# Minimizing data requirements for chemical and material property prediction via cluster-based training set selection

Source: [nature.com](https://www.nature.com/articles/s43588-026-01076-9) · 2026-11-18 · Computing
Page: https://themorning.science/story/minimizing-data-requirements-for-chemical-and-material-property-prediction-via-c-55e61fc8add39dd3
Kind: research · Impact: medium

## In brief

- A survey of 100 algorithms across 60 chemical and materials property prediction tasks was conducted.
- Cluster-based selection of training data outperformed active learning in the study.
- The paper is published in Nature Computational Science (doi:10.1038/s43588-026-01076-9).

## Why it matters

The findings suggest that choosing training sets by clustering can reduce the data needed to train property prediction models, which can lower the cost of generating chemical and materials data.

## Timeline

- 2026-11-18: Published online in Nature Computational Science

## Coverage

- [Minimizing data requirements for chemical and material property prediction via cluster-based training set selection](https://www.nature.com/articles/s43588-026-01076-9) — nature.com, 2026-11-18

Tags: machine learning, materials science, chemistry, active learning, training data selection

---

Brief generated by AI (claude-haiku-5-5) from the reporting listed under Coverage. Headlines belong to their publishers. The Morning Science – https://themorning.science
