One-Dimensional Convolutional Neural Network with Adaptive Moment Estimation for Modelling of the Sand Retention Test

Razak, Nurul Nadhirah Abd; Abdulkadir, Said Jadid; Maoinser, Mohd Azuwan; Shaffee, Siti Nur Amira; Ragab, Mohammed Gamal

doi:10.3390/app11093802

Cited by 7 publications

(1 citation statement)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Adaptive Moment Estimation (Adam) is used as an optimization function, which updates all weights with a constant learning rate alpha during the process. Therefore, dual improvements in quality and speed can be achieved during model optimization ( Razak et al, 2021 ).…”

Section: Methodsmentioning

confidence: 99%

The classification of brain network for major depressive disorder patients based on deep graph convolutional neural network

Zhu

Yu²,

He³

2023

Front. Hum. Neurosci.

View full text Add to dashboard Cite

IntroductionThe early diagnosis of major depressive disorder (MDD) is very important for patients that suffer from severe and irreversible consequences of depression. It has been indicated that functional connectivity (FC) analysis based on functional magnetic resonance imaging (fMRI) data can provide valuable biomarkers for clinical diagnosis. However, previous studies mainly focus on brain disease classification in small sample sizes, which may lead to dramatic divergences in classification accuracy.MethodsThis paper attempts to address this limitation by applying the deep graph convolutional neural network (DGCNN) method on a large multi-site MDD dataset. The resting-state fMRI data are acquired from 830 MDD patients and 771 normal controls (NC) shared by the REST-meta-MDD consortium.ResultsThe DGCNN model trained with the binary network after thresholding, identified MDD patients from normal controls and achieved an accuracy of 72.1% with 10-fold cross-validation, which is 12.4%, 9.8%, and 7.6% higher than SVM, RF, and GCN, respectively. Moreover, the process of dataset reading and model training is faster. Therefore, it demonstrates the advantages of the DGCNN model with low time complexity and sound classification performance.DiscussionBased on a large, multi-site dataset from MDD patients, the results expressed that DGCNN is not an extremely accurate method for MDD diagnosis. However, there is an improvement over previous methods with our goal of better understanding brain function and ultimately providing a biomarker or diagnostic capability for MDD diagnosis.

show abstract

Section: Methodsmentioning

confidence: 99%

The classification of brain network for major depressive disorder patients based on deep graph convolutional neural network

Zhu

Yu²,

He³

2023

Front. Hum. Neurosci.

View full text Add to dashboard Cite

show abstract

Application of machine and deep learning techniques to estimate NMR-derived permeability from conventional well logs and artificial 2D feature maps

Masroor

Niri

Rajabi-Ghozloo

et al. 2022

J Petrol Explor Prod Technol

View full text Add to dashboard Cite

Nuclear magnetic resonance (NMR) logs can provide information on some critical reservoir characteristics, such as permeability, which are rarely obtainable from conventional well logs. Nevertheless, high cost and operational constraints limit the wide application of NMR logging tools. In this study, a machine learning (ML)-based procedure is developed for fast and accurate estimation of NMR-derived permeability from conventional logs. Following a comprehensive preprocessing on the collected data, the procedure is trained and tested on a well log dataset, with selected conventional logs as inputs, and NMR-derived permeability as target, shallow and deep learning (DL) methods are applied to estimate permeability from selected conventional logs through artificial production of NMR-derived information from the input data. Three supervised ML algorithms are utilized and evaluated, including random forest (RF), group method of data handling (GMDH), and one-dimensional convolutional neural network (1D-CNN). Additionally, a modified two-dimensional CNN (named as Residual 2D-CNN) is developed which is fed by artificial 2D feature maps, generated from available conventional logs. The hyper-parameters of the ML and DL models are optimized using genetic algorithm (GA) to improve their performances. By comparing the output of each model with the permeability derived from NMR log, it is illustrated that nonlinear machine and deep learning techniques are helpful in estimation of NMR permeability. The obtained accuracy of RF, GMDH, 1D-CNN and Res 2D-CNN models, respectively, is 0.90, 0.90, 0.91 and 0.97 which indicate that Res 2D-CNN model is the most efficient method among the other applied techniques. This research also highlights the importance of using generated feature maps for training Res 2D-CNN model, and the essential effect of the applied modifications (i.e., implementing residual and deeper bottleneck architectures) on improving the accuracy of the predicted output and reducing the training time.

show abstract

Sand screen selection by sand retention test: a review of factors affecting sand control design

Khan,

Zainal,

Idris

et al. 2024

J Petrol Explor Prod Technol

View full text Add to dashboard Cite

The installation of sand screens in open-hole completions in the wellbore is crucial for managing sand production. The main reason for using standalone screens in open-hole completions is their relatively reduced operational complexity compared to other sand control technologies. However, directly applying the screen to the bottom of the hole can lead to an incorrect screen type selection, resulting in an unreliable sand control method. To address this issue, a sand retention test is conducted to evaluate the performance of a standalone screen before field installation. Nevertheless, current sand retention test setups encounter several challenges. These include difficulties in identifying minimum retention requirements, interpreting results in the context of field conditions, and replicating field-specific parameters. The existing sand retention test introduces uncertainties, such as inaccurately replicating field requirements, inconsistent selection of wetting fluids, flow rates, and channel formation, leading to variations in the choice of the optimal screen using this test. In response to these challenges, this study aims to review the sand retention test and propose an improved sand retention method to overcome these problems. The focus of this article is to provide an in-depth analysis of previous sand retention test setups, their contributions to characterizing sand screens, and the parameters utilized in determining test outcomes. Additionally, this review outlines a procedure to investigate the impact of different particle sizes on screen erosion. Key findings emphasize the importance of using high-quality materials, proper screen design to resist damage and erosion, achieving acceptable natural packing behind the screen, and considering factors such as geology, wellbore conditions, and installation techniques. The analysis reveals that a high quantity of finer and poorly sorted sand increases sand production. The study recommends performing a sand pack test closer to reservoir conditions for better evaluation. Premium sand screens demonstrate the highest retention capacity, followed by metal mesh and wire-wrapped screens. Additionally, geotextiles show potential for enhancing sand retention, and screen design affects erosion resistance and service life.

show abstract

One-Dimensional Convolutional Neural Network with Adaptive Moment Estimation for Modelling of the Sand Retention Test

Cited by 7 publications

References 53 publications

The classification of brain network for major depressive disorder patients based on deep graph convolutional neural network

The classification of brain network for major depressive disorder patients based on deep graph convolutional neural network

Application of machine and deep learning techniques to estimate NMR-derived permeability from conventional well logs and artificial 2D feature maps

Sand screen selection by sand retention test: a review of factors affecting sand control design

Contact Info

Product

Resources

About