Scholarlink

<p>Discovering sustainable glass compositions demands navigating vast chemical spaces—a challenge that conventional experimentation cannot meet efficiently. Here we introduce the Simulation-Calibrated Active Learning Estimator (SCALE), a closed-loop framework uniting high-throughput molecular dynamics (MD), machine learning (ML), and robotic synthesis to bridge the gap between simulation and experiment. Over 42,000 melt–quench MD simulations with compact cells ( ≈ 200–500 atoms) train ML models that predict density and elastic moduli with cross-validated <i>R</i><sup><i>2</i></sup> values up to 0.98. Comparison with 55 robotically synthesized sodium alumino-borosilicate glasses reveals systematic density overestimation of up to 5%. Rather than naively augmenting training data, SCALE iteratively learns a composition-dependent calibration from minimal targeted measurements. The protocol substantially reduces density errors over three experimental iterations of six measurements each and demonstrates the potential for glass optimization with a small number of strategically chosen experiments.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Accelerating sustainable glass discovery: integrating molecular dynamics, machine learning, and robotic synthesis

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月24日

查看全文
  • Felix Arendt,
  • Tina Waurischk,
  • Stefan Reinsch,
  • Andrea S. S. de Camargo,
  • Marek Sierka

摘要

Discovering sustainable glass compositions demands navigating vast chemical spaces—a challenge that conventional experimentation cannot meet efficiently. Here we introduce the Simulation-Calibrated Active Learning Estimator (SCALE), a closed-loop framework uniting high-throughput molecular dynamics (MD), machine learning (ML), and robotic synthesis to bridge the gap between simulation and experiment. Over 42,000 melt–quench MD simulations with compact cells ( ≈ 200–500 atoms) train ML models that predict density and elastic moduli with cross-validated R2 values up to 0.98. Comparison with 55 robotically synthesized sodium alumino-borosilicate glasses reveals systematic density overestimation of up to 5%. Rather than naively augmenting training data, SCALE iteratively learns a composition-dependent calibration from minimal targeted measurements. The protocol substantially reduces density errors over three experimental iterations of six measurements each and demonstrates the potential for glass optimization with a small number of strategically chosen experiments.