https://dspace.univ-ouargla.dz/jspui/handle/123456789/253 2026-05-09T14:41:20Z https://dspace.univ-ouargla.dz/jspui/handle/123456789/40335 Titre: Evaluation des modeles de prediction des parametres petro physique des reservoirs petroliers a partir des donnees de diagraphies : Cas du Champ de Hassi Messaoud Auteur(s): Bouzenad, Hadjer Tesnim Résumé: This study evaluates the performance of four machine learning models (Ridge, Bagging, Extra Trees, and XGBoost) for predicting porosity, permeability, and water saturation from well log data in the Cambrian reservoir of the Hassi Messaoud field. The objective is to identify which model performs best, depending on the nature and availability of input data. XGBoost showed the highest accuracy for porosity prediction (R² = 0.997), while Extra Trees performed best for permeability and saturation (R² > 0.97). The workflow includes feature selection based on Spearman correlation and feature importance, along with cross-validation. The results highlight the potential of non- linear algorithms while also acknowledging limitations due to data heterogeneity across wells 2025-01-01T00:00:00Z https://dspace.univ-ouargla.dz/jspui/handle/123456789/40109 Titre: Application of Noise Suppression Methods to Potential Field Data from The Gulf of Aden: Tectonic and Structural Interpretation Auteur(s): ALMINE, Abdelmalik Résumé: Numerous studies have utilized edge detection filters based on potential field derivatives, ratios, and statistical methods to assess geological structures and offer interpretations. However, the varied responses from these filters can lead to misinterpretations, making it challenging for users to select the most effective filter. To ensure accurate evaluations and prevent misinterpretations, it is crucial to simultaneously assess filters on the same theoretical models. This study introduces new edge detection filters based on enhanced algebraic and geometric functions applied to potential field data derivatives. The performance of 23 edge detection candidates was evaluated using 2.5D gravity models and magnetic compositional data under different scenarios. The results indicate that the modified fast sigmoid function (MFSED) outperforms the other 22 filters in terms of accuracy for both gravity and magnetic models. This comparison enables the inference of tectonic structural patterns by generating multiple results from different filters and examining artefacts. Additionally, edge enhancement filters were applied to free-air and magnetic gravity data of the Eden Fault, leading to the identification of boundaries related to seafloor spreading, divergent plates, and transform faults. These boundaries align well with the locations of earthquakes at shallow depths. The study suggests that the local fault system contributes to the dynamics of the Gulf of Aden, with seismic activities along normal fault zones and their transformation being associated with defined structural boundaries. This application of new edge detection filters offers a novel approach to studying faulting processes through multiple monitoring techniques. Description: UNVERSTE KASDI MERBAH OURAGLA Faculty of Hydrocarbons , Renewable Energy and Earth and Universe Sciences Department of Earth and Universe Sciences Dissertation Academic Master Domain: Earth and Universe Sciences Field: Geology Specialty: Geology of Sedimentary Basins 2024-01-01T00:00:00Z https://dspace.univ-ouargla.dz/jspui/handle/123456789/39719 Titre: Porosity Prediction Using An Artificial Intelligence Random Forest Mechanism At The Menzel Ladjmet Field - Berkine Basin - Auteur(s): LEHELLA, OTMAN Résumé: The note discusses the use of artificial intelligence in predicting porosity using the Random Forest mechanism. Challenges to traditional porosity predictions and the importance of applying artificial intelligence in this context are reviewed. Then a detailed explanation of the Random Forest mechanism and how to use it in predicting porosity was presented. Previous studies that demonstrated the effectiveness of using the Random Forest mechanism in improving the accuracy of porosity prediction are discussed. However, the use of AI in porosity prediction faces challenges such as obtaining high-quality training data and noise processing. It is emphasized that the use of artificial intelligence in porosity prediction represents a huge development in the scientific and engineering fields. This technique can improve our understanding of rock properties and contribute to improving our ability to predict porosity with greater accuracy. It can also promote resource exploration and extraction, achieve cost savings and reduce environmental impact. Description: KASDI MERBAH UNIVERSITY – OUARGLA FACULTY OF HYDROCARBONS, RENEWABLE ENERGY AND EARTH AND UNIVERSE SCIENCES DEPARTMENT OF EARTH AND UNIVERSE SCIENCES END OF STUDY MEMORY With A View To Obtaining The Master's Degree In Geology Option: Petroleum Geology 2023-01-01T00:00:00Z https://dspace.univ-ouargla.dz/jspui/handle/123456789/39595 Titre: Microfaunes des Marnes de Gratenes(Tiaret,algérie):impact paléonvironnemental Auteur(s): Ben Abde Lhafide, Djafar Résumé: Le présent travail est consacré à une étude micropaléontologique (foraminifères), et paléoenvironnementale de la Formation des Marnes d’Aïn Gnega au nord de Tiaret (Algérie nord- occidentale). Cette formation est d'âge Jurassique supérieur ; riche en foraminifères benthiques. L'étude de ces foraminifères montre une population composée de 15 spécimens, dominée par des formes hyalines et agglutinées. Sur le plan biostratigraphique, les assemblages définis indiquent un âge Jurassique supérieur ; alors que sur le plan paléoécologique ; quatre assemblages ont été individualisés. Ces derniers suggèrent des changements paléoenvironnementaux liés aux variations tectono- eustatiques. Description: UNIVERSITE KASDI MERBAH-OUARGLA FACULTE DES HYDROCARBURES DES ENERGIE RENOUVELABLES ET DES SCIENCES DE LA TERRE ET DE L UNIVERS DEPARTEMENT DES SCIENCES DE LA TERRE ET DE L UNIVERS Mémoire de Master Académique Domaine : Sciènes de la Terre et de l Univers Spécialité:Ensembles des Bassins Sédimentaires Filiére:Géologie 2023-01-01T00:00:00Z