(7j) Advanced Materials Design Using Molecular Simulation, Evolutionary Computing and Machine Learning | AIChE

(7j) Advanced Materials Design Using Molecular Simulation, Evolutionary Computing and Machine Learning


Patra, T. K. - Presenter, The University of Akron
Research Interests: Polymer and Soft Matter; Glass Transiton; Self-Assemly, Phase Transition and Free Energy of Materials; High Throughput Materials Design; Machine Learning

Teaching Interests: Thermodynamics, Statistical Mechanics, Theory of Liquids, Polymer Physics, Numerical Methods, Molecular Modeling

Abstract: Molecular simulation has emerged as a remarkable technique for investigating structure-property relationships in a wide variety of materials. Combining it with evolution based optimization methods such as genetic algorithm can provide tremendous opportunity for discovering new materials of extremal properties. However, the major roadblock in this direction is that the determination of a molecular property via simulations is very slow. Alternatively, machine learning tools have been progressively adopted by the materials science community to accelerate design of materials with targeted properties. Nevertheless, in the search for new materials exhibiting properties and performance beyond that previously achieved, machine learning approaches are frequently limited by two major shortcomings. First, they are intrinsically interpolative. They are therefore better suited to the prediction of properties within the known range of accessible behavior than to the discovery of new materials with extremal behavior. Second, they require the availability of large datasets, which in some fields are not available and would be prohibitively expensive to produce. Here we describe a new strategy for combining genetic algorithms, machine learning, and molecular simulation to discover materials with extremal properties in the absence of pre-existing data. Predictions from progressively constructed machine learning tools are employed to bias the evolution of a genetic algorithm, with fitness evaluations performed via direct molecular dynamics simulation. We survey several materials design problems, in particular, polymer compatabilizer, porous polymeric materials, and polymer glasses, with in this framework. Further development of this computational framework and its implication to future material design will be discussed in this presentaion. In additon, we employ molecular simulation to provide useful guidelines for designing polyelectrolytes and polymer nanocomposites.


This paper has an Extended Abstract file available; you must purchase the conference proceedings to access it.


Do you already own this?



AIChE Pro Members $150.00
AIChE Graduate Student Members Free
AIChE Undergraduate Student Members Free
AIChE Explorer Members $225.00
Non-Members $225.00