Python for Glass Genomics
Data-driven approaches such as machine learning have gained a lot of interest in the recent past and can prove key to predict structure and composition of materials for tailored applications. To this extent, PyGGi aids accelerated innovation in the areas of glass science and technology using state-of-the-art machine learning and artificial intelligence.
PyGGi has various packages that allows easy discovery of material knowledge. PyGGi Bank is a large database of glass properties, which allows users to contribute their data. PyGGi Seer predicts various glass properties using machine learning algorithms, like density, elastic moduli, glass transition temperature, hardness, and several others, as a function of just the glass composition. PyGGi Zen is an optimization package that allows the discovery of glasses with targeted properties and compositions, at the tap of a button. PyGGi is continuously evolving—much more features are being added with the sole of aim accelerating glass innovation to meet the requirements of the growing infrastructure and economy.
PyGGi also aims to develop an online glass community through the Forum, which can be a platform for knowledge exchange, interactions, and collaborations.
PyGGi thanks the IIT Delhi HPC facility for computational and storage resources.
Department of Civil Engineering,
Department of Materials Science and Engineering (Joint Appointment),
Indian Institute of Technology Delhi
Computer Services Center, IIT Delhi
Department of Chemical Engineering, IIT Delhi
Dept. of Civil and Environmental Engineering,
University of California Los Angeles
Dept. of Materials Science and Engineering IIT Delhi
PyGGi is developed and maintained by an active group of researchers and scholars. Some of the main contributors of the project are mentioned below.