Blar i NTNU Open på forfatter "Berg, Carl Fredrik"
-
Fine-Tuning of Faster Region-Based Convolutional Neural Network for Automatic Core Plug Detection in Optical Core Images
Adelved, Dennis (Master thesis, 2020)Denne oppgaven presenterer to fremgangsmåter for å trene en Faster Region-based Convolutional Neural Network (Faster R-CNN) objektgjenkjenningsmodell. Denne modellen kan brukes til automatisk gjenkjenning av både CCA og ... -
Geometrically derived efficiency of slow immiscible displacement in porous media
Berg, Carl Fredrik; Slotte, Per Arne; Hosseinzade Khanamiri, Hamid (Peer reviewed; Journal article, 2020)The efficiency of a displacement is the fraction of applied work over the change in free energy. This displacement efficiency is essential for linking wettability to applied work during displacement processes. We quantify ... -
Identification of the Transition Between Two Phase Flow Regimes in Sphere Packs
Husøy, June Katrin Strand (Master thesis, 2018)This thesis presents an experimental investigation of the simultaneous immiscible two phase flow, in three dimensional porous media made up of glass beads. The objective of this thesis was to find the scaling relation ... -
Lattice Boltzmann Modeling of microfluidic two-phase flow with complex pore structure
Hannanu, Muhammad Iffan (Master thesis, 2019)In the past, the technology to capture a high-resolution image was not mature enough to enable pore-scale modeling and simulation. Additionally, including sufficient pore geometry complexities leads to a heavy computational ... -
Lithology classification of whole core CT scans using convolutional neural networks
Chawshin, Kurdistan; Berg, Carl Fredrik; Varagnolo, Damiano; Lopez, Olivier (Journal article; Peer reviewed, 2021) -
Lithology classification of whole core CT scans using convolutional neural networks
Chawshin, Kurdistan; Berg, Carl Fredrik; Varagnolo, Damiano; Lopez, Olivier (Peer reviewed; Journal article, 2021)X-ray computerized tomography (CT) images as digital representations of whole cores can provide valuable information on the composition and internal structure of cores extracted from wells. Incorporation of millimeter-scale ... -
Machine learning procedures for automatic well planning in reservoir simulation models
Kristoffersen, Brage Strand (Doctoral theses at NTNU;2021:404, Doctoral thesis, 2021)Simulation of reservoir models is a tool to optimize the development of an oil and gas reservoir. Part of the development is placement of wells in the reservoir, and this well placement optimization process is performed ... -
Multi-Phase Segmentation of Imaged Fluid Distribution in Porous Media Using Deep Learning
Vikdal, Ådne Årevik (Master thesis, 2021)Nøyaktig segmentering av CT-bilder er en nøkkelfaktor i utviklingen av Digital Rock Models. Tradisjonell segmenteringsarbeidsflyt er arbeidskrevende ettersom den er avhengig av manuell samhandling og kvalitetskontroll. De ... -
Optimal Well Inflow Modelling
Nakibuule, Maria Assumpta (Master thesis, 2021)Horisontale brønner (HWs) er utplassert i hydrokarbonreservoarer for å øke reservoarets kontringsområde og dermed utvinning. Trykktap langs brønnens lengde, og reservoarets heterogenitet skaper en ubalansert brønninnstrø ... -
Optimizing the Rate Balance Between Multiple CO2 Injectors for the Aurora Storage Site
Alali, Jalal (Master thesis, 2023)Den globale utfordringen med å redusere klimagassutslipp har nødvendiggjort utviklingen av effektive strategier for fangst og lagring av karbon (CCS). Denne oppgaven fokuserer på optimalisering av CO2-injeksjonsoperasjonen ... -
Predicting Inter-Pore Hydraulic Conductivity Using Convolutional Neural Network
Kårstad, Tormod (Master thesis, 2022)Det overordnede målet for denne oppgaven er å utvikle en metode for å generere presise estimat av strømningsegenskaper. Oppgaven beskriver et forsøk på å bruke et konvolusjonelt nevralt nettverk (CNN) til å predikere den ... -
Predicting Resistivity and Permeability of Porous Media Using Minkowski Functionals
Slotte, Per Arne; Berg, Carl Fredrik; Hosseinzade Khanamiri, Hamid (Journal article; Peer reviewed, 2019)Permeability and formation factor are important properties of a porous medium that only depend on pore space geometry, and it has been proposed that these transport properties may be predicted in terms of a set of geometric ... -
A quantitative study of salinity effect on water diffusion in n-alkane phases: from pore-scale experiments to molecular dynamic simulation
Yan, Lifei; Chang, Yuanhao; Hassanizadeh, S. Majid; Xiao, Senbo; Raoof, Amir; Berg, Carl Fredrik; He, Jianying (Peer reviewed; Journal article, 2022)Numerous mechanisms have been proposed to untangle the effect of a low concentration of dissolved salts in the water flooding medium. One potential mechanism for enhanced oil movement is proposed with osmosis effect, ... -
Reduced well path parameterization for optimization problems through machine learning
Kristoffersen, Brage Strand; Bellout, Mathias; Silva, Thiago Lima; Berg, Carl Fredrik (Peer reviewed; Journal article, 2021)In this work we apply a recently developed machine learning routine for automatic well planning to simplify well parameterization in reservoir simulation models. This reduced-order parameterization is shown to be beneficial ... -
Resistivity Estimation Using Convolutional Neural Networks
Bui, Richard Che (Master thesis, 2021)Denne oppgaven undersøker egnetheten av å anvende 2D tverrsnitt av 3D kjerneprøver i form av CT-scan data sammen med konvolusjonelle nevrale nettverk(CNN) for å bygge modeller for prediksjon av resistivitet. En av de viktige ... -
Shuffle & untangle: novel untangle methods for solving the tanglegram layout problem
Nguyen, van Nghia; Chawshin, Kurdistan; Berg, Carl Fredrik; Varagnolo, Damiano (Peer reviewed; Journal article, 2022)Motivation A tanglegram is a plot of two-tree-like diagrams, one facing the other, and having their labels connected by inter-tree edges. These two trees, which could be both phylogenetic trees and dendrograms stemming ... -
Tracer-Based Two-Phase Upscaling
Rosvoldaune, Stian Falkfjell (Master thesis, 2019)Nøyaktig oppskalering av strømning i reservoar er et viktig tema i olje og gass industrien på grunn av de store beregningskostnadene assosiert med å utføre simuleringer på komplekse reservoarmodeller. Målet med en oppskalering ... -
Upscaling polymer flooding using MRST
Danilova, Anna (Master thesis, 2016)Reservoir simulation models are widely used as a decision making tool in oil and gas industry. Modern technologies allow creating very detailed high-resolution models to represent the properties of a reservoir system as ...