A Novel Artificial Neural Network-Based Correlation for Evaluating the Rate of Penetration in a Natural Gas Bearing Sandstone Formation: A Case Study in a Middle East Oil Field

This study presented an empirical correlation to estimate the drilling rate of penetration (ROP) while drilling into a sandstone formation. The equation developed in this study was based on the artificial neural networks (ANN) which was learned to assess the ROP from the drilling mechanical parameters. The ANN model was trained on 630 datapoints collected from five different wells; the suggested equation was then tested on 270 datapoints from the same training wells and then validated on three other wells. The results showed that, for the training data, the learned ANN model predicted the ROP with an AAPE of 7.5%. The extracted equation was tested on data gathered from the same training wells where it estimated the ROP with AAPE of 8.1%. The equation was then validated on three wells, and it determined the ROP with AAPEs of 9.0%, 10.7%, and 8.9% in Well-A, Well-B, and Well-D, respectively. Compared with the available empirical equations, the equation developed in this study was most accurate in estimating the ROP.

Wildfires and Monsoons: Cryptic Drivers for Highly Variable Provenance Signals within a Carboniferous Fluvial System

Sediment delivery and supply are explicitly controlled by variations in broad-scale processes such as climate, tectonics and eustasy. These in turn influence fluvial processes and hinterland evolution. A bespoke multi-proxy approach (integrating apatite and zircon U-Pb geochronology, trace elements in apatite, and Pb-in-K-feldspar provenance tools) coupled with outcrop investigation is used to constrain the temporal trends in sediment delivery to channel sandstones of the fluvio-estuarine mid-Viséan Mullaghmore Sandstone Formation, Ireland. Provenance data indicate unique detrital signatures for all sampled horizons, indicating the fluctuating nature of sediment supply to this medium-sized basin. Tectonism and/or abrupt relative sea-level fall likely caused fluvial rejuvenation, resulting in local basement sourcing of the initial fill. Older and more distal sources, such as the Nagssugtoqidian Belt of East Greenland, become more prominent in stratigraphically younger channel sandstones suggesting catchment expansion. Paleoproterozoic to Mesoproterozoic sources are most dominant, yet the detrital grain cargo varies in each channel sandstone. Proximal sources such as the Donegal Batholith and Dalradian Supergroup are variable and appear to switch on and off. These signal shifts are likely the result of channel migration and paleoclimatic fluctuation. A monsoonal climate and large-scale wildfire events (evidenced by fusain) likely contributed to modify plant cover, intensify erosion, and increase run-off and sediment delivery rates from specific areas of the hinterland.

A Comprehensive Model Integrating the Stress Sensitivity for Pressure Transient Behavior Study on the Two-Zone System for Offshore Loose Sandstone Reservoirs

Permeability changes in the weakly consolidated sandstone formation, caused by sand migration, has a serious impact on the interpretation of well testing and production prediction. In this article, a two-zone comprehensive model is presented to describe the changes in permeability by integrating the produced sand, stress sensitivity characteristics. In this model, inner zone is modeled as a higher permeability radial reservoir because of the sand migration, while the outer zone is considered as a lower permeability reservoir. Besides, non-Newtonian fluid flow characteristics are considered as threshold pressure gradient in this paper. As a result, this bi-zone comprehensive model is built. The analytical solution to this composite model can be obtained using Laplace transformation, orthogonal transformation, and then the bottomhole pressure in real space can be solved by Stehfest and perturbation inversion techniques. Based on the oilfield cases validated in the oilfield data from the produced sand horizontal well, the flow regimes analysis shows seven flow regimes can be divided in this bi-zone model considering stress sensitive. In addition, the proposed new model is validated by the compassion results of traditional method without the complex factors. Besides, the effect related parameters of stress sensitivity coefficient, skin factor, permeability ratio and sanding radius on the typical curves of well-testing are analyzed. This work introduces two-zone composite model to reflect the variations of permeability caused by the produced sand in the unconsolidated sandstone formation, which can produce great influence on pressure transient behavior. Besides, this paper can also provide a more accurate reference for reservoir engineers in well test interpretation of loose sandstone reservoirs.

Utilizing Microseismic to Monitor Fracture Geometry in a Horizontal Well in a Tight Sandstone Formation

This paper presents the use of real-time microseismic (MS) monitoring to understand hydraulic fracturing of a horizontal well drilled in the minimum stress direction within a high-temperature high-pressure (HTHP) tight sandstone formation. The well achieved a reservoir contact of more than 3,500 ft. Careful planning of the monitoring well and treatment well setup enabled capture of high quality MS events resulting in useful information on the regional maximum horizontal stress and offers an understanding of the fracture geometry with respect to clusters and stage spacing in relation to fracture propagation and growth. The maximum horizontal stress based on MS events was found to be different from the expected value with fracture azimuth off by more than 25 degree among the stages. Transverse fracture propagation was observed with overlapping MS events across stages. Upward fracture height growth was dominant in tighter stages. MS fracture length and height in excess of 500 ft and 100 ft, respectively, were created for most of the stages resulting in stimulated volumes that are high. Bigger fracture jobs yielded longer fracture length and were more confined in height growth. MS events fracture lengths and heights were found to be on average 1.36 and 1.30 times, respectively, to those of pressure-match.

VULNERABILITY ANALYSIS OF UNDERGROUND AQUIFERS TO CONTAMINATION USING THE DRASTIC METHOD AND RISK DETERMINATION

Groundwater represents an important component in the supply of freshwater in several regions around the world. The contamination of these waters is a worrisome problem in the management of water resources. Since underground aquifers are vulnerable to contamination by human and industrial activities, including land use, the diagnosis associated with land use is critical for environmental management. The present study was carried out in the Uberaba sandstone formation, in which the vulnerability of the subterranean aquifers was determined using the DRASTIC method, by evaluating the interaction between the use and occupation of the land using a geographic information system. Thus, the risk of contamination of the underground aquifer was determined by evaluating the land use with the water quality and fertility. The tool applied in the present study proved effective for the diagnosis, management and action planning in the short and long term, with the intention of preserving these natural resources.

Leveraging Acoustic Logging for Identification & Quantification of Induced Fractures

The main objective of the acoustic logging in 15K openhole multistage fracturing completions (OH MSFs) is to identify the fracture initiation points behind pipe and contributing fractures to gas production. The technique will also help to understand the integrity of the OH packers. A well was identified to be a candidate for assessment through such technique. The selected well was one of the early 15K OH MSF completions in the region that was successfully implemented with the goal of hydrocarbon production at sustained commercial rates from a gas formation. The candidate well was drilled horizontally to achieve maximum contact in a tight gas sandstone formation. Similar wells in the region have seen many challenges of formation breakdown due to high formation stresses. The objective of this work is to use the acoustic data to better characterize fracture properties. The deployment of acoustic log technology can provide information of fractures initiation, contribution for the production and the reliability of the isolation packers between the stages. The candidate well was completed with five stages open-hole fracturing completion. As the well is in an open hole environment, a typical PLT survey provides the contribution of individual port in the cumulative production but provides limited or no information of contributing fractures behind the pipe. The technique of acoustic logging helped to determine the fracture initiation points in different stages. If fractures can be characterized more accurately, then flow paths and flow behaviors in the reservoir can be better delineated. The use of acoustic logging has helped to better understand the factors influencing fracture initiation in tight gas sandstone reservoirs; resulting in a better understanding of fractures density and decisions on future openhole length, number of fracturing stages, packers and frac ports placement.

Application of Various Machine Learning Techniques in Predicting Water Saturation in Tight Gas Sandstone Formation

Water saturation (Sw) is a vital factor for the hydrocarbon in-place calculations. Sw is usually calculated using different equations; however, its values have been inconsistent with the experimental results due to often incorrectness of their underlying assumptions. Moreover, the main hindrance remains in these approaches due to their strong reliance on experimental analysis which are expensive and time-consuming. This study introduces the application of different machine learning (ML) methods to predict Sw from the conventional well logs. Function networks (FN), support vector machine (SVM), and random forests (RF) were implemented to calculate the Sw using gamma-ray (GR) log, Neutron porosity (NPHI) log, and resistivity (Rt) log. A dataset of 782 points from two wells (Well-1 and Well-2) in tight gas sandstone formation was used to build and then validate the different ML models. The data set from Well-1 was applied for the ML models training and testing, then the unseen data from well-2 was used to validate the developed models. The results from FN, SVM and RF models showed their capability of accurately predicting the Sw from the conventional well logging data. The correlation coefficient (R) values between actual and estimated Sw from the FN model were found to be 0.85 and 0.83 compared to 0.98, and 0.95 from the RF model in the case of training and testing sets, respectively. SVM model shows an R-value of 0.95 and 0.85 in the different datasets. The average absolute percentage error (AAPE) was less than 8% in the three ML models. The ML models outperform the empirical correlations that have AAPE greater than 19%. This study provides ML applications to accurately forecast the water saturation using the readily available conventional well logs without additional core analysis or well site interventions.

A sensitivity analysis of a single extraction well from deep geothermal aquifers in the Cheshire Basin, UK

Deep hot sedimentary aquifers (HSAs) are targeted for geothermal exploitation in the Cheshire Basin, UK. In this study, a single extraction well targeting the Collyhurst Sandstone Formation was modelled on MATLAB coupling heat and fluid flux. The Collyhurst Sandstone Formation in the Crewe area of the Cheshire Basin is expected to be found at a depth of 2.8 to 3.5 km, and was chosen as an area for geothermal exploration due to the high demand for energy.Model results suggest that low-enthalpy, deep geothermal systems with thick HSAs are affected by both geological and engineering parameters. The results of this study highlight that the thermal gradient, hydraulic conductivity, production rate, length and position of the well screen are the key parameters capable of affecting the success and viability of any single well scheme. Poor planning during exploration and development can hinder the productivity of any single well scheme and these parameters must be considered to fully understand the risk. Engineering parameters, such as the length of the well screen, can be used during well planning to mitigate geological risks in the aquifer, whilst the results presented can also be used as a guide for energy potential under varying conditions.

Several Decades of Fluid Diversion Evolution, Is There a Good Solution?

The success of any matrix treatment depends upon the complete coverage of all zones. Consequently, the selection of the diversion technology is critical for treatment success. While various types of diverting agents are commercially available, the proper selection of optimal diverter depends on many factors, including well completion and history, compatibility with reservoir and treatment fluids, treatment objectives, operational constraints, and safety and environment considerations. The study will cover five major types of non-mechanical diversion technologies considered as potential solutions for offshore deepwater oil reservoirs: dynamic diversion, relative permeability modifiers (RPM), viscoelastic surfactants (VES), particulate diversion, and perforation diversion. All of them, but a dynamic diversion, are based on different chemicals or products to be added to the injected treatment fluid, and occasionally some can be complementary to each other. Given the offshore and deepwater settings, mechanical diversion techniques were not covered in the study, aiming to find a solution that would achieve acceptable diversion while minimizing operational effort, which would enable riser-less intervention and the use of light intervention techniques. This study was driven by the need to effectively stimulate a 500ft of a cased and perforated interval with a permeability of 500 md, and injection rate limited to 16 bpm due to completion limitations. The sandstone formation, with static in situ temperature of 270F, was far beyond the applicability of dynamic diversion and, to achieve the desired full coverage for the planned scale inhibition treatment required and combination with another diverter system was needed. The process applied included compatibility tests, regained permeability tests, and test well trials. Depending on the specific diversion product analyzed the testing procedures were adapted to obtain the information to properly guide to the optimal solution.