Research

This work was done in collaboration with King Abdullah University of Science and Technology (KAUST). Research started through a student program which I took on as one of my internships while studying at the University of Waterloo. After succesful initial research I was invited back as a consultant to create numerous more Artificial Neural Networks (ANNs) for various combustion phenomena.

Once I started studying Computer Science at the Technical University of Delft I continued working and advising as an independent researcher. I did this out of curiosity and because my work provided the foundation for numerous other projects.

A Machine Learning Model for Predicting Threshold Sooting Index of Fuels Containing Alcohols and Ethers

DOI: 10.1016/j.fuel.2022.123941 Contribution In this project, my role as an advisor was crucial in the development of the artificial neural networks (ANNs) for predicting the threshold sooting index (TSI) of fuels. My background in computer science and data science was vital in ensuring the accuracy and reliability of the ANN model. This task required a meticulous approach to testing and validating the software, which was essential for proper and efficient data processing, model training, and prediction of outcomes....

A Methodology for Designing Octane Number of Fuels Using Genetic Algorithms and Artificial Neural Networks

DOI: 10.1021/acs.energyfuels.1c04052 Contribution In this research project, I made significant progress in three key areas. Firstly, I developed precise artificial neural networks (ANNs) for predicting Research Octane Number (RON) and Motor Octane Number (MON), achieving an impressive R2 of 0.99 for both, along with low mean absolute error (MAE) values. Secondly, I harnessed the power of genetic algorithms, significantly enhancing the optimization process by systematically reducing high octane component usage. Lastly, my advisory role in developing the polygonal method further refined the optimization process....

Predicting Ignition Quality of Oxygenated Fuels Using Artificial Neural Networks

DOI: 10.4271/04-14-02-0005 Contribution In our study, my primary contribution was developing and implementing machine learning models, particularly Artificial Neural Networks (ANNs), to predict the Derived Cetane Number (DCN) of oxygenated fuels. My role was instrumental in processing the data to accurately reflect the diverse chemical compositions of these fuels, a vital step for the ANNs to effectively learn and predict DCN values. Additionally, I introduced innovative techniques for model optimization, including a methodology for tuning hyperparameters and the use of a genetic algorithm, which significantly enhanced the robustness and accuracy of the final models....

Data Science Approach to Estimate Enthalpy of Formation of Cyclic Hydrocarbons

DOI: 10.1021/acs.jpca.0c02785 Contribution In this study, my role as an advisor was essential, particularly in guiding the development and optimization of machine learning models based on Support Vector Regression (SVR) for predicting the enthalpy of formation in cyclic hydrocarbons. I provided critical insights into the algorithmic design and hyperparameter selection of the SVR model, ensuring its robustness and accuracy. Additionally, I played a key role in reviewing the paper, contributing to the refinement of its scientific communication and ensuring the clarity and precision of the technical content presented....

Machine Learning to Predict Standard Enthalpy of Formation of Hydrocarbons

DOI: 10.1021/acs.jpca.9b04771 Contribution In this study, my key contribution was developing and implementing Artificial Neural Networks (ANNs) and Support Vector Regression (SVR) models. These models were engineered to accurately estimate the standard enthalpy of formation for a variety of hydrocarbons. I optimized these models using a two-level K-fold cross-validation method, enhancing both accuracy and reliability. Additionally, I was responsible for defining the hyperparameter search space for these models, ensuring a balance between model complexity and generalizability....

Predicting Octane Number Using Nuclear Magnetic Resonance Spectroscopy and Artificial Neural Networks

DOI: 10.1021/acs.energyfuels.8b00556 Contribution In this work, I focused on harnessing Artificial Neural Networks (ANNs) to accurately predict the Research Octane Number (RON) and Motor Octane Number (MON) for various fuel blends, a significant step forward in understanding complex fuel behaviors. My work centered around developing and fine-tuning the ANN models, integrating molecular parameters obtained from 1H Nuclear Magnetic Resonance (NMR) spectroscopy data. This integration was crucial for capturing the intricate relationships between molecular compositions of fuels and their octane ratings, especially in the context of non-linear variations observed with ethanol-blended gasoline....