Accelerated Materials & Chemicals Development

Background / Motivation

IHPC aim to accelerate materials discovery, design and deployment via synergistic efforts between theory, computations and experiments in an integrated and high-throughput way. Today, via advanced high-throughput methods, we are seeing an increase in materials and chemicals (M&C) databases that curate the structure, phase stability and physical/chemical/functional properties of a wide class of materials including structural alloys, materials for energy and catalysis, and polymers.

With the proliferation of M&C data, the development of artificial intelligence (AI) and machine-learning (ML) approaches to accelerate materials design is a highly active field. IHPC, with its deep engineering/simulation expertise, is in au unique position to synergise and combine physics- and chemistry-based knowledge towards interpretability in AI/ML. 

In partnership with various A*STAR experiment laboratories, IHPC is a hub to tailor-made M&C solutions to accelerate the discovery and deployment of materials and chemical processes that are core to our partners’ businesses. 

Accelerated Materials & Chemicals Development

Capabilities

IHPC’s accelerated M&C development efforts include: 

Inorganic materials (in partnership with IMRE)

  • Structural alloys
  • Catalysts and electrocatalysts
  • Electronic materials
  • Thermoelectric materials

Soft materials (in partnership with ICES)

  • Polymeric materials for oilfield chemicals
  • Formulations for consumer care products

Rapid chemical process development (in partnership with ICES)

Applications

Scalable Cloud-based AI Platform for Reaction Optimisation

Chemical reaction yield depends on several factors, ranging from catalyst materials selection and preparation method, surface science and reaction conditions. The complex interplay between these factors leads to laborious optimisation of the reaction parameters requiring expensive trial runs. For certain industrially-important reaction classes, many catalysts have been tried and documented over the years; these problems are well-suited for data-driven approaches. 

Using the water-gas-shift reaction as a used-case, we develop an AI platform for reaction optimisation and catalyst discovery. We incorporate fundamental physics- and chemistry-based features to construct rationalisable and reproducible AI models. The AI platform (Fig 1) includes automated machine-learning AutoML and Intuitive Graphical User Interface (GUI) for usability and ML workflow templates for reusability, allowing broader user adoption of AI tools in materials discovery. 

IHPC envisions the scalable platform to serve as a bedrock for future lab digitalisation effort with public or private research laboratories where researchers progressively contribute to an expanding dataset, create new ML and optimisation templates for sustainable chemical process development with speed, efficiency and lower costs.

AI platform for reaction optimisation
Fig 1. AI Platform for Reaction Optimisation

High Entropy Alloy

High entropy alloys (HEAs) which are made of five or more elements of approximately equal concentrations, is an up-and-coming class of alloys that are beginning to find traction in the manufacturing industry (Fig 2). Due to a huge design space of possible alloying elements and compositions, machine-learning tools are needed to build surrogate models to rapidly screen through the compositional space using high-throughput computations. It then identifies candidates with the desired phase stability, short-range ordering, solidification dynamics, microstructure and mechanical properties. Partnering with A*STAR's Institute of Materials and Research Engineering (IMRE), IHPC is able to perform rapid prototyping of promising HEA candidates (Fig 3).

5-element HEA

Fig 2. Tracking short-range order and phase separation of a 5-element HEA vs. temperature using ML surrogate model and Monte-Carlo simulations 

Atomistic model of HEA

Fig 3. Atomistic model/representation of HEA using SQS method

Collaboration Opportunities 

Leverage the span of technical expertise at IHPC for technology advancement to help your business move up the value chain. 

IHPC welcomes interested party to collaborate in research and development relating to Accelerated Materials & Chemicals Development in developing improved chemical & material solutions for various engineering applications, tapping into our expertise in physics-based simulations and data-driven discovery platforms.  


For more info or collaboration opportunities, please write to enquiry@ihpc.a-star.edu.sg