Fast electrical imaging of injected fluid in hydraulic fracturing using a practical interactive parameter estimation method

Li, Yinchu; Yang, Dikun

doi:10.1190/segam2019-3215758.1

Cited by 5 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pre-trained models are architectures previously trained on an extensive data set, and then the weights of these models are transferred and trained on a downstream task. For example, a popular deep convolutional neural network called ResNet [ 75 , 76 ] has been trained on 3.2 million ImageNet [ 52 ] images and have been used for many downstream tasks such as, predicting fluid flow [ 77 ], hydraulic fracture [ 78 ], and fluid-structure interaction [ 79 ]. Similar architectures with residual blocks have seen many adoptions in challenging downstream tasks such as image-to-image translation, image inpainting, and semantic segmentation [ 80 , 81 ].…”

Section: Methodsmentioning

confidence: 99%

Machine learning (ML)-assisted surface tension and oscillation-induced elastic modulus studies of oxide-coated liquid metal (LM) alloys

Hossain,

Kamran,

Tavakkoli

et al. 2023

J. Phys. Mater.

View full text Add to dashboard Cite

Pendant drops of oxide-coated high-surface tension fluids frequently produce perturbed shapes that impede interfacial studies. Eutectic gallium indium (eGaIn) or gallium indium tin (Galinstan) are high-surface tension fluids coated with a ~5nm gallium oxide (Ga2O3) film and falls under this fluid classification, also known as liquid metals (LM). The recent emergence of LM-based applications often cannot proceed without analyzing interfacial energetics in different environments. While numerous techniques are available in the literature for interfacial studies- pendant droplet-based analyses are the simplest. However, the perturbed shape of the pendant drops due to the presence of surface oxide has been ignored frequently as a source of error. Also, exploratory investigations of surface oxide leveraging oscillatory pendant droplets have remained untapped. We address both challenges and present two contributing novelties- (a) by utilizing the machine learning technique, we predict the approximate surface tension value of perturbed pendant droplets, (ii) by leveraging the oscillation-induced bubble tensiometry method, we study the dynamic elastic modulus of the oxide-coated LM droplets. We have created our dataset from LM's pendant drop shape parameters and trained different models for comparison. We have achieved >99% accuracy with all models and added versatility to work with other fluids. The best-performing model was leveraged further to predict the approximate values of the nonaxisymmetric LM droplets. Then, we analyzed LM's elastic and viscous moduli in air, harnessing oscillation-induced pendant droplets, which provides complementary opportunities for interfacial studies alternative to expensive rheometers. We believe it will enable more fundamental studies of the oxide layer on LM, leveraging both symmetric and perturbed droplets. Our study broadens the materials science horizon, where researchers from machine learning and artificial intelligence domains can work synergistically to solve more complex problems related to surface science, interfacial studies, and other studies relevant to LM-based systems.

show abstract

Section: Methodsmentioning

confidence: 99%

Machine learning (ML)-assisted surface tension and oscillation-induced elastic modulus studies of oxide-coated liquid metal (LM) alloys

Hossain,

Kamran,

Tavakkoli

et al. 2023

J. Phys. Mater.

View full text Add to dashboard Cite

show abstract

“…However, the resolution of the frequency-domain EM method also has limitations. In 2017, the Advanced Energy Consortium (AEC), together with other organisations, implemented a test for hydraulic fracturing monitoring using the transient electromagnetic (TEM) method with a long wire source, in which the casing wells in fracturing construction sites were used as a long wire source, and anomalous signals from induced fractures at a depth of 2 km were detected (Hibbs and Wilt, 2016;Li and Yang, 2019). The highpower TEM method with a long wire source has the distinct advantages of high signal-to-noise ratio, considerable depth of exploration, and low cost, and it has gradually become the focus of research for deep mineral and unconventional oil and gas exploration (Di et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Development and Consideration of 3D Transient Electromagnetic Forward Modelling for the Hydraulic Fracturing Monitoring

et al. 2022

View full text Add to dashboard Cite

3-D Numerical Study on Controlled Source Electromagnetic Monitoring of Hydraulic Fracturing Fluid With the Effect of Steel-Cased Wells

Yang

et al. 2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Fast electrical imaging of injected fluid in hydraulic fracturing using a practical interactive parameter estimation method

Cited by 5 publications

References 12 publications

Machine learning (ML)-assisted surface tension and oscillation-induced elastic modulus studies of oxide-coated liquid metal (LM) alloys

Machine learning (ML)-assisted surface tension and oscillation-induced elastic modulus studies of oxide-coated liquid metal (LM) alloys

Development and Consideration of 3D Transient Electromagnetic Forward Modelling for the Hydraulic Fracturing Monitoring

3-D Numerical Study on Controlled Source Electromagnetic Monitoring of Hydraulic Fracturing Fluid With the Effect of Steel-Cased Wells

Contact Info

Product

Resources

About