Congratulations Kwabena Asiedu Koranteng

Kwabena Asiedu Koranteng is a graduating MPhil student in Materials Engineering at KNUST. His research focuses on the intersection of computational materials science and engineering, deep learning, and energy materials design.

During his MPhil studies, he developed explainable graph neural networks (GNNs) and transformer-based architectures for structure–property prediction in metal–organic frameworks (MOFs)—materials with immense potential for gas adsorption and energy storage applications. His work explored how deep learning, cooperative game theory, and attention mechanisms can uncover new design principles for next-generation materials, improving the interpretability and reliability of AI-driven materials discovery.

Through his research, the model architectures developed can explain model predictions at the atomic level, showing how individual atoms in a crystal structure contribute to the overall property of the material. His thesis contributes to advancing explainable AI methodologies in materials science, an emerging area at the frontier of materials informatics and computational discovery.

Kwabena attributes much of his success to self-driven learning, passion for coding the math correctly, and the mentorship of dedicated advisors. He expresses deep gratitude to Prof. Luke Achenie, whose guidance was instrumental in shaping his research; Dr Emmanuel Kwesi Arthur, who encouraged him to begin this journey; and Prof. Nana Yaw Asiedu, who helped him appreciate the depth and potential of computational modelling in materials research.

The KNUST Engineering Education Project (KEEP) has been instrumental to his academic journey, providing financial and institutional support that made his research possible. Kwabena remains immensely grateful to the KEEP management and staff for their continuous encouragement and belief in his vision.

Looking ahead, Kwabena intends to continue his work in computational and explainable materials design, focusing on agentic discovery frameworks for energy storage materials. He aims to contribute to the global push for data-driven, sustainable materials innovation through advanced modelling and machine intelligence