Pre-cum-Mains GS Foundation Program for UPSC 2026 | Starting from 14th Nov. 2024 Click Here for more information
Source: The post is based on the article “GNoME: Google DeepMind’s AI breakthrough could revolutionize chip, battery development” published in “Indian Express” on 8th December 2023
Why in the News?
Researchers at Google DeepMind have developed a new Deep Learning Artificial Intelligence (AI) tool called GNoME to discover new materials.
What is GNoME?
GNoME stands for Graph Networks for Materials Exploration. It is a Deep Learning AI tool developed by researchers at Google DeepMind.
Purpose: To discover new materials and predict material stability.
What has been discovered by GNoME till now?
GNoME is said to have discovered over 2.2 million new materials including 380,000 materials that it predicts to be stable.
This breakthrough that could have wide-reaching application in sectors such as renewable energy, battery research, semiconductor design and computing efficiency.
How does GNoME work?
1) GNoME is a graph neural network model (GNN) where the input data for the model takes the form of a graph that can then be likened to connections between atoms.
2) It was trained using active learning (a type of machine learning technique used to scale up a model first trained on a small specialised dataset)
– This technique is great for discovering new materials because it can find patterns beyond what’s in the original dataset.
3) It then combines two pipelines to discover new stable materials :
a. Structural- creates candidates with structures similar to known crystals.
b. Compositional- a randomised approach based on chemical formulas .
4) The predictions made by it are then evaluated using Density Functional Theory (a technique used in physics, chemistry and materials science to understand atomic structures and assess crystal stability).
What is the significance of GNoME?
1) GNoME has significantly improved the accuracy of predicting material stability from 50% to approximately 80%.
2) It has increased the number of known stable materials. This could lead to the development of new technologies such as more efficient batteries and superconductors.
3) It uses filters to narrow down the list of potential materials. This saves time and money by avoiding the need to synthesize and test materials that are unlikely to be stable.
UPSC Syllabus: Science and Technology
