# Data-driven model rapidly predicts dehydrogenation barriers in solid-state materials

**URL:** <https://community.materialssquare.com/t/data-driven-model-rapidly-predicts-dehydrogenation-barriers-in-solid-state-materials/241>\
**Category:** News\
**Created:** [May 17, 2024, 2:38pm UTC](https://community.materialssquare.com/t/data-driven-model-rapidly-predicts-dehydrogenation-barriers-in-solid-state-materials/241 "2024-05-17T14:38:29Z")\
**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:** [May 17, 2024, 2:38pm UTC](https://community.materialssquare.com/t/data-driven-model-rapidly-predicts-dehydrogenation-barriers-in-solid-state-materials/241/1 "2024-05-17T14:38:29Z")

</div>

Researchers at Tohoku University have developed a data-driven model that efficiently predicts the dehydrogenation barriers of magnesium hydride (MgH₂), a promising solid-state hydrogen storage material. This model uses the crystal Hamilton population orbital and atomic hydrogen distances to derive a distance-energy ratio, making predictions faster and less computationally intensive than traditional methods. Validated against experimental data, the model shows excellent agreement, advancing the development of high-performance hydrogen storage solutions and potentially applicable to other metal hydrides.

For more details, visit Phys org:

> **[Data-driven model rapidly predicts dehydrogenation barriers in solid-state...](https://phys.org/news/2024-05-driven-rapidly-dehydrogenation-barriers-solid.html)**
>
> Researchers have developed a data-driven model to predict the dehydrogenation barriers of magnesium hydride (MgH2), a promising material for solid-state hydrogen storage. This advancement holds significant potential for enhancing hydrogen storage...