https://repositorio.ufba.br/handle/ri/2616 2026-04-17T03:00:59Z 2026-04-17T03:00:59Z Luz, Marcos Augusto Lima da https://repositorio.ufba.br/handle/ri/43507 2025-11-24T11:49:01Z 0009-09-30T00:00:00Z

Título: Automação sísmica híbrida: integração de inteligência artificial e métodos determinísticos na análise de velocidades. Autor(es): Luz, Marcos Augusto Lima da Primeiro Orientador: Vasconcelos, Marcos Alberto Rodrigues Abstract: This research presents a hybrid seismic automation methodology that integrates artificial intelligence techniques with deterministic methods for the automatic analysis and estimation of seismic velocity fields. The main goal is to optimize hydrocarbon exploration by enhancing model accuracy and ensuring operational safety throughout geological interpretation. Traditionally, the construction of the velocity field relies on manual picking from semblance panels, a subjective and time-consuming procedure that demands expert interpretation, especially under noisy or geologically complex conditions. The proposed workflow combines statistical and machine learning approaches in a sequential and integrated manner. The process begins with a sample pre-clustering technique, responsible for the preliminary structuring of the data and for automatically determining the optimal number of clusters. Next, the joint application of the K-means++ algorithm and Principal Component Analysis (PCA) enables efficient dimensionality reduction, improving data coherence and representativeness. In the deterministic stage, the Dix equation is employed to convert RMS velocities into interval velocities, which serve as training data for a Multilayer Perceptron (MLP) neural network. This supervised model performs the final adjustment of the velocity field, ensuring physical consistency, smoothness, and monotonic behavior. The hybrid nature of the methodology arises from the synergistic integration between deterministic physical modeling and adaptive artificial intelligence prediction. The proposed approach was validated using both synthetic models and real seismic data from the Gulf of Mexico, demonstrating robustness, stability, and applicability across diverse geological scenarios. The results confirm that the hybrid seismic automation framework provides more realistic and continuous velocity models, substantially reducing human intervention and improving interpretive efficiency in complex exploration environments. Editora / Evento / Instituição: Universidade Federal da Bahia Tipo: Tese

0009-09-30T00:00:00Z Matos, Maria Luíza Belmonte Bulcão de https://repositorio.ufba.br/handle/ri/42779 2025-08-25T12:48:29Z 0006-06-17T00:00:00Z

Título: Controle hidrográfico-biogeoquímico do pCO2 no Oceano Atlântico Sudoeste. Autor(es): Matos, Maria Luíza Belmonte Bulcão de Primeiro Orientador: Mendonça, Luís Felipe Ferreira de Abstract: This study aims to understand and investigate the physical and biological processes that influence the variability of pCOff in the Southwestern Atlantic Ocean, using numerical model data provided by the Copernicus Marine Service. For this purpose, time series of SST, SSS, Chl-a, and pCOff were analyzed from late 2021 to 2024. During summer, the southern Brazilian coast and continental shelf exhibit higher pCOff values compared to winter, due to the absence of the La Plata River Plume and increased input of warm waters driven by the Brazil Current. The extent of the La Plata Plume is a key factor in this region, as it regulates seasonal variability in pCOff. Its spatial influence during summer and winter significantly affects the concentrations of local variables. Analyzing this seasonal effect, the current patterns modulate the distribution of nutrients, Chl-a, and consequently pCOff along the coast and shelf. This dynamic leads to enhanced coastal productivity during autumn and winter, as well as greater COff uptake and consumption, characterizing the region as one of low pCOff, positively correlated with SST and SSS. Editora / Evento / Instituição: Universidade Federal da Bahia Tipo: Dissertação

0006-06-17T00:00:00Z Silva, Annie Gabrielle de Oliveira https://repositorio.ufba.br/handle/ri/42743 2025-08-18T13:24:46Z 0002-02-27T00:00:00Z

Título: Estimativa de parâmetros geoelétricos e gravimétricos através de inversão híbrida com os métodos Metropolis e Steepest Descent. Autor(es): Silva, Annie Gabrielle de Oliveira Primeiro Orientador: Dutra, Alanna Costa Abstract: The main objective of this dissertation was to test inversion methodologies applied to synthetic gravimetric and geoelectrical data, integrating the inversion and interpretation of these data for the study of a hydrogeological environment. Based on the theory of potential fields, both methods face inherent ambiguities in the interpretation of their anomalies, which can be caused by several possible sources. To mitigate these limitations, joint inversion was used, which simultaneously processes the data, generating models that represent the geometry of the density and resistivity interfaces and the distribution of these properties. The study was conducted in two main stages: the individual modeling of the geophysical data and the application of two joint inversions, a global one, using the Metropolis method, and a local one, using the Steepest Descent, both implemented through codes developed in Python. Four initial models were evaluated under three noise levels (no noise, 5% and 10%), generating 24 models using the Metropolis methodology, which served as input for the Steepest Descent, totaling 48 inverted models. The results allowed us to evaluate the quality of the inversion methodologies, identify the limitations of each geophysical method and visualize the geometry and distribution of properties in the geological environment, contributing to the understanding and development of more robust solutions for inverse problems. Editora / Evento / Instituição: Universidade Federal da Bahia Tipo: Dissertação

0002-02-27T00:00:00Z Vieira, Marcelo Querino e Silva do Prado https://repositorio.ufba.br/handle/ri/41125 2025-02-07T12:57:46Z 2024-11-28T00:00:00Z

Título: Extensão do critério de Barbieri em tomografia de tempos de trânsito não-linear. Autor(es): Vieira, Marcelo Querino e Silva do Prado Primeiro Orientador: Bassrei, Amin Abstract: This work offers two methods to evaluate the quality of traveltime tomography with regularization by derivative matrices and also to improve velocity models. Both methods are based on Barbieri's work, originally developed in medical tomography. The first, Barbieri Criterion (BC), considers forward modeling by straight rays, while the second one, Modified Barbieri Criterion (MBC), is ruled by Fermat's principle. Both use filtering by singular value decomposition to suppress dominant eigenimages by assuming that inversion algorithm errors are randomly located. Simulations with synthetic data showed that both methods had improved the solution in model RMS sense, even if high Gaussian noise was added to data. In general, MBC requires greater regularization than standard inversion. When applied to real data from Dom João Field, Recôncavo Basin, both methods had recovered similar models and with a higher resolution than the standard approach. Real data results were validated by seismic reflection data. Forward modeling was performed by ray tracing, based on analytical solution for differential ray equation, and by graphs, which is a simple application of Fermat's principle. Graph modeling proved to be superior as it always links sources and receivers regardless of velocity model. Numerical inversion was performed by generalized inverse and by a conjugate gradient method, which presented a lower computational cost without losing quality. Solution was stabilized by regularization by derivative matrices. Regularization factors were selected by L-curve and sine-Theta-curve, the latter developed in this work as an extension to the former, or by generalized cross-validation. Editora / Evento / Instituição: Universidade Federal da Bahia Tipo: Tese

2024-11-28T00:00:00Z