Towards a Generalizable AI for Materials Discovery: Validation through Immersion Coolant Screening
This addresses the need for generalizable AI in materials discovery, particularly for multi-criteria screening tasks like immersion coolant development, though it is incremental as it builds on existing transfer learning concepts.
The paper tackled the problem of AI models being problem-specific in materials discovery by introducing GATE, a generalizable framework that jointly learns 34 physicochemical properties, and validated it by screening billions of candidates to identify 92,861 promising molecules for immersion cooling fluids, with four showing strong experimental agreement and performance comparable to or exceeding a commercial coolant.
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.