... Abstract Underground hydrogen storage (UHS) is crucial for balancing renewable energy fluctuations, but modeling its dynamic injection and withdrawal cycles introduces sharp fronts and complex behaviors. Traditional neural networks when modeling an underground hydrogen storage operation...

... Abstract An unsupervised clustering for rock typing definition coupled with a feedforward deep learning neural network have been developed in-house for a giant brown field. This field under study has thick reservoir sediment deposition amounting to 7000 ft with more than 200 reservoir units...

... on the inference dataset consistently achieved an R 2 of above 0.96, indicating strong generalization capability in predicting complex combinations of geological parameters. deep learning neural network geology co 2 artificial intelligence machine learning climate change scenario saline aquifer...

... by structural trends is established using the Convolutional Neural Network algorithm. Thereafter, the relationships between various principal controlling factors and depth are analyzed. Employing the Particle Swarm Optimization algorithm, which adopts a global optimization scheme to circumvent the entrapment...

... data and the lack of physical support in surrogate models, providing reliable support for complex reservoir development decisions. deep learning geologist neural network modeling & simulation geology machine learning artificial intelligence physical loss label loss training process...

... on the geological data within each window, using the Bayesian Information Criterion to assess the distribution of geological attributes within these windows. This distribution is incorporated as geological prior knowledge into a Bayesian neural network (BNN) model, where an online update model for ROP prediction...

.... As a result, the encoder in this work also demonstrates its ability to be an efficient backbone model for extracting significant information from borehole image data. neural network image data deep learning geologist artificial intelligence machine learning borehole image data geology...

... reservoir characteristics, optimizing exploration and development strategies, and enhancing resource utilization efficiency in the oil and gas industry. digital core geologist neural network geology artificial intelligence flow in porous media core sample reconstruction noise pore structure...

... characteristics and the poor fitting of water cut in some wells affect the prediction accuracy of remaining oil and the adjustment and exploitation potential of the oilfield. To solve the above problems, a set of fine geological modeling method of dual-medium buried hill reservoir based on BP neural network...

... artificial intelligence neural network machine learning deep learning reservoir characterization interpretation prediction network model synthetic training data international petroleum technology conference fault pattern fault probability perpendicular prediction result fault interpretation...

... artificial intelligence real time system abnormal event algorithm drilling fluid management & disposal incident operation drilling operation neural network well control detection stand pipe pressure drilling fluids and materials machine learning indicator exhibition detection time outlet...

... to the prediction of real-time rate of penetration. The results are expected to provide guidance for the further study on the increase of drilling speed and reduction of well costs. geologist neural network deep learning drilling operation geology drilling fluids and materials drilling fluid management...

... using the pre-stack elastic parameters inversion technique, and the elastic modulus K is used as a sensitive parameter for gas prediction. On this basis, neural network is used to find the inverse law of the above rock physical laws acting on the elastic parameters of pre-stack inverse bodies. Thus...

...-encoder is a generative artificial neural network capable of learning latent representations of the input data without supervision. First, we construct a suitable filter based on the tool response function of the low-resolution target log and apply this filter to the high-resolution source log...

... of pipeline operating status, and the operating data stored in SCADA system lacks operating condition labels, which makes it difficult to explore the potential value of the data. In this work, a hybrid neural network model based on multiplex visibility graphs (MVG) is proposed for operating conditions...

... the closest match to an unlabeled sample. The system utilizes image-processing and neural-network-based encodings to build a database. Using this, it is possible to utilize existing legacy data as a guide to interpret new samples. The advantage of the system is that the associated metadata for the legacy thin...

... enablement and people behaviors in order to successfully develop and implement AI capability in inspection. This is followed by a detailed discussion on AI development methodology and results from data science perspective. work process neural network classifier inspection architecture data...

... machine learning geological subdiscipline almani deformation neural network equation permeability geomechanical deformation implementation international petroleum technology conference approach kumar coupling iteration application permeability multiplier computed accuracy Introduction...

... shift into account. More in detail, we continuously train a recurrent Deep Neural Network to build a virtual sensor from other signals and we compare the prediction versus the real signal to raise (in case) an anomaly. Furthermore, Kullback-Leibler (KL) divergence is used to estimate the overlap between...

... Synthetic-aperture radar (SAR) approaches are limited by their algorithm complexity which difficult to work with imbalanced data sets, doubts to select optimal features, and the relatively slow detection. Using deep learning approach could speed up the oil detection. convolutional neural network U-Net...