NEWS STORIES | 2022
An Introduction to FUSION-MAP Project
Feb. 22, 2022
An Introduction to FUSION-MAP project: AI/ML and Computational Science for Empowering Hydrogen Economy
Many of the key technological challenges associated with alternative energies could be traced back to the lack of suitable materials. New materials are required to address the urgent societal need for clean energy solutions (e.g., solar cells, batteries, fuel cells, electrolyzers, CO2 utilization). The process of discovering and optimizing new functional materials takes many years, and slows the commercialization of new technologies. Flexible computational science such as artificial intelligence, machine learning and robotics present an opportunity to break this bottleneck and shorten deployment timelines from decades to years.
Discovering a breakthrough material is a very challenging assignment to do. All materials contain one or more ingredients. The choice of ingredients and their ratios determine the performance of the material. The performance of materials also depends on how the ingredients are combined. For example, combining carbon atoms at extreme temperature and pressure forms diamond, one of the hardest known materials. Under milder conditions, however, carbon atoms form graphite, a soft material used for pencils. As a result of the many possible ingredients and many possible ways they can be combined, there are billions of possible materials, the vast majority of which are not useful.
Finding a useful material is like finding a needle in a haystack if there is any. Materials scientists are therefore turning to automated experiments powered by artificial intelligence.
The critical material properties for fuel cell and hydrogen technologies being evaluated for a variety of applications are (i) light weight, (ii) cost and availability, (iii) high volumetric and gravimetric density of hydrogen, (iv) fast kinetics, (v) ease of activation, (vi) low temperature of dissociation or decomposition, (vii) appropriate thermodynamic properties, (viii) long-term cycling stability, and (ix) high degree of reversibility. All the said properties greatly demand from us to understand the fundamental mechanistic behavior of materials involving catalysts and their physicochemical reaction toward hydrogen at an atomic or molecular scale.
The Fuel cell and hydrogen technologies Understanding through Semantic, Interfaces and Ontologies -Materials Acceleration Platform (FUSION-MAP)
The FUSION-MAP project, hosted by the International Green Hydrogen Alliance (IGH2A) and co-lead by Hybrixcel Inc., is a research initiative aimed at accelerating the development of green hydrogen systems. The project will establish a consortium of academic and industry partners to collaborate on advancing the understanding and discovery of sustainable and scalable solutions for energy storage in Canada and worldwide. By leveraging AI-accelerated methodologies and advanced technologies, FUSION-MAP aims to revolutionize the process of inventing green hydrogen systems.
Materials Acceleration Platform is an emerging paradigm to accelerate the autonomous discovery of functional materials. The reduced timeline of accelerated materials and process development is facilitated by the convergence of High-Throughput Computational (HTC) screening with improved computations using for simulations of materials properties predictions, automation, and robotic systems for chemistry laboratories, using scientific AI in materials science and the diversity of machine learning methods adapted to material science and areas of physics and chemistry.
In this regard, the FUSION-MAP project intends to develop machine and deep learning tools and models that can efficiently utilize relevant data to predict fuel cell and hydrogen technologies materials and interfaces evolve in space and time. The aim is to create cost-effective incorporated inverse design techniques for identifying of future materials in product specifications. Furthermore, all the properties of an optimal product predicted falls into the certain region of materials property robustness, hence confirming that the optimal product can be predicted after considering a unique material properties prediction error. Future efforts will be on extending the flexibility of these techniques in other related research areas where multiple objectives have to be optimized simultaneously.
The ability to understand and control fuel cell and hydrogen technologies interfaces is essential for the development of high-performing and sustainable technologies. The chemical space within a fuel cell is comprised of a multitude of different elements and structures that cross influence each other. The combinatorics of this space is enormous and exhaustive to explore in a physical lab.
FUSION-MAP project relies on the development of a unique R&D infrastructure and accelerated methodologies that unites and integrates insights from leading experts, competences and data throughout hydrogen value chain with Artificial Intelligence (AI), High-Performance Computing (HPC), and autonomous synthesis robotics. In short, FUSION-MAP aims to reinvent the way we invent fuel cell and hydrogen technologies and to develop core modules and key demonstrators of a Materials Acceleration Platform specifically designed for the accelerated discovery of materials and interfaces.
Six main research areas have already been identified to address the challenge of developing next-generation fuel cell and green hydrogen systems. The six research areas defined so far are:
- Hydrogen Production
- Hydrogen storage and distribution
- Hydrogen use in transport
- Hydrogen use in heating and power generation
FUSION-MAP methods and tools will be used in current Hydrogen and Fuel Cell Technologies research:
– Catalyst materials for fuel cells and electrolyzers
– Materials for solar water splitting technologies
– Hydrogen handling materials
– Hydrogen storage materials
On February 8th, 2022, IGH2A launched the FUSION-MAP project for discovery of materials and interfaces in fuel cell and hydrogen technologies, accelerate their development process in order to facilitate increased uptake of hydrogen in clean energy applications. We believe that AI and ML technologies will bring about promising results in the empowering of the hydrogen economy.