| Ref.No: | 61517400 |
| Start date: | 17.07.2024 |
| End date: | 16.12.2026 |
| Approval date: | 10.07.2024 |
| Department: | CHEMICAL ENGINEERING |
| Sector: | MATERIALS SCIENCE AND ENGINEERING |
| Financier: | 5η ΠΡΟΚΗΡΥΞΗ ΕΛΙΔΕΚ Υ.Δ., ELIDEK |
| Budget: | 26.100,00 € |
| Public key: | 90Ο646ΨΖΣ4-1ΝΔ |
| Scientific Responsible: | Prof. THEODOROU |
| Email: | doros@central.ntua.gr |
| Description: | THE DEVELOPMENT OF MODERN, INNOVATIVE TECHNOLOGIES REQUIRES DESIGNING NEW MATERIALS WITH CONTROLLED PROPERTIES, NECESSITATING A FUNDAMENTAL UNDERSTANDING OF INTERACTIONS AND MECHANISMS THAT DETERMINE MACROSCOPIC BEHAVIOR. MOLECULAR SIMULATION IS AN EFFECTIVE AND RELIABLE TOOL FOR STUDYING MOLECULAR MECHANISMS AND PREDICTING MATERIAL PROPERTIES. THE INTEGRATION OF MACHINE LEARNING (ML) IN MOLECULAR SIMULATIONS HAS THE POTENTIAL TO EXTEND COMPUTATIONAL METHODS AND ASSIST IN THE STUDY OF COMPLEX MATERIALS. THIS PHD THESIS WILL DEVELOP AND APPLY SYSTEMATIC METHODOLOGIES COMBINING MOLECULAR SIMULATIONS AND ML ALGORITHMS, TO CREATE RELIABLE COARSE-GRAINED (CG) MODELS. ML MODELS OFFER GREATER FLEXIBILITY AND EXPRESSIVENESS COMPARED TO TRADITIONAL CG MODELS, ENABLING ACCURATE REPRESENTATION OF COMPLEX ENERGY SURFACES AND MANY-BODY INTERACTIONS. THE AIM IS TO CREATE INNOVATIVE COMPUTATIONAL METHODOLOGIES USING AI FOR SIMULATING MATERIALS ACROSS DIFFERENT TIMESCALES AND ELUCIDATING THE STRUCTURE-PROPERTY RELATIONSHIP NECESSARY FOR MOLECULAR-LEVEL MATERIAL DESIGN. |
