... operational parameter algorithm hyperparameter feature importance interaction analysis prediction Introduction Unconventional oil and gas resources are abundant worldwide and hold significant development potential, accounting for nearly 40% of the global energy supply ( Chen et al. 2022...

... Abstract The primary objective is to describe the application of a robust method and system for predicting the lifespan of Electric Submersible Pumps (ESPs) using advanced machine learning techniques. This system aims to enhance the efficiency and reliability of ESPs by leveraging data from...

... Abstract In this paper we describe the automated sand deposition prediction and erosion control advisors (SDECA) in the multiphase production network and how it enhances operational excellence and strengthens the Health, Safety and Environment vision by monitoring pipeline integrity in real...

... structure prediction reservoir bco utilizing machine learning geology machine learning unlock subsurface production bayesian belief network bbn dataset information production rate unlock subsurface production potential Introduction BCO refers to the possibility of finding and producing...

... of simulation results may lead to different operator responses, making an informed modeller / engineer essential to determining the risk during off-specification events and hence advise the appropriate response. The results also show that the appropriate action depends on the circumstances, making predictive...

... for the analysis, which provides FLOW or NO FLOW labels, signifying successful oil or gas extraction, respectively. Once validated, the model predicts perforation outcomes in the Mutiara, Pamaguan, Badak, Nilam, Lampake, and Semberah Field, Sanga-Sanga Block, contributing to the advancement of predictive...

... are not equal and neither is equal to 1. In addition, the formation temperature of deep shale is higher than that of shallow shale formation, which would have an effect on the horizontal stress prediction. Here, this paper estimates the anisotropic horizontal stress using well logs sonic data in a well of deep...

... the comparative study against classical convolutional neural network (CNN) and long short-term memory (LSTM) models. This study combined deep learning techniques and mercury injection capillary pressure to efficiently realize the rapid intelligent prediction of CO 2 -brine RP curves that facilitate the evaluation...

... the pseudo-component and CO 2 storage mechanisms. This makes the scheme optimization tedious. Therefore, we propose a deep learning-based surrogate model to efficiently implement numerical simulation of CO 2 -flooding and storage. Proposed method consists of automatic encoder and prediction part. The auto...

... and predictive Machine Learning (ML) modeling was developed and deployed in the Montney unconventional siltstone gas reservoir, British Columbia, Canada to identify production zone "sweet spots" from reservoir quality data (i.e., geological, geophysical, and geomechanical) data and completion quality data (e.g...

... Abstract Several studies have used machine learning-based techniques to improve the production behavior prediction in existing shale gas wells. However, few studies have investigated production prediction in new wells wherein no prior information is available. This is challenging because...

... Abstract Sand production prediction is essential from the early stages of field development planning for well completion design and later for production management. Unconsolidated and weakly consolidated sandstones are prone to fail at low flowing bottom hole pressures during hydrocarbon...

... laboratory studies show high agreement. The model coefficients obtained by treatment of laboratory data allow predicting skin growth in production wells under fines migration. coal seam gas reservoir characterization migration upstream oil & gas coal bed methane concentration correspond...

.... However, RF remains one of the greatest uncertainties in O&G projects. The difficulty in RF prediction arises due to the number of variables affecting the recovery from a reservoir. These includes variables that are both uncertain and beyond the control of O&G operators, such as fluid flow...

... of souring potential in the field is required. This paper is the results of our experience in H 2 S mapping at reservoir-well-facilities modelling, history matching, and prediction of H 2 S. We will highlight the workflow adopted to find the root causes of souring via sampling and modelling approach since...

... Abstract An accurate pore-pressure prediction plays an important role in well planning as exploration targets shift to deeper over-pressured reservoirs. Pore pressure related problems in high-pressure high-temperature (HPHT) wells include well control, lost circulation, formation breathing...

... Abstract Data limitation and sparsity are considered the main source of non-uniqueness and ill-posedness in elastic property prediction on seismic data using Deep Learning (DL). The ill-posed regression problem can be solved by conducting adequate pre-processing steps through data augmentation...

... Abstract With technology disruption and the increasing trend in big data, it is crucial for offshore gas production fields to transform process performance monitoring practice from manually monitoring on monthly basis by site process engineers to real-time monitoring with a predictive model...

.... However, these methods are time-consuming and/or resource-intensive. This paper proposes a novel machine learning approach to predict permeability scores. Field drilling and wireline data are acquired from 80 wells in the Surat Basin, Australia. The permeability scores are based on petrophysical...

... platforms, seamlessly linked with Insights dashboard module in providing actionable insights, and weight predictive module supported by Machine Learning (ML) model was developed. This paper discussed the Minimum Viable Product (MVP) Phase 1 development outcome, using a close-loop weight control ecosystem...