Artificial intelligence powered material search engine

Many data-driven applications in material science have been made possible because of recent breakthroughs artificial intelligence(AI). The use AI engineering is becoming more viable as the number data such X-Ray diffraction, various spectroscopy, and microscope grows. In this work, we reported a search engine that uses interatomic space (d value) from X-ray diffraction to provide information. We investigated techniques for predicting prospective using data. used Random Forest, Naive Bayes (Gaussian), Neural Network algorithms achieve this. These an average accuracy 88.50\%, 100.0\%, 88.89\%, respectively. Finally, combined all these into ensemble approach make prediction generic. This method has ~100\% rate. Furthermore, are designing graph neural network (GNN)-based architecture improve interpretability accuracy. Thus, want solve computational time complexity traditional dictionary-based metadata-based engines generic prediction.