Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Domingos Alves Dias Jr et al.
Summary: Seismic reflection is widely used in the oil and gas industry to prospect hydrocarbon resources, and has been used in Brazilian onshore fields to estimate gas accumulations. However, the analysis and interpretation of seismic data are time-consuming due to the large amount of information and noise. To assist geoscientists, a methodology based on convolutional long short-term memory and particle swarm optimization is proposed for detecting gas accumulation. Testing in the Parnaiba Basin shows promising results with an F1-score of 84.22%, sensitivity of 98.06%, specificity of 99.44%, and accuracy of 99.42%.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Energy & Fuels
H. N. Hansen et al.
Summary: The petroleum industry is focusing on buried reservoir discoveries and exploring CO2 storage sites to extend the lifespan of operating installations. To effectively characterize and predict reservoir quality, an innovative approach is needed that integrates existing core-and well log data. Core analysis provides in-depth knowledge, while continuous data sources are more efficient for regional analysis. This study demonstrates the integration of petrographic-and facies data with machine learning to effectively utilize existing core data and accurately predict reservoir properties.
GEOENERGY SCIENCE AND ENGINEERING
(2023)
Article
Energy & Fuels
Joshua Kwesi Desbordes et al.
Summary: This paper introduces a transfer learning based optimization framework for dynamic production optimization problems, which utilizes methods such as domain adaptation learning, extended boundary constraints, and transfer component analysis to improve the optimization speed and accuracy of production control options.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2022)
Article
Energy & Fuels
Yihuai Lou et al.
Summary: The paper presents a method to improve the accuracy of seismic dip estimation using deep learning models. By generating realistic synthetic seismic data sets and training a supervised deep learning model, the reliability and effectiveness of seismic dip estimation are enhanced.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2022)
Article
Energy & Fuels
Zhongzheng Wang et al.
Summary: This study proposes an adaptive and robust deep learning-based framework for well control optimization, which addresses the generalization problem. Compared to previous methods, the framework trains a policy that is robust to environmental variations and can adapt to unseen but similar environments.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2022)
Article
Energy & Fuels
Zhongzheng Wang et al.
Summary: This study presents an adaptive and robust deep learning-based framework to address the generalization problem in well control optimization. The trained agent demonstrates excellent optimization efficiency and generalization performance, making it particularly valuable for deployment in unforeseen situations in the real world.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2022)
Article
Geochemistry & Geophysics
Ji Chang et al.
Summary: Lithology identification is crucial in geologic exploration and reservoir evaluation. Existing work shows that integrating unsupervised domain adaptation methods can effectively improve model performance and address the issue of data distribution differences in new wells.
Article
Mathematics, Applied
Charles K. Chui et al.
Summary: This paper introduces a direct time-frequency method based on sinusoidal signal approximation for solving the inverse problem of multicomponent signal separation, as well as obtaining a more accurate component recovery formula derived from linear chirp approximation. By analyzing the SSO based on adaptive STFT, error bounds for instantaneous frequency estimation and component recovery are derived for both sinusoidal signal-based and linear chirp-based models, providing mathematical guarantee for the proposed non-stationary multicomponent signal separation method. Results are confirmed through experiments.
JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS
(2021)
Article
Mathematics, Applied
Tingting Wu et al.
Summary: This study proposes two methods for modeling seismic wavefield in the frequency domain to obtain an alias-free result with fewer frequencies than typically required by the Nyquist sampling theorem. The methods address the numerical challenge of solving Helmholtz equations of large wave numbers by introducing l(1) regularization models and a new sampling technique. Numerical experiments demonstrate that the proposed methods are accurate, robust, and efficient in modeling seismic wavefield with only a few low frequencies.
JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS
(2021)
Article
Engineering, Civil
Hamid Reza Ahmadi et al.
Summary: The research proposes a new method for damage detection in concrete piers of bridges, which accurately identifies damages and diagnoses their location. The method is based on short-time Fourier transform and a new damage index, using small impact loads and recorded responses. This approach is not only easy to use, but also significantly reduces the cost of field surveys.
Article
Computer Science, Information Systems
Andrea Rosales Sanabria et al.
Summary: Sensor-based human activity recognition (HAR) plays a significant role in various fields such as smart city, smart home, and personal healthcare. The shift-GAN proposed in this article integrates Bi-GAN and KMM to achieve robust feature transfer between two different domains. Experimental results demonstrate that shift-GAN outperforms over 10 existing domain adaptation techniques, learns intrinsic feature mappings independent of activities between two domains, is robust to sensor noise, and less sensitive to training data.
Article
Computer Science, Artificial Intelligence
Chengjian Feng et al.
Article
Computer Science, Interdisciplinary Applications
Luana Batista da Cruz et al.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2020)
Article
Computer Science, Artificial Intelligence
Amira Soudani et al.
EXPERT SYSTEMS WITH APPLICATIONS
(2019)
Article
Computer Science, Artificial Intelligence
Yan Huang et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2019)
Article
Computer Science, Interdisciplinary Applications
Robherson Wector de Sousa Costa et al.
MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING
(2018)
Article
Computer Science, Artificial Intelligence
Antonio Oseas de Carvalho Filho et al.
PATTERN RECOGNITION
(2018)
Article
Engineering, Geological
Maria Zucconi et al.
SOIL DYNAMICS AND EARTHQUAKE ENGINEERING
(2017)
Article
Geosciences, Multidisciplinary
K. Unglert et al.
JOURNAL OF VOLCANOLOGY AND GEOTHERMAL RESEARCH
(2016)
