... to leverage DAS and quantify the flow rate contribution of each well section outfitted with fiber optic sensors. These techniques, spanning from Speed of Sound (SoS) tracking, to analytical fluid flow and heat transfer modeling, to machine learning models trained using labeled DAS-based features, serve...

..., estimating the production impacts remains a challenge, particularly when newer developments occur in a different formation. This study seeks to use machine learning (ML) models to quantify the production losses resulting from delayed development of a secondary bench in an unconventional reservoir compared...

... in the vertical wells and its implications for future use in deciding frac stage placement. clastic rock rock type mudstone sedimentary rock complex reservoir artificial intelligence machine learning urtec field development structural geology petroleum geology reservoir characterization...

... the effectiveness of AI techniques to predict drilling dynamics. Wang et al. (2023) leveraged transformer-based models for real-time analysis, achieving superior anomaly detection compared to traditional methods. Phelan et al. (2022) employed random forest machine learning models on Utah FORGE data to predict both...

... and machine learning (ML)-based life-cycle optimization methodologies by considering various constraint and optimization strategies listed in Table 1 andTable 2 as well as different optimization options with/without relative permeability and capillary pressure hysteresis. In all cases, we include molecular...

... formation north dakota gas injection method modeling & simulation machine learning diffusion mechanism efficiency corey exponent urtec diffusion coefficient matrix sensitivity advection bakken formation URTeC: 4043537 Evaluation of Cyclic Gas injection EOR in Unconventional Reservoirs...

...; Alvayed et al., 2023). However, in the absence of microseismic data, there are multiple solutions for the inversion of fracture network, making it difficult to obtain the accurate distribution of hydraulic fractures. With the rapid advancement of artificial intelligence, machine learning methods have been...

... Nonlinear Regression (Hybrid SNR). This innovative model integrates recent advancements in machine learning and sparsity techniques. Unlike conventional methods, Hybrid SNR is suited to discern the intricate governing equations that dictate flow of phases in unconventional reservoirs characterized...

... gas injection method geology enhanced recovery data mining modeling & simulation machine learning reservoir visualization urtec conference geologist artificial intelligence geological subdiscipline co 2 real-time visualization bhp unconventional resource technology conference...

... sufficiently capture the key characteristics of shale and tight recoveries. In addition, machine learning and artificial intelligence also play an important role in shale and tight reservoir modeling (e.g., Han et al., 2022; Wang et al., 2024). This is due to one of the key features of shale and tight asset...

...URTeC: 4038060 Integrating Experiments and Well Logs to Predict Caney Shale Static Mechanical Properties during Production with Supervised Machine Learning Sherif M. Kholy*, Hunjoo P. Lee, and Mileva Radonjic, Oklahoma State University. Copyright 2024, Unconventional Resources Technology Conference...

... without the written consent of URTeC is prohibited. Abstract A two-stage, data-driven, end-to-end framework utilizing machine learning is developed, evaluated, and presented to optimize the rate of penetration (ROP) in S-shaped wells. This framework employs prior knowledge from existing wells in Southern...

... Abstract In this paper, we present an automated data-driven workflow using Machine Learning (ML) for gas lift optimization in unconventional fields. This workflow integrates a ML model that accurately forecasts the Gas Lift Performance Curve, and a Bayesian Optimization Framework to solve...

... and deep learning models trained on an ensemble of physics models to improve the scalability and reliability for shale and tight reservoir forecasting. We construct generic reservoir models that can capture key first principles of unconventional well production mechanisms. PVT and pressure machine learning...

...URTeC: 4034008 A Machine-Learning-Based Workflow for Drilling Risk Prediction of Wellbore Instability and Trajectory Optimization in Ultra-Deep Formation Hanqing Wang1, Ruxin Zhang2, Ziyan Deng3, Jin Meng1, Han Wang1, Yujie Zhou1, Fan Yang1, Ji Chang1, Yitian Xiao1, Huiwen Pang*4 1. SINOPEC...

...URTeC: 4036015 Physics-Informed Machine Learning Approach for Closed-Loop Reservoir Management Using RGNet Zhenyu Guo*1, Sathish Sankaran1, 1. Xecta Digital Labs. Copyright 2024, Unconventional Resources Technology Conference (URTeC) DOI 10.15530/urtec-2024-4036015 This paper was prepared...

... of detail and accuracy in the analysis. Data-driven approaches, such as those proposed by Lougheed et al. (2019), Eltahan et al. (2021), Tavassoli et al. (2021), and Fathi et al. (2023), leverage historical data to use as analogs or to train machine-learning models capable of predicting inter-well...

...URTeC: 4036239 Machine Learning vs. Type Curves in the Appalachian Basin: A Comparative Study A. Cui*1, A. Yanke2, T. Dao2, P. Ye2, T. Cross1, B. Davis1, 1. Novi Labs, 2. Equinor. Copyright 2024, Unconventional Resources Technology Conference (URTeC) DOI 10.15530/urtec-2024-4036239 This paper...

... 1. Discovery: Review current control and surveillance technologies to identify opportunities for AI-based enhancement. 2. Assessment: Gather key data for model training and evaluate integration compatibility with existing systems. 3. Development: Develop and calibrate AI / machine learning (ML...

... quality, in general, varies along the reservoir. We propose a machine learning workflow to first improve wellbore log quality, then propagate markers as well as petrophysical and geomechanical property interpretation from a few high tier wells to the entire field where log availability might be restricted...