About this Abstract |
| Meeting |
2027 TMS Annual Meeting & Exhibition
|
| Symposium
|
AI-Enabled Materials Processing: Integrating Accelerated Experimental Workflows and Processing-Aware Machine Learning
|
| Presentation Title |
The Optimization of Tar Sand Digestion by a Locally Fabricated Tar Sand Digester |
| Author(s) |
Lasisi Umoru, D Olaoye, Ayodele Abeeb Daniyan, Oladeji Ige |
| On-Site Speaker (Planned) |
Lasisi Umoru |
| Abstract Scope |
The growing global demand for alternative energy sources has heightened interest in unconventional petroleum resources such as tar sands. Nigeria’s vast deposits, particularly in Ondo State, remain underutilized due to environmental and technical challenges. This study investigates the optimization prediction of tar sand digestion using a locally fabricated laboratory-scale Tar Sand Digester at the Central Technological and Laboratory Workshop, Obafemi Awolowo University, Nigeria. Tar sands sourced from Agbabu, Ondo State, were analyzed to assess emissions, effluents, and residues generated during digestion. A key innovation of the research is the integration of Artificial Intelligence (AI), specifically Artificial Neural Networks (ANNs), to predict environmental outcomes based on experimental parameters and outputs. The AI models trained on these data effectively forecasted pollution profiles under different operating conditions. The results demonstrate the potential of AI in optimization, offering a framework for sustainable tar sand exploitation in Nigeria, informing policy, industrial design, and regulatory decision-making. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Computational Materials Science & Engineering, Machine Learning, Process Technology |