The researchers of Indian Institute of Technology (IIT-D) Delhi have developed a first of its kind machine learning software - 'Python for Glass Genomics' (PyGGi) for predicting and optimising glass compositions.
The machine learning software which was launched on Friday will allow researchers and companies to easily predict glasses with superior properties such as scratch and crack resistance at the tap of a button.
The main objective behind the PyGGi is to reduce the cost in predicting new glasses for tailored applications and the software will also help in making new glasses cheaper and affordable.
"How many of us have wished for mobile phone screens or glass utensils or window panes that resist damage? Despite two thousand years of usage, developing glasses with tailored properties is still an open challenge," said Professor N M Anoop Krishnan, Civil Engineer Department and project investigator of the project, adding to address this problem, the researchers has developed this software which will help to develop novel glasses such as bullet proof and scratch resistant glasses.
"Understanding and predicting the composition-structure-property relationship is the key to developing novel glasses such as bullet proof and scratch resistant glasses.
Data-driven approaches such as machine learning and artificial intelligence can exploit our existing knowledge to predict glasses for tailored applications. PyGGi is a software package developed using python, for predicting and optimizing the properties of inorganic glasses," Krishnan added.
"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," said another project member, Hariprasad Kodamana, professor, Chemical Engineer Department.
The team will work on new capabilities that are relevant to customer requirements and industrial needs.
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, they said.
