... ROP and formation properties. Ben Aoun and Madarász (2022) also focused on ROP prediction for geothermal drilling at Utah FORGE, utilizing machine learning models like random forest regressors and artificial neural networks. Hegde et al. (2019) proposed a machine learning approach to classify...

... time of the model, for instance, mud weight ranges from 9-10.5 and the 141-670000 for the revelation on bottom, after normalization value range would be from 0-1. The normalization process is performed based on the following equation: URTeC: 4043246 6 Artificial Neural Networks (ANN): It s an algorithm...

... 3 illustrates the high-level digital workflow. Figure 3 Deep learning model based well calibration and probabilistic forecasting workflow. Deep Learning Model Training We train the proxy models with Recurrent Neural Networks (RNN). Instead of a vanilla RNN, we incorporate various hidden layers...

... in the unified workflow are implemented using a wide variety of DL models ranging from classical ML-based approaches to autoencoder based neural networks to the more powerful Transformer-based approaches that are very effective at modelling the sequential nature of the wellbore logs. Introduction In this study...

... networks to forecast future production performance. Probably the most commonly used model is the recurrent neural network (RNN), due to its natural temporal causality within the recursive structure (Aranguren et al., 2022). Fargalla et al. (2024) implemented shale gas production forecasting by integrating...

...URTeC: 4043980 A Novel Fusion: Integrating Artificial Neural Networks and Production Fit Models for Swift and Coherent Data-Physics Predictive Modeling of a Mature Oil Field in Texas Felipe Ospina!1, Pallav Sarma*1 Carlos Calad1, 1. Tachyus Copyright 2024, Unconventional Resources Technology...

... development programs, ML models have been developed to account for the relative spatial position of wells in the "wine-rack" cross-sectional (barrel) view. These models also depend on engineered features such as staggered offset and vertical offset. Our novel approach uses 2D convolutional neural networks...

... deep learning geologist complex reservoir reservoir surveillance neural network production monitoring machine learning production control dataset depletion function prediction forecast workflow geology artificial intelligence depletion urtec sensitivity accuracy validation...

... with refined models. The third method uses two artificial neural networks. We train the first network using the refined grid to predict fluid flow at the fracture face. The second network is trained as a reverse proxy on the coarse model to compute transmissibility from flow rate. Our analytical modifications...

... of these complex systems, researchers have turned to data-driven approaches to enhance forecasting accuracy and efficiency. Muther et al. (2021) discusses the application of machine learning methods, including Artificial Neural Networks (ANN), Deep Neural Networks (DNN), Long-Short-Term Memory (LSTM), Support...

... Abstract The oil and gas industry faces dual challenges and opportunities posed by the ever-expanding reservoir monitoring data landscape due to ever-growing volumes of data. Artificial intelligence (AI) offers a powerful solution, with machine learning and neural networks poised...

... fluid dynamics geologist neural network clastic rock shale gas complex reservoir artificial intelligence deep learning mape rock type dataset modeling & simulation machine learning realization production forecasting accuracy prediction permeability sedimentary rock geology...

... distribution uniformity across concurrently stimulated perforation clusters. Leveraging datasets obtained through casing-embedded optical cables, measuring vibrations throughout the stimulated interval, we employ a neural network-based model. The distributed fiber optic measurements are integrated...

... independently normalize URTeC 4046687 9 both input features and the target variable to ensure all data fall within the 0-1 range. The ReLU activation function is utilized in our neural network to introduce non-linearity, enabling the model to capture complex relationships within the data more efficiently. Next...

... and artificial intelligence (AI) considered as promising approaches to address This issue. This research aims to utilize and evaluate the performance of several Artificial Neural Networks (ANNs) architectures to predict lithological units (members) of a Permian-Triassic carbonate succession using integration...

... vector regression (SVR), artificial neural network (ANN) and random forest. The model inputs are phase change (units of DAS data collected in the field) of ten channels in the stress shadow zone, and the output is fracture width of 2400 observations (Figure 12). URTeC 3870194 11 Figure 12 Histogram...

... production period followed by 5 Huff-n-Puff cycles. CMG commercial simulation package was used to develop the production rates and recovery factors for the defined scenarios. The developed data was then used to train, test, validate, and blind test the Artificial Neural Network (ANN) proxy model to predict...

... to maximum the EUR (i.e., cumulative production within a certain period) or the NPV from a fractured well. upstream oil & gas geologist clastic rock sedimentary rock geology drilling operation optimization problem fracture mudstone neural network optimum ufd dimensionless pi ufd...

... of formation and fluid data. Besides, frequent manual operations are always ignored in the production history because of their cumbersome processing. To overcome this limitation, a supervised deep neural network (DNN) model is established in this paper to forecast hydrocarbon production that considers...

...-in induced liquid loading in unconventional wells with long laterals. Based on the acquired insights, various machine learning models, including tree-based algorithms (random forest and gradient boosting), feed-forward neural networks, and recurrent neural networks (simple RNN, LSTM, and GRU), were...