scholarly journals Intelligent Identification Method of Sedimentary Microfacies Based on DMC-BiLSTM

2021 ◽  
Author(s):  
Ze Ren Luo ◽  
Yang Zhou ◽  
Yu Xing Li ◽  
Liang Guo ◽  
Juan Juan Tuo ◽  
...  
Keyword(s):  
Deep Learning ◽  
Oil And Gas ◽  
Nonlinear Problems ◽  
Temporal Correlation ◽  
Learning Method ◽  
Correlation Clustering ◽  
Oil And Gas Exploration ◽  
Original Curve ◽  
Spatio Temporal ◽  
Sedimentary Microfacies

Sedimentary microfacies division is the basis of oil and gas exploration research. The traditional sedimentary microfacies division mainly depends on human experience, which is greatly influenced by human factor and is low in efficiency. Although deep learning has its advantage in solving complex nonlinear problems, there is no effective deep learning method to solve sedimentary microfacies division so far. Therefore, this paper proposes a deep learning method based on DMC-BiLSTM for intelligent division of well-logging—sedimentary microfacies. First, the original curve is reconstructed multi-dimensionally by trend decomposition and median filtering, and spatio-temporal correlation clustering features are extracted from the reconstructed matrix by Kmeans. Then, taking reconstructed features, original curve features and clustering features as input, the prediction types of sedimentary microfacies at current depth are obtained based on BiLSTM. Experimental results show that this method can effectively classify sedimentary microfacies with its recognition efficiency reaching 96.84%.

A deep learning method for data recovery in sensor networks using effective spatio-temporal correlation data

Sensor Review ◽  
2019 ◽  
Vol 39 (2) ◽  
pp. 208-217 ◽  
Author(s):  
Jinghan Du ◽  
Haiyan Chen ◽  
Weining Zhang
Keyword(s):  
Deep Learning ◽  
Sensor Networks ◽  
Large Scale ◽  
Time Series Data ◽  
Temporal Correlation ◽  
Data Recovery ◽  
Series Data ◽  
Learning Method ◽  
Content Type ◽  
Spatio Temporal

Purpose In large-scale monitoring systems, sensors in different locations are deployed to collect massive useful time-series data, which can help in real-time data analytics and its related applications. However, affected by hardware device itself, sensor nodes often fail to work, resulting in a common phenomenon that the collected data are incomplete. The purpose of this study is to predict and recover the missing data in sensor networks. Design/methodology/approach Considering the spatio-temporal correlation of large-scale sensor data, this paper proposes a data recover model in sensor networks based on a deep learning method, i.e. deep belief network (DBN). Specifically, when one sensor fails, the historical time-series data of its own and the real-time data from surrounding sensor nodes, which have high similarity with a failure observed using the proposed similarity filter, are collected first. Then, the high-level feature representation of these spatio-temporal correlation data is extracted by DBN. Moreover, to determine the structure of a DBN model, a reconstruction error-based algorithm is proposed. Finally, the missing data are predicted based on these features by a single-layer neural network. Findings This paper collects a noise data set from an airport monitoring system for experiments. Various comparative experiments show that the proposed algorithms are effective. The proposed data recovery model is compared with several other classical models, and the experimental results prove that the deep learning-based model can not only get a better prediction accuracy but also get a better performance in training time and model robustness. Originality/value A deep learning method is investigated in data recovery task, and it proved to be effective compared with other previous methods. This might provide a practical experience in the application of a deep learning method.

Spatio-temporal deep learning method for ADHD fMRI classification

2019 ◽  
Vol 499 ◽  
pp. 1-11 ◽  
Author(s):  
Zhenyu Mao ◽  
Yi Su ◽  
Guangquan Xu ◽  
Xueping Wang ◽  
Yu Huang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Learning Method ◽  
Spatio Temporal

scholarly journals Fine description of sedimentary system in Wuerxun Sag of Hailaer Basin

2020 ◽  
Vol 194 ◽  
pp. 05048
Author(s):  
ZHOU Yue ◽  
GAO Geng ◽  
WANG Duanyang ◽  
YANG Xu
Keyword(s):  
Large Scale ◽  
Oil And Gas ◽  
Sedimentary Facies ◽  
Key Factors ◽  
Oil And Gas Exploration ◽  
Fan Delta ◽  
Sedimentary System ◽  
Sedimentary Microfacies ◽  
Surrounding Areas ◽  
Sand Bodies

Wuerxun depression is one of the depressions with great exploration potential in Hailaer Basin and has submitted large-scale reserves. At present, it has entered the stage of fine exploration, and the exploration object has changed from structural reservoir to lithologic reservoir exploration. The remaining targets are mainly concentrated in the trough and surrounding areas, with strong concealment and difficult to identify. Fine identification of sand bodies, genesis, types and distribution of sedimentary fans are one of the key factors restricting oil and gas exploration. Based on core observation and genetic mechanism, three sedimentary facies models of Braided River Delta, fan delta and sublacustrine fan are established. In this paper, the method of “sequence control, cycle correlation and hierarchical closure” is used to fine characterize the fan delta sedimentary system in this area, which lays a foundation for the study of sedimentary microfacies of subdivision layers, optimization of lithologic reservoir targets and guidance of oil and gas exploration deployment.

Deep Learning Assisted Doppler Sensing for Hydrocarbon Downhole Flow Velocity Estimation

2021 ◽  
Author(s):  
Klemens Katterbauer ◽  
Alberto Marsala ◽  
Virginie Schoepf ◽  
Linda Abbassi
Keyword(s):  
Deep Learning ◽  
Flow Velocity ◽  
Oil And Gas ◽  
Velocity Estimation ◽  
Gas Reservoirs ◽  
Hydrocarbon Production ◽  
Oil And Gas Exploration ◽  
Learning Framework ◽  
Measurement Results ◽  
Interpretative Framework

Abstract Logging hydrocarbon production potential of wells has been at the forefront of enhancing oil and gas exploration and maximize productivity from oil and gas reservoirs. A major challenge is accurate downhole fluid phases flow velocity measurements in production logging due to the criticality of mechanical spinner-based sensor devices. Ultrasonic Doppler based sensors are more robust and deployable either in wireline or logging while drilling (LWD) conditions; however, due to the different sensing physics, the measurement results may not be equivalent. We present in this work an innovative deep learning framework to estimate spinner phase velocities from Doppler based sensor velocities. Tests of the framework on a benchmark dataset displayed strong estimation results. This allows for the real-time automatic interpretative framework implementation and flow velocity estimations either in conventional wireline production logging technologies (PLTs) and potentially also in LWD conditions, when the well is flowing in underbalanced conditions.

scholarly journals Automated Classification of High-resolution Rock Image Based on Residual Neural Network

2021 ◽  
Vol 2095 (1) ◽  
pp. 012051
Author(s):  
Weibo Cai ◽  
Juncan Deng ◽  
Qirong Lu ◽  
Kengdong Lu ◽  
Kaiqing Luo
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
High Resolution ◽  
Oil And Gas ◽  
Automated Classification ◽  
Maximum Probability ◽  
Rock Classification ◽  
Oil And Gas Exploration ◽  
Local Image

Abstract The identification and classification of high-resolution rock images are significant for oil and gas exploration. In recent years, deep learning has been applied in various fields and achieved satisfactory results. This paper presents a rock classification method based on deep learning. Firstly, the high-resolution rock images are randomly divided into several small images as a training set. According to the characteristics of the datasets, the ResNet (Residual Neural Network) is optimized and trained. The local images obtained by random segmentation are predicted by using the model obtained by training. Finally, all probability values corresponding to each category of the local image are combined for statistics and voting. The maximum probability value and the corresponding category are taken as the final classification result of the classified image. Experimental results show that the classification accuracy of this method is 99.6%, which proves the algorithm’s effectiveness in high-resolution rock images classification.

scholarly journals Modelling the Publishing Process of Big Location Data Using Deep Learning Prediction Methods

Electronics ◽  
2020 ◽  
Vol 9 (3) ◽  
pp. 420
Author(s):  
Yan Yan ◽  
Bingqian Wang ◽  
Quan Z. Sheng ◽  
Adnan Mahmood ◽  
Tao Feng ◽  
...  
Keyword(s):  
Deep Learning ◽  
Traffic Congestion ◽  
Traffic Management ◽  
Temporal Correlation ◽  
Data Publishing ◽  
Release Time ◽  
Discrete Wavelet ◽  
Learning Mechanisms ◽  
Location Data ◽  
Spatio Temporal

Centralized publishing of big location data can provide accurate and timely information to assist in traffic management and for facilitating people to decide travel time and route, mitigate traffic congestion, and reduce unnecessary waste. However, the spatio-temporal correlation, non-linearity, randomness, and uncertainty of big location data make it impossible to decide an optimal data publishing instance through traditional methods. This paper, accordingly, proposes a publishing interval predicting method for centralized publication of big location data based on the promising paradigm of deep learning. First, the adaptive adjusted sampling method is designed to address the challenge of finding a reasonable release time via a prediction mechanism. Second, the Maximal Overlap Discrete Wavelet Transform (MODWT) is introduced for the decomposition of time series in order to separate different features of big location data. Finally, different deep learning models are selected to construct the entire framework according to various time-domain features. Experimental analysis suggests that the proposed prediction scheme is not only feasible, but also improves the prediction accuracy in contrast to the traditional deep learning mechanisms.

Sign in / Sign up

Export Citation Format

Share Document