{
  "id": 16662646,
  "title": "Beyond trial and error: Integrating computation, processing, and AI to design high-entropy alloys",
  "url": "https://urgent.news/2026/10/26/beyond-trial-and-error-integrating-computation-processing-and-ai-to",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-26T21:20:01.000Z",
  "source": {
    "name": "Phys.org",
    "slug": "phys-org",
    "url": "https://phys.org/news/2026-10-trial-error-ai-high-entropy.html"
  },
  "original_language": "en",
  "account": "High-entropy alloys (SHEAs), which blend multiple principal elements in comparable proportions, present a complex challenge due to the large number of variables involved in determining their properties. To address this, researchers have developed computational tools to analyze individual aspects such as atomic-scale interactions, phase stability, microstructure evolution, and macroscopic properties. However, these methods lack a unified approach, each having its own limitations in scalability, cost, and predictive accuracy.\n\nA 2026 review by an international team of researchers led by AIMR and POSTECH aims to bridge these fragmented approaches into a systematic framework for SHEA development. The review positions computational methods as complementary tools operating at different scales, including density functional theory and molecular dynamics for atomic-scale phenomena, phase diagram calculations and phase-field modeling for phase stability and microstructure evolution, and crystal plasticity modeling linking microstructure to mechanical behavior. Artificial intelligence and machine learning are then used to extend this analysis into data-driven design, allowing for coherent predictions of phase stability, microstructure evolution, and mechanical properties.\n\nThe review demonstrates how simulating manufacturing processes like additive manufacturing and severe plastic deformation can directly link processing conditions to microstructural outcomes and performance. Additionally, processing-guided microstructural design can create advanced architectures like core–shell and reverse-gradient structures for enhanced mechanical performance and resistance to hydrogen embrittlement.\n\nLooking forward, the authors envision a closed-loop platform where computation and AI identify promising compositions, physics-based simulations explain the mechanisms behind them, and experiments validate these findings and feed data back into the models. This integrated approach aims to move beyond empirical trial and error and establish a more systematic, predictive design philosophy for SHEAs. By organizing diverse studies into a coherent framework, the review hopes to guide future alloy development away from intuition and towards a collaborative effort involving computational science, processing science, and artificial intelligence.",
  "summary": "Designing structural high-entropy alloys (SHEAs) means solving a problem with an enormous number of moving parts: which combinations of composition and processing conditions will yield the phases, microstructures, and mechanical properties a given application demands? Because these alloys mix multiple principal elements in comparable proportions, that question spans length and time scales that no…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}