Teses de Mestrado ESTiG
URI permanente desta comunidade:
Navegar
Percorrer Teses de Mestrado ESTiG por orientador "Abranches, João Dinis Oliveira"
A mostrar 1 - 3 de 3
Resultados por página
Opções de ordenação
- Gaussian processes in the description of aqueous electrolyte solutionsPublication . Josefovicz, Matheus; Pinho, Simão; Abranches, João Dinis Oliveira; Watanabe , Erica Roberta Lovo da RochaThis work investigates the use of Gaussian Processes (GPs), a Bayesian machine learning method, for predicting osmotic (OC) and activity coefficients (AC) of electrolytes in aqueous solution at 298.15 K. A comprehensive database was constructed from recommended data reported in the literature, containing osmotic and activity coefficients for 1:1, 1:2, and 2:1 electrolytes over a wide range of molalities. The descriptors employed consist exclusively of sigma profiles of cations and anions, generated from COSMO calculations based on Density Functional Theory (DFT), which are combined with electrolyte molality in the first model and with ionic strength in the second model. After a rigorous data curation step that excluded ions affected by the use of standard ionic radii in COSMOtherm, the final dataset comprised 82 electrolytes and 45 distinct ions. The GP models were trained by testing different kernel functions and normalization strategies, with a stratified division of the data into training and validation sets, while the test set was specifically defined to contain representative electrolytes from the dataset. Predictive performance was evaluated using the coefficient of determination (R²) and the Mean Squared Log Error (MSLE). The results demonstrate that GPs can interpolate osmotic and activity coefficients with high accuracy across different classes of electrolytes and molality ranges, achieving R² values close to 1.0 for both the training and validation datasets. As predictive capacity increases, interpolative capacity decreases; however, the model was still able to predict thermodynamic data with good accuracy, achieving R² for test set equal to 0.9013 for OC, and equal to 0.9412 for AC. These findings indicate that the combination of sigma profiles and Gaussian Processes constitutes a promising and computationally efficient approach for predicting thermodynamic properties of aqueous electrolyte solutions, reducing reliance on extensive experimental datasets and offering an interesting alternative to traditional thermodynamic models.
- Green solvents and AI-driven models for recycling 3D printing wastePublication . Costa, Samuel Felipe Martins; Abranches, João Dinis Oliveira; Ferreira , Olga; Patrício, Patrícia Santiago de OliveiraThe increasing adoption of 3D printing, particularly using polylactic acid (PLA), has led to a significant rise in plastic waste, calling for the development of sustainable recycling solutions. Among recycling approaches, the physical method is gaining more space, especially with advances in the use of green solvents. Therefore, this study examines the application of green solvents and artificial intelligence (AI)-driven models for the dissolution and recovery of PLA from 3D printing waste. In particular, the research focuses on identifying environmentally friendly solvents, based on qualitative PLA dissolution data, using machine learning (ML) techniques to find and predict the best solvents for dissolving PLA while minimizing contamination from additives and other polymers. Among the solvents initially investigated, dimethylformamide (DMF), chloroform (CLFM), dimethyl carbonate (DC), and isosorbide dimethyl (IDE) achieved complete dissolution of PLA after 24 h at 50 °C. Dissolution behavior was further examined above and below the PLA glass transition temperature (Tg = 55 - 60 °C), with only ethyl acetate (EtAce) changing from a poor solvent to a good solvent with increasing temperature. The Hansen Solubility Parameters (HSP) and the infinite dilution activity coefficients (γ∞) predicted by COSMO-RS were employed to rationalize the dissolution behavior, showing unsatisfactory discrimination between good and poor solvents. Subsequently, ML models were applied to the experimental dataset to identify additional suitable solvents. The results demonstrated excellent predictive performance, correctly classifying good and poor solvents for PLA and identifying new good solvents as acetonitrile (ACN), methyl acetate (MeAce), and dichloromethane (DCM). Overall, by integrating solvent-based recycling with AI-driven optimization, this work showed potential solvents to enhance the circular economy of PLA-based materials, promoting more sustainable and effective waste management practices.
- The application of active learning methodologies in the description of the salt effect on the solubility of amino acidsPublication . Piske, Christopher Andrey; Abranches, João Dinis Oliveira; Pinho, Simão; Leite, Priscilla dos Santos GaschiIn aqueous solutions containing electrolytes, ions influence both the solubility and the stability of biomolecules. However, inconsistencies across published data highlight the need for a critical review. To address this, a database was constructed on the solubility of glycine in electrolyte solutions spanning from 1996 to 2024, and the experimental data were critically evaluated. Gaussian Process (GP) models were implemented to analyze, predict, and validate solubility behavior. The GP model successfully captures salting-in and salting-out trends, along with specific ion effects reported in the literature. It also provides predictive uncertainty estimates that help identify potentially inconsistent data points or sets. This uncertainty-based analysis enables the reconciliation of conflicting datasets and helps prioritize new experimental measurements in regions where data are sparse or less reliable. By applying a data-filtering method that removes experimental points falling outside the uncertainty range of the model, the influence of inconsistent values is reduced. This results in a more robust model fit and improved prediction accuracy. Therefore, the GP establishes a quantitative foundation for consolidating the current knowledge on the solubility of glycine in saline solutions, identifying methodological inconsistencies in the literature.