# Materials science and engineering: New vision in the era of artificial intelligence

**Authors:** Tao Qiang, Honghong Gao  
**arXiv:** [1804.08293](https://arxiv.org/abs/1804.08293)  
**Date:** 2018-04-23  
**Summary page:** https://www.summarizepaper.com/en/paper/1804.08293v1/

## Key points

- Materials science and engineering (MSE) has evolved from experimental to theoretical and computational methods, and now to a data-intensive paradigm.
- Computational materials science has played a crucial role in advancing MSE.
- Tao Qiang and Honghong Gao propose the data-intensive MSE (DIMSE) model that leverages artificial intelligence (AI) for materials discovery.
- DIMSE utilizes large amounts of data and AI techniques to accelerate the development of novel materials.
- Embracing AI in materials science research enables efficient analysis of vast amounts of data and uncovering valuable insights.
- DIMSE is expected to significantly contribute to future advancements in materials science.
- AI can reshape the field by leveraging data-intensive approaches like DIMSE.
- Researchers can address complex challenges in materials discovery more effectively with these approaches, leading to accelerated progress in developing innovative materials.

## Summary

In the field of materials science and engineering (MSE), scientific discovery has evolved from experimental approaches to theoretical and computational methods, and now to a data-intensive paradigm. Computational materials science has played a crucial role in advancing this field, leading to significant achievements in recent years. Tao Qiang and Honghong Gao provide an overview of the classical MSE models and propose their own model called data-intensive MSE (DIMSE) which leverages the power of artificial intelligence (AI) to address global challenges in materials discovery. By utilizing large amounts of data and applying AI techniques, DIMSE offers new opportunities for accelerating the development of novel materials. The paper emphasizes the importance of embracing AI in materials science research as it enables scientists to analyze vast amounts of data more efficiently and uncover valuable insights. It is expected that this model will contribute significantly to accelerating future advancements in materials science. This work highlights the evolving nature of scientific discovery in MSE and underscores the potential impact that AI can have on reshaping this field by leveraging data-intensive approaches like DIMSE. Researchers can address complex challenges in materials discovery more effectively with these approaches, ultimately leading to accelerated progress in developing innovative materials for various applications.