用统一几何空间学习34种材料属性，提升发现新冷却液的效率与准确性。
Towards a Generalizable AI for Materials Discovery: Validation through Immersion Coolant Screening
- 构建共享几何空间，联合学习多种物理化学性质，减少多目标筛选偏差。
- 无需重新训练，筛选数十亿分子后找出92,861个候选，4个经实验验证有效。
- 适用于复杂真实场景，如数据中心冷却液开发，可推广至各类材料发现任务。
人工智能已成为加速材料发现的强大工具，但现有模型大多针对特定问题，需额外数据收集和重新训练才能应对新属性。本文提出并验证了通用型AI框架GATE（Geometrically Aligned Transfer Encoder），该框架联合学习涵盖热、电、机械、光学等领域的34种物理化学性质。通过在共享几何空间中对齐这些性质，GATE捕捉跨属性相关性，有效降低因属性割裂导致的误报率——这是多准则筛选中的关键瓶颈。为验证其通用性，GATE在无任何任务特化调整的情况下，应用于数据中心浸没冷却液的发现，这一挑战由开放计算项目（OCP）定义。在筛选数十亿候选分子后，GATE识别出92,861种具备实际部署潜力的分子。其中4种经实验或文献验证，其性能与湿实验测量高度一致，达到或超越商用冷却液水平。结果表明，GATE是一个可直接迁移至多样材料发现任务的通用智能平台。
原文摘要 · Abstract (English)
Artificial intelligence (AI) has emerged as a powerful accelerator of materials discovery, yet most existing models remain problem-specific, requiring additional data collection and retraining for each new property. Here we introduce and validate GATE (Geometrically Aligned Transfer Encoder) -- a generalizable AI framework that jointly learns 34 physicochemical properties spanning thermal, electrical, mechanical, and optical domains. By aligning these properties within a shared geometric space, GATE captures cross-property correlations that reduce disjoint-property bias -- a key factor causing false positives in multi-criteria screening. To demonstrate its generalizable utility, GATE -- without any problem-specific model reconfiguration -- applied to the discovery of immersion cooling fluids for data centers, a stringent real-world challenge defined by the Open Compute Project (OCP). Screening billions of candidates, GATE identified 92,861 molecules as promising for practical deployment. Four were experimentally or literarily validated, showing strong agreement with wet-lab measurements and performance comparable to or exceeding a commercial coolant. These results establish GATE as a generalizable AI platform readily applicable across diverse materials discovery tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。