Depositional conditioning of three dimensional training images: Improving the reproduction and representation of architectural elements in sand-dominated fluvial reservoir models

Mullins, James R.; Pringle, Jamie K.; Howell, John; Clarke, Stuart M.

doi:10.1016/j.marpetgeo.2019.104156

Cited by 11 publications

(6 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the reservoir performance of ice‐contact deltas can be negatively affected by meso‐scale heterogeneities which are directly linked to the depositional processes taking place at the ice margin (e.g. Mitten et al ., 2020). Evidence for ice overriding, bulldozing and mixing by ice‐margin oscillations are clearly visible in delta morphology (Fig.…”

Section: Discussionmentioning

confidence: 99%

Cool deltas: Sedimentological, geomorphological and geophysical characterization of ice‐contact deltas and implications for their reservoir properties (Salpausselkä, Finland)

et al. 2021

View full text Add to dashboard Cite

Sediments deposited by glacial meltwaters (for example, ice-contact delta deposits) form permeable packages in the subsurface that can act as reservoirs for both water and hydrocarbons. They are also an important source of aggregate for the construction industry. As reservoirs they are challenging to characterize in terms of their structure, flow and storage properties due to their complex depositional history. In this study, ice-contact deltas of Salpausselkä I and II end moraines in Southern Finland are studied using a combination of geomorphological mapping, sedimentological studies and near surface geophysical methods. Sedimentary logs from isolated outcrops were correlated to ground penetrating radar (GPR) profiles to unravel the internal structure and depositional history of these ice-contact deltas. Subsequently, electrical resistivity tomography (ERT) and gravity data were analysed to estimate the depth to bedrock and to model porosity distribution within the sediments. Results of the study suggest that the delta deposits have a broad range of porosities (10 to 42%) with lowest values found in the bottomset beds. The most variable porosities are in the subaqueous ice-contact-fan zone, and consistently high porosities occur in delta foreset/topset facies. Detailed sedimentary logging linked to the GPR data shows heterogeneities such as mud drapes on foresets and kettle holes which are below the resolution of ERT and gravity methods but significantly affect reservoir properties of the deltas. Moreover, oscillation of the ice-margin may have introduced larger heterogeneities (for example, buried ice marginal ridges, or eskers) into the sedimentary sequence which are atypical for other Gilbert-type deltas. Finally, subglacially sculpted, highly variable bedrock topography exerts a major control on sediment distribution within the delta making reservoir volume and quality less predictable. This work has implications for present-day freshwater aquifers and low enthalpy geothermal energy in southern Finland and other deglaciated regions, as well as hydrocarbon exploration of analogous deposits in the subsurface from Pleistocene and pre-Pleistocene glaciogenic sequences.

show abstract

Section: Discussionmentioning

confidence: 99%

Cool deltas: Sedimentological, geomorphological and geophysical characterization of ice‐contact deltas and implications for their reservoir properties (Salpausselkä, Finland)

et al. 2021

View full text Add to dashboard Cite

show abstract

“…It is also worth noting that whilst many have investigated lithological layering, few, if any, have considered realistic geological features or facies modelling which are typically incorporated into reservoir modelling in conventional geothermal 2023)) or petroleum applications (e.g. Abdelmaksoud et al (2019); Mitten et al (2020)) and impact the hydraulic/thermal subsurface characteristics. It is difficult to quantify the impact such systems could have on the performance of a DBHE; however, it is likely in highly heterogeneous systems which could correspond to variable thermal properties, degree of fluid saturation or groundwater flow would be most influential on results.…”

Section: Impact Of Geological Parametersmentioning

confidence: 99%

A comprehensive review of deep borehole heat exchangers (DBHEs): subsurface modelling studies and applications

Kolo,

Brown,

Nibbs

et al. 2024

Geotherm Energy

View full text Add to dashboard Cite

Deep borehole heat exchangers (DBHEs) with depths exceeding 500 m have been researched comprehensively in the literature, focusing on both applications and subsurface modelling. This review focuses on conventional (vertical) DBHEs and provides a critical literature survey to analyse (i) methodologies for modelling; (ii) results from heat extraction modelling; (iii) results from modelling deep borehole thermal energy storage; (iv) results from heating and cooling models; and (v) real case studies. Numerical models generally compare well to analytical models whilst maintaining more flexibility, but often with increased computational resources. Whilst in-situ geological parameters cannot be readily modified without resorting to well stimulation techniques (e.g. hydraulic or chemical stimulation), engineering system parameters (such as mass flow rate of the heat transfer fluid) can be optimised to increase thermal yield and overall system performance, and minimise pressure drops. In this active research area, gaps remain, such as limited detailed studies into the effects of geological heterogeneity on heat extraction. Other less studied areas include: DBHE arrays, boundary conditions and modes of operation. A small number of studies have been conducted to investigate the potential for deep borehole thermal energy storage (BTES) and an overview of storage efficiency metrics is provided herein to bring consistency to the reporting of thermal energy storage performance of such systems. The modifications required to accommodate cooling loads are also presented. Finally, the active field of DBHE research is generating a growing number of case studies, particularly in areas with low-cost drilling supply chains or abandoned hydrocarbon or geothermal wells suitable for repurposing. Existing and planned projects are thus presented for conventional (vertical) DBHEs. Despite growing interest in this area of research, further work is needed to explore DBHE systems for cooling and thermal energy storage.

show abstract

“…Most methods for object instance segmentation require all training instances to be labeled with a segmentation mask [34]. Image training is frequently used to decide what heterogeneity should be included in a multipoint statistical reservoir model [35]. In this study, the training image is built based on two different objects, namely plastic bottles and plastic bags.…”

Section: Training Image Samplesmentioning

confidence: 99%

Faster R-CNN Algorithm for Detection of Plastic Garbage in the Ocean: A Case for Turtle Preservation

Faisal¹,

Chaudhury

Sankaran

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Turtles are one of the ancient marine animals that live today. However, the population is threatened with extinction, so its existence needs to be protected and preserved because turtles often eat plastic waste in the ocean whose shape, texture, and color are similar to jellyfish. The technology in the computer vision area can be used to find the solution related to the case of reducing plastics and bottles trash in the ocean by implementing robotics. The region-based Convolutional Neural Network (CNN) is the latest image segmentation and has good detection accuracy based on the Faster R-CNN algorithm. In this study, the training image was built based on two different objects, namely plastic bottles and plastic bags. The target is that the two objects can be recognized even if there are other objects in the vicinity, or the image quality will be affected by the color of the seawater. The results obtained are that plastic objects and bottles can be recognized correctly in the picture. Of the five-color hues tested, the results show that the object detection process is valid on the average color hue, sepia, bandicoot, and grayscale. In contrast, the object detection process is invalid in black-and-white tones. The test results shown in the table explain that the object detection that gets the highest results is an image with normal coloring, while the lowest value is on bandicoot. The average accuracy of all types of images tested is 96.50. However, the accuracy value still needs to be improved to apply feasibility permanently to hardware such as diving robots.

show abstract

Depositional conditioning of three dimensional training images: Improving the reproduction and representation of architectural elements in sand-dominated fluvial reservoir models

Cited by 11 publications

References 69 publications

Cool deltas: Sedimentological, geomorphological and geophysical characterization of ice‐contact deltas and implications for their reservoir properties (Salpausselkä, Finland)

Cool deltas: Sedimentological, geomorphological and geophysical characterization of ice‐contact deltas and implications for their reservoir properties (Salpausselkä, Finland)

A comprehensive review of deep borehole heat exchangers (DBHEs): subsurface modelling studies and applications

Faster R-CNN Algorithm for Detection of Plastic Garbage in the Ocean: A Case for Turtle Preservation

Contact Info

Product

Resources

About