# Machine learning explains material's unexpected thermal conductivity

**URL:** <https://community.materialssquare.com/t/machine-learning-explains-materials-unexpected-thermal-conductivity/580>\
**Category:** News\
**Created:** [August 23, 2024, 12:59pm UTC](https://community.materialssquare.com/t/machine-learning-explains-materials-unexpected-thermal-conductivity/580 "2024-08-23T12:59:18Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![gabriele1](https://yyz1.discourse-cdn.com/flex003/user_avatar/community.materialssquare.com/gabriele1/32/20_2.png) [@gabriele1](https://community.materialssquare.com/u/gabriele1)\
**Post date:** [August 23, 2024, 12:59pm UTC](https://community.materialssquare.com/t/machine-learning-explains-materials-unexpected-thermal-conductivity/580/1 "2024-08-23T12:59:18Z")

</div>

Researchers at Cornell University used machine learning and X-ray techniques to explain the unusual increase in thermal conductivity in germanium telluride (GeTe) as it is heated. They discovered that as GeTe changes phase from rhombohedral to cubic, the bonds between certain atoms (Ge-Ge and Te-Te) strengthen significantly, which boosts thermal conductivity. This insight, confirmed through advanced computational methods and bonding analysis, could enhance the design of materials for thermoelectric and other energy applications.

For more details, you can read the full article here:

> **[Machine learning explains material's unexpected thermal conductivity](https://phys.org/news/2024-08-machine-material-unexpected-thermal.html)**
>
> Using a combination of machine learning and powerful X-rays, Cornell researchers have solved a mystery behind the unusual behavior seen in a class of materials with potential for thermoelectric energy conversion and other applications.