
Tsuji Takeshi
Tsuji Takeshi
中科院分区:
地球科学2区
文献类型:
--
作者:
Ahmad Ahmad B.;Tsuji Takeshi

文献摘要

参考文献

被引文献

相似文献

板块俯冲带由于板块碰撞而引发地震并形成山脉,从而产生复杂的结构并引起大质量的下坡输送(即塌陷)。在板块俯冲带收集了大量的 3D 地震数据,可用于研究与地震和碳氢化合物聚集(即水合物和天然气藏)相关的塌陷。人工智能的发展为大数据分析(例如解释大量地震数据)提供了新技术(即关联规则学习、决策树学习和神经网络)。在这里,我们使用卷积神经网络(CNN)自动检测复杂的地质结构,例如塌陷单元。我们在南开俯冲带采集的 3D 地震数据上测试了我们的方法。在 3D 数据体中手动定义多个地震剖面中的坍落单元后,我们将信息馈送到 CNN,CNN 准确识别了坍落单元的空间分布。 CNN 模型使用真实的 3D 地震数据进行训练,直到模型训练所在区域的坍落度单元达到 90% 的分类准确率。我们进一步将南海数据训练的 CNN 模型应用于另一个板块汇聚边缘(日本东北部的 Sanriku-Oki)的 3D 地震数据,并成功识别了 Sanriku-Oki 地震体中的滑塌单元。除了坍落度识别之外,我们的 CNN 比基于地震属性的众所周知的方法更好地预测断层。在南开数据中,通过CNN识别的滑落单元分布在较少的正断层带上。这些自动解释的高精度表明,该方法可以应用于其他弧前盆地,以高空间分辨率研究地质结构(例如滑塌和断层)。
Plate subduction zones cause earthquakes and build mountain ranges due to plate collisions, which generate complex structures and induce the down-slope transport of large masses (i.e., slumps). Extensive 3D seismic data have been collected in plate subduction zones and can be used to investigate the slumps associated with earthquakes and hydrocarbon accumulations (i.e., hydrate and gas reservoirs). The development of artificial intelligence has provided new techniques (i.e., association rule learning, decision tree learning, and neural networks) for big-data analysis, such as interpreting large seismic data volumes. Here, we use a convolutional neural network (CNN) to automatically detect complex geological structures, such as slump units. We tested our method on the 3D seismic data acquired in the Nankai subduction zone. After manually defining slump units in several seismic profiles within the 3D data volume, we fed the information to the CNN, which accurately identified the spatial distribution of slump units. The CNN model was trained using real 3D seismic data until it achieved 90 % classification accuracy for slump units in the same region as the model was trained. We further applied our CNN model trained by the Nankai data to the 3D seismic data at another plate convergent margin (Sanriku-Oki in northeast Japan) and succeeded in identifying slump units in the Sanriku-Oki seismic volume. In addition to slump identification, our CNN predicted faults better than well-known methods based on seismic attributes. The slump units identified via CNN are distributed at fewer normal fault zone in the Nankai data. The high accuracy of these automatic interpretations shows that this approach can be applied to other forearc basins to investigate geological structures (e.g., slump and faults) at high spatial resolution.
DOI: 10.1186/1880-5981-66-120
发表时间: 2014
期刊: Earth, Planets and Space
影响因子: --
作者:
T. Tsuji;J. Ashi;Y. Ikeda
通讯作者: Y. Ikeda
DOI: 10.1016/j.marpetgeo.2020.104305
发表时间: 2020-06
影响因子: 4.2
作者:
Kakda Kret;T. Tsuji;Chanmaly Chhun;O. Takano
通讯作者: Kakda Kret;T. Tsuji;Chanmaly Chhun;O. Takano
为什么使用 CNN 进行地震解释?
DOI: 10.1190/segam2018-2997155.1
发表时间: 2018
期刊: SEG technical program expanded abstracts
影响因子: --
作者:
H. Di;Zhen Wang;G. AlRegib
通讯作者: G. AlRegib
SVD-Softmax:大词汇量神经网络的快速 Softmax 逼近
DOI: --
发表时间: 2017
期刊: Neural Information Processing Systems
影响因子: --
作者:
Kyuhong Shim;Minjae Lee;Iksoo Choi;Yoonho Boo;Wonyong Sung
通讯作者: Wonyong Sung
边坡稳定性的区域变异:应用于加利福尼亚州 Eel 边缘
DOI: 10.1016/s0025-3227(98)00120-0
发表时间: 1999
期刊:
影响因子: --
作者:
Homa J. Lee;J. Locat;P. Dartnell;Kenneth Israel;F. Wong
通讯作者: F. Wong