Discovery of Materials through Applied Machine Learning and General Machine Learning Architecture

Supriya Rakshit; Mitali Pathak

Abstract

Advances in artificial intelligence technologies, especially machine learning, have generated possibilities in the material sciences to facilitate material exploration and to achieve a profound understanding of the relationship between the constituent elements of the material and the properties represented by the material. The application of machine learning to the exploration of experimental materials is sluggish due to the monetary and temporal costs of experimental data, however parallel methods, such as continuous compositional gradients or high-performance characterization setups, are capable of producing more data than the traditional experimental method and are thus ideal for conjunction with machine learning. A random forest machine learning algorithm has been introduced to two separate substance discovery problems the discovery of modern metallic glass forming ternary compositions and the discovery of novel ammonia decomposition catalysts and has accelerated the creation of high-performance materials.Keywords: Artificial intelligence technology, machine learning, materials genome initiative (MGI), metallic glasses (MG), random forest (RF) algorithms

Discovery of Materials through Applied Machine Learning and General Machine Learning Architecture

Abstract

Read more of it

Publish your article

Abstract

Related articles

Electric Vehicle Integration to Stabilize the Grid by Improving Power Quality

Operational-Amplifier-Based Realization of a 1-BitArithmetic Logic Unit: Design, Implementation, and Experimental Validation

An Extensive Analysis of QC's Difficulties & Restrictions

Smart Battery Management System with Real-Time Estimation of SOC and SOH

A Overview on Reimagining MOSFET as Precision Thermal Sensor

Phase-Change Material Integrated Semiconductor Circuits for In-Memory Analog Computing Applications

Read more of it

Publish your article