MENU

MARVEL-AI: A*STAR’s AI-Driven Materials Discovery Framework

A*STAR Singapore
Overview
A*STAR has launched MARVEL-AI to accelerate the transition of advanced materials from discovery to industrial deployment using an AI-enabled closed-loop system. The initiative demonstrates significant throughput gains, such as a 25-fold increase in polymer sample production and 400-fold increase in alloy screening. This framework aims to bridge the gap between laboratory research and real-world application across semiconductors, energy, and chemicals.
In Depth

Key Findings

MARVEL-AI integrates AI-enabled discovery, automated experimentation, and industrial translation to reduce the time and resources required to bring new materials to market. The platform focuses on four primary material classes: metal alloys, ceramics, composites, and polymers and organics. By linking prediction and validation in an iterative loop, the initiative has already achieved substantial performance milestones in throughput and prototyping.

Technical Details

The system employs a closed-loop architecture where AI models identify candidates and guide automated synthesis and testing, with the resulting data feeding back into the AI to refine future exploration. Specific technical achievements include:

  • Polymers: Automation increased daily output from three sequential samples in an 8-hour window to 75 samples produced in 24 hours via parallel processing, a 25-fold increase.
  • Metal Alloys: In-house synthesis and characterization allow for the screening of up to 470 unique alloy samples per day, exceeding conventional methods by more than 400 times.
  • Composites: The framework enabled the development of a hydrogen-carrying capsule prototype that is four times more durable and 50% lighter than previous versions.

Background & Context

Led by the Agency for Science, Technology and Research (A*STAR) and anchored by the A*STAR Institute of Materials Research and Engineering (IMRE), the initiative is supported by METI, EnterpriseSG, EDB, and NRF under the Research, Innovation and Enterprise 2030 (RIE2030) framework. The platform collaborates with Institutes of Higher Learning (IHLs) and industry partners, including Google Cloud for secure research environments and CuspAI for generative AI integration.

Significance & Outlook

MARVEL-AI seeks to move beyond discovery by ensuring materials are validated under real-world conditions and manufactured at scale. Strategic collaborations target high-performance alloys for aerospace and defense, sustainable materials with reduced reliance on critical raw materials, and advanced membrane materials. The goal is to foster high-value startups and attract multinationals to Singapore’s materials development ecosystem.

Source: https://www.a-star.edu.sg/news/press-releases/marvel-ai-accelerating-advanced-materials-innovation-from-discovery-to-deployment

Get our weekly technology intelligence — free

Receive an infographic that lets you judge at a glance whether each field’s analysis report is worth reading.

Subscribe Free — Weekly Tech Intelligence

By subscribing, you’ll receive Troy-Technical’s weekly technology intelligence newsletter.

  • Your email and selected fields are used only to deliver the newsletter.
  • We never share your information with third parties.
  • You can unsubscribe anytime via the link in each email.

See our Privacy Policy for details.

Takes about a minute · Unsubscribe anytime

Published by Troy-Technical, an independent site run by one engineer with a career in materials development.
About the author / Contact info@troy-technical.jp
Let's share this post !

Author of this article

TOC