Research@IITD: PyGGi

Researchers at IIT Delhi have developed a first of its kind machine learning software -- Python for Glass Genomics (PyGGi) for predicting and optimizing glass compositions.

Priced at Rs 75,000 the software, the first version of PyGGi was launched on August 2. Besides cutting on the cost, this machine learning algorithms will also help in reducing the manufacture time because of giving away of the usual trial and errors.

PyGGi will allow researchers and companies to easily predict various glass properties like density, elastic modulus, bulk modulus, shear modulus and Poisson's ratio at the tap of a button. The models that have been used for property prediction have been trained over a large experimental data set using algorithms like Neural Network and Gaussian Process.

"In glasses, understanding and predicting the composition–structure–property relationship is the key to developing novel glassy systems. Data-driven approaches such as machine learning can prove key to predict structure and composition of glasses for tailored applications. PyGGi is a software package developed using python, for predicting and optimizing the properties of inorganic glasses," says Prof N. M. Anoop Krishnan, one of the Project Investigators(PI)

The models that have been used in PyGGi for property prediction have been trained over a large experimental data set using algorithms like Neural Network and Gaussian Process. The built-in range function allows analysing the variation of these properties as the composition of the glass changes over a range of its oxide proportions. The plotting tools can then be used to get a clearer picture of the variation of the properties with respect to other variables. PyGGi can be used for predicting and designing new glasses tailored for specific applications.

"PyGGi will be constantly updated and upgraded to meet the industrial and academic challenges in the field of glass science. We are also open to developing raw modules based on user requirements. These modules can be exclusively given to users who support the research in PyGGi, says Prof Hariprasad Kodamana, who is the second PI of the project.

The team will work on new capabilities that include additional properties such as refractive index, abbe number and liquidus temperature. The researchers are also trying to extend this scalable approach to other materials as well with aim of accelerating materials discovery for healthcare, energy, and automotive applications.