A comparison of deep machine learning and Monte Carlo methods for facies classification from seismic data

蒙特卡罗方法 马尔科夫蒙特卡洛 计算机科学 人工神经网络 算法 机器学习 人工智能 数据集 贝叶斯概率 数据挖掘 统计 数学 地质学 古生物学 构造盆地
作者
Darío Graña,Leonardo Azevedo,Mingliang Liu
出处
期刊:Geophysics [Society of Exploration Geophysicists]
卷期号:85 (4): WA41-WA52 被引量:71
标识
DOI:10.1190/geo2019-0405.1
摘要

Among the large variety of mathematical and computational methods for estimating reservoir properties such as facies and petrophysical variables from geophysical data, deep machine-learning algorithms have gained significant popularity for their ability to obtain accurate solutions for geophysical inverse problems in which the physical models are partially unknown. Solutions of classification and inversion problems are generally not unique, and uncertainty quantification studies are required to quantify the uncertainty in the model predictions and determine the precision of the results. Probabilistic methods, such as Monte Carlo approaches, provide a reliable approach for capturing the variability of the set of possible models that match the measured data. Here, we focused on the classification of facies from seismic data and benchmarked the performance of three different algorithms: recurrent neural network, Monte Carlo acceptance/rejection sampling, and Markov chain Monte Carlo. We tested and validated these approaches at the well locations by comparing classification predictions to the reference facies profile. The accuracy of the classification results is defined as the mismatch between the predictions and the log facies profile. Our study found that when the training data set of the neural network is large enough and the prior information about the transition probabilities of the facies in the Monte Carlo approach is not informative, machine-learning methods lead to more accurate solutions; however, the uncertainty of the solution might be underestimated. When some prior knowledge of the facies model is available, for example, from nearby wells, Monte Carlo methods provide solutions with similar accuracy to the neural network and allow a more robust quantification of the uncertainty, of the solution.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
治治治完成签到,获得积分10
1秒前
YanDongXu发布了新的文献求助10
3秒前
123发布了新的文献求助10
3秒前
TianlangPan完成签到,获得积分10
3秒前
njhuxs完成签到,获得积分10
4秒前
芬达完成签到 ,获得积分10
6秒前
yangminghan发布了新的文献求助10
6秒前
蜂蜜小熊完成签到 ,获得积分10
8秒前
9秒前
9秒前
9秒前
清脆的巧凡应助Dawn采纳,获得20
10秒前
10秒前
田様应助今夜不设防采纳,获得10
10秒前
华仔应助Nikko采纳,获得10
10秒前
我是老大应助Brain采纳,获得10
12秒前
星辰大海应助KKKpumc采纳,获得10
12秒前
至乐无乐完成签到 ,获得积分10
13秒前
xinglonglin完成签到,获得积分10
13秒前
Yep0672发布了新的文献求助10
14秒前
14秒前
Vera完成签到,获得积分10
15秒前
酷波er应助龙仔采纳,获得10
15秒前
15秒前
共享精神应助123采纳,获得10
15秒前
16秒前
16秒前
夜倾心完成签到,获得积分10
16秒前
Lychee完成签到 ,获得积分10
17秒前
杜本内完成签到,获得积分10
17秒前
18秒前
18秒前
yangminghan完成签到,获得积分10
19秒前
jiakai完成签到,获得积分10
21秒前
capitalist发布了新的文献求助10
21秒前
争取不秃顶的医学僧完成签到,获得积分10
21秒前
21秒前
lelele发布了新的文献求助10
21秒前
周少发布了新的文献求助10
22秒前
22秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Effective Learning and Mental Wellbeing 400
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3975953
求助须知:如何正确求助?哪些是违规求助? 3520269
关于积分的说明 11201866
捐赠科研通 3256738
什么是DOI,文献DOI怎么找? 1798436
邀请新用户注册赠送积分活动 877578
科研通“疑难数据库(出版商)”最低求助积分说明 806464