... modulus. We addressed these challenges through targeted modifications in our methodology, thereby enhancing the model's applicability across varied mineralogical and porosity conditions. Our findings indicate that the combination of texture and shape analyses, coupled with machine learning techniques, can...

... the difference between the ensemble of cases and the observed data across set number of iterations progressively converging the ensemble towards the historical data. Combining the text book implementation of ESMDA with Machine Learning (ML) techniques (See Saetrom, 2017) brought it robustness, to deliver...

...The 29th Formation Evaluation Symposium of Japan, September 12-13, 2024 Application of Bagging Ensemble Machine Learning Models to Predict Porosity of Sandstone Formations Using Well Log Data Kushan Sandunil 1, Ziad Bennour 1, Saaveethya Sivakumar 1, Hisham Ben Mahmud 2 and Ausama Giwelli 3, 4 1...

... issue that can arise during the process of machine learning is the phenomenon of overlearning. Overlearning is a phenomenon whereby the model becomes overly adapted to the features of the training data, rendering it unable to respond effectively to test or validation data that differs from the training...

...[Open] The 29th Formation Evaluation Symposium of Japan, September 12-13, 2024 Machine Learning-Based Classification for Mapping CO2 Presence using Seismic Data M Farid B M Amin 1, Dr. Satyabrata Nayak Parsuram 1, Debjyoti Das 2 , Modekhai Mordekhai 2, Taufan Rusady 2, Samiran Roy 2 and Kian Wei...

...The 29th Formation Evaluation Symposium of Japan, September 12-13, 2024 APPLICATION OF MACHINE LEARNING IN DOWNHOLE CO2 MEASUREMENT USING FORMATION TESTER Nishant Kumar1, Anis Turki1, Bin Dai1 and Amirul Afiq B Yaakob2 1.Halliburton Energy Services 2.Petronas Copyright 2024, held jointly...

... in a subsequent deterministic pre-stack elastic seismic inversion. This will extend the seismo-petrophysical characterization of the target sand from the specific location of well T3 to a larger surrounding area. 3) Machine Learning-Based Permeability Prediction and K-ARPT Construction: (i) To perform a machine...

...The 29th Formation Evaluation Symposium of Japan, September 12-13, 2024 Expanding The Use of Nuclear Magnetic Resonance (NMR) And Machine Learning for Reservoir Characterization of An Offshore Gas Field Rock Typing and Capillary Pressure Profiling Abraham J.S. Simanjuntak1., Johnny Y.C. Jin1...

... environment due to economic factors. This requires an innovative out-of-box solution to close the gap and narrow down the uncertainty in petrophysical evaluation. This paper will discuss few case studies utilizing artificial intelligence (AI) and machine learning (ML) workflow in petrophysical evaluation...

... of the three major lithology zones: Dunite, Gabbro, and Harzburgite. Another two automatic facies analysis methods were also attempted which are Class-Based Machine Learning (CBML) and Heterogeneous Rock Analysis (HRA) to compare the result with FaciesSpect. These methods have already used commercially...

... Introduction This paper presents the methodology used to deliver a consistent set of rock types, with petrophysical outputs of porosity, water saturation, and permeability, using a class-based machine learning (CbML) method. This novel tool is designed for summarizing the unique...

... of T1-T2 distribution may be varied for different types of rock, the rock typing analysis is necessary before performing 2D clustering analytics. Then an unsupervised machine learning algorithm is applied to the stacked T1T2 map for each rock type, leveraging the variations in individual pore-fluid...

.... upstream oil & gas solver core analysis geology artificial intelligence machine learning japan government mineral log analysis 28th formation evaluation symposium numerical solver multi-salinity analysis synthetic data equation ffri measurement geologist asia government well logging...

... evaluation machine learning carbonate rock rock type reservoir characterization calibration test section vug resistivity reservoir effectiveness fracture core calibration effectiveness evaluation 28th formation evaluation symposium dissolution vug chengdu separation Copyright 2023, held...

... of TRI. We examined the correlation between HSV color spaces and the ruggedness index G TRI . Third, we examined the use of a machine learning model to predict the ruggedness of the orthoimage in the Oga Coast, with the Itoshima Coast data, HSV color space data, and G TRI data as the supervisory data...

... in Triassic Chang 8 Formation, in Ansai Region, eastern Ordos Basin, a method of constructing pseudo capillary pressure from conventional well logging data based on machine learning method was proposed. Based on the analysis of the morphological feature of mercury injection capillary pressure (MICP) from core...

.... Results showed a significant improvement compared to more traditional approaches but could only be applied in modern wells with NMR data. The work presented in this paper extends this study to wells with no NMR, by using machine learning techniques, linear regression and python coding to predict changes...

...-2 to draw the multiple images of facies distribution constrained by well data using Generative Adversarial Network (GAN). reservoir characterization flow in porous media machine learning fluid dynamics deep learning 26th formation evaluation symposium estimation result sedimentary...

... machine learning classification pretest interpretation reservoir permeability evaluation intrinsic permeability permeability estimation mobility porosity lithofacies Classification lithofacies Japan Fluid Dynamics evaluation effective permeability 25th formation evaluation symposium...

... locations. The comparison was attained with respect to the variance estimation through the cross-validation procedure. It was concluded that Bayesian Kriging is more accurate prediction of formation permeability than the universal Kriging. geologic modeling geological modeling machine learning...