Science and Technology of Advanced Materials: Methods

Electron spin states can now be probed at much higher resolution and more efficiently, opening new opportunities in materials analysis and data processing technologies.

Analysis of materials can be done quicker and with less expertise with the help of proven machine learning techniques established in biomedical fields.

GPT-4 shows promise as an aid to chemistry researchers, yet its limitations reveal the need for further improvements.

Researchers have developed a proof-of-concept system that allows robotic experiments to run without any human intervention.

Researchers have developed an AI-driven system that can design novel molecules with any desired properties and suggest methods to create them using readily available materials.

Researchers have combined machine learning with robotic process automation to speed up and simplify a time-consuming process.

A new method allows scientists to gather enough information about the properties of metals to enable the prediction of the properties of new materials.

Analysis of materials can be done quicker and with less expertise with the help of proven machine learning techniques established in biomedical fields

The latest ‘large language model’ artificial intelligence system, GPT-4, could aid chemistry researchers, but limitations reveal the need for improvements.

The search for innovative materials will be greatly assisted by software that can suggest new experimental possibilities and also control the robotic systems that check them out.

Two key challenges in chemistry innovation are solved simultaneously by exploring chemical opportunities with artificial intelligence.

Machine learning algorithms allow analysis and characterization of the atomic arrangement of silicon surface superstructures without the need for human expertise.

A model that rapidly searches through large amounts of materials could find sustainable alternatives to existing composites.

Machine learning and robotic process automation combine to speed up and simplify a process used to determine crystal structures.

Scientists in Japan have combined two computational models to extract more data on steel alloys from a single test, with implications for the discovery of new materials.

A model that rapidly searches through large numbers of materials could find sustainable alternatives to existing composites.

A quick, cost-effective approach improves the accuracy with which machine learning models can predict the properties of new materials.

A quick, cost-effective approach improves the accuracy with which machine learning models can predict the properties of new materials.