... neural network (NN), creating a map from well-location parameters to the objective function. We utilize the analytical gradient of the NN, resulting in an effective search direction while saving the computational cost associated with stochastic-gradient perturbations. Our method features a novel NN...

... and generalizability. The developed model performs robust smoke detection with high precision alerting and minimizing false positives from steam images. This application has been deployed in the plant within an end-to-end solution, creating a positive impact on operations. neural network operation detection...

.... dataset geologist rock type neural network carbonate rock sedimentology sedimentary rock deep learning artificial intelligence machine learning depositional environment synthetic seismogram application information noise correlation coefficient synthetic dataset realization inversion...

... specialized domains for companies. artificial intelligence deep learning natural language neural network machine learning llm knowledge management information application large language model sequence architecture database petroleum engineering requirement probability fine-tuning arxiv...

.... machine learning classification neural network triplet artificial intelligence cnn classifier dataset inspection workflow vector nearest neighbor accuracy similarity damage classification gas equipment component validation backbone Introduction Oil and gas companies across the globe...

... the decision of whether to run a wireline image log. To achieve this goal, it is necessary to efficiently analyze multiple criteria that would ordinarily be dependent on the speed and subjectivity of human interpretation. The chosen solution involves the combination of convolutional neural networks with feed...

... reservoir simulation enhanced recovery prediction equation geology evolution multi-step embed journal neural network machine learning arxiv preprint arxiv application latent representation chen Introduction Reservoir simulation is a computational process used to model multi-physics...

... learning flow in porous media reservoir simulation artificial intelligence neural network scaling method geology rock type machine learning upscaling pcu-dl module accuracy architecture physics-constrained upscaling permeability value reservoir characterization pore segmentation equation...

... the simultaneous analysis of large datasets, its effectiveness is often compromised by data noise and ambiguity, which can degrade the accuracy of the algorithms. Hence, this research incorporates uncertainty quantification into attention mechanism neural network to produce more reliable outcomes in seismic...

... of uncertain model parameters. To tackle these issues, we resort to cutting-edge deep learning (DL) technologies for their universal approximation capability in forward and inverse modeling based on automatic differentiation. In this study, we develop a Deep Neural Network-based History-Matching (DNN-HM...

..., physical mechanism and constraints are embedded into the data-driven model to make the prediction results satisfy the prior domain knowledge. The transfer learning method based on physics-guided neural network (TL-PG) integrates the seepage theory with sparse spatial data to improve the prediction accuracy...

..., establishing a new state-of-the-art in the field, offering enhanced accuracy and robustness in seismic data processing. diffusion posterior sampling deep learning neural network artificial intelligence reservoir characterization copaint refined diffusion posterior sampling gaussian noise...

... fluids and materials drilling fluid management & disposal tripping borehole prediction well planning drillstring design node beijing gat neural network wellbore integrity artificial intelligence pipe machine learning wellbore tripping wellbore geometry mechanism engineering china...

...) architecture to augment engineering datasets, particularly those related to solid particle erosion ( Ramiro et al., 2018 , Mansi et al., 2020 ). The framework consists of two main components: a generator and a discriminator. These neural networks compete against each other in a process known as adversarial...

... Abstract The goal is to estimate the injector-to-producer connectivity from injection-production history data by implementing an attention-based graph neural network for fusion model (AGFM). The AGFM can identify the complex relationships between the injectors and producers, ensuring...

... such as injection rate and pressure data as input and multiphase production rates as output. We combine reduced physics models into a neural network architecture by utilizing two different approaches. In the first approach, the reduced physics model is used for pre-processing to obtain approximate solutions...

.... This research proposes applying transfer learning to a physics-aware deep-learning-based proxy reservoir simulator titled Embed to Control and Observe (E2CO). In this study, the original physics-informed deep neural network proxy model of an existing reservoir is allowed to retrain key layers within...

...-decoder structure to do production forecasting. The findings demonstrate that ST-GFE significantly improves prediction accuracy for newly developed wells compared to the purely temporal models, such as recurrent neural network (RNN)-based and Transformer models. ST-GFE adapts to production changes...

..., these simulations are often computationally expensive. However, through training on readily available simulation datasets, recent advancements in data-driven models have made it possible to predict CO 2 movement rapidly. In this study, we adopt the U-Net Enhanced Graph Convolutional Neural Network (U-GCN...

... by utilizing an efficient gradient-based method. The reservoir surrogate model is based on the multi-model Embed-to-control Observe (E2CO) architecture, consisting of four blocks of neural networks: encoder, transition, transition output, and decoder. In this work, the surrogate model is coupled...