Estimating elastic parameters from digital rock images based on multi-task learning with multi-gate mixture-of-experts

计算机科学 稳健性(进化) 人工神经网络 卷积神经网络 人工智能 同方差 机器学习 算法 异方差 生物化学 基因 化学
作者
Zhiyu Hou,Danping Cao
出处
期刊:Journal of Petroleum Science and Engineering [Elsevier]
卷期号:213: 110310-110310 被引量:9
标识
DOI:10.1016/j.petrol.2022.110310
摘要

Digital rock physics analysis has become an effective approach complementary to traditional experimental physics in estimating elastic parameters from digital rock images to study the relationship between the grain structure and rock mechanical properties. However, conventional numerical simulation requires lots of computational time and GB voxels memory. Recently, the convolutional neural network (CNN) has proven to be a successful method for estimating physical parameters from digital rock images, and multi-parameter simultaneous prediction using multi-task learning has been the focus of attention. But these methods don't achieve satisfactory results due to tasks' mutual interferences that affect network performances such as accuracy, robustness, and efficiency. To address these issues, a multi-task learning network with multi-gate mixture-of-experts was proposed to estimate elastic parameters from two-dimension digital rock images (MMOEROCK) in this paper. Parallel operational expert networks were used to replace traditional serial operational networks in order to reduce the mutual interferences of tasks. Gate networks were used to control the output weights of different expert networks in order to allow selective sharing among independent expert networks. The homoscedastic uncertainty loss function was used to automatically adjust the weight of each task loss function to improve network performance in searching for the optimal solution. The experimental results showed that the R2-scores of the bulk modulus, shear modulus, P wave velocity, and S wave velocity could reach 0.89, 0.92, 0.92, and 0.91 on the validation set and 0.97, 0.96, 0.96, and 0.94 on the test set, respectively, and MMOEROCK after fully training achieved an 800 speedup factor compared with the finite element method.
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
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
成成完成签到 ,获得积分10
刚刚
刚刚
水形物语发布了新的文献求助10
1秒前
阿托品完成签到,获得积分10
1秒前
634301059完成签到 ,获得积分10
1秒前
斯文败类应助啊标采纳,获得10
1秒前
NMZN完成签到,获得积分10
3秒前
JamesPei应助爱听歌的从筠采纳,获得10
4秒前
xuwenwen完成签到,获得积分10
5秒前
安容天完成签到,获得积分10
5秒前
无奈醉柳完成签到,获得积分10
6秒前
leng发布了新的文献求助30
6秒前
7秒前
7秒前
勤劳的香菇完成签到,获得积分20
12秒前
打打应助空曲采纳,获得10
13秒前
Jacklzu完成签到,获得积分10
13秒前
sims发布了新的文献求助10
13秒前
欢喜小霸王完成签到 ,获得积分10
14秒前
niekyang发布了新的文献求助10
14秒前
14秒前
爆米花应助boom采纳,获得30
14秒前
CipherSage应助任性茉莉采纳,获得10
15秒前
李瑞康完成签到 ,获得积分10
16秒前
16秒前
17秒前
搞怪半烟完成签到,获得积分10
18秒前
18秒前
None发布了新的文献求助10
20秒前
Li完成签到,获得积分10
20秒前
chanyi发布了新的文献求助10
21秒前
syy发布了新的文献求助10
21秒前
十七完成签到 ,获得积分10
22秒前
23秒前
www完成签到,获得积分10
23秒前
leng完成签到,获得积分10
23秒前
23秒前
合适磬发布了新的文献求助10
23秒前
haiqi完成签到,获得积分10
23秒前
24秒前
高分求助中
Comparative Anatomy of the Vertebrates 9th 3000
Continuum Thermodynamics and Material Modelling 3000
Production Logging: Theoretical and Interpretive Elements 2700
Les Mantodea de Guyane Insecta, Polyneoptera 1000
Structural Load Modelling and Combination for Performance and Safety Evaluation 1000
Conference Record, IAS Annual Meeting 1977 820
England and the Discovery of America, 1481-1620 600
热门求助领域 (近24小时)
化学 材料科学 生物 医学 工程类 有机化学 生物化学 物理 纳米技术 计算机科学 内科学 化学工程 复合材料 基因 遗传学 物理化学 催化作用 量子力学 光电子学 冶金
热门帖子
关注 科研通微信公众号,转发送积分 3571929
求助须知:如何正确求助?哪些是违规求助? 3142327
关于积分的说明 9446826
捐赠科研通 2843700
什么是DOI,文献DOI怎么找? 1563001
邀请新用户注册赠送积分活动 731530
科研通“疑难数据库(出版商)”最低求助积分说明 718557