Researchers have discovered a new way to perform “general inverse design” with reasonably high accuracy. This breakthrough paves the way for the further development of a burgeoning and rapidly evolving field that could eventually enable the use of machine learning to accurately identify materials based on a desired set of properties defined by science. user. This could be revolutionary for materials science and have broad industrial benefits and use cases.
The work was conducted by researchers from the Interdisciplinary Low Energy Electronic Systems (LEES) Research Group of the Singapore-MIT Alliance for Research and Technology (SMART), MIT’s research enterprise in Singapore, as well as collaborators from MIT, the National University of Singapore and Nanyang. Technological University.
A major challenge in materials science and research has been the long desired ability to create a material or compound with a specific set of characteristics and properties to suit a particular application or use case. To solve this problem, researchers have traditionally used material screening through material property databases, which has led to the discovery of a limited number of compounds with user-defined functional properties. However, even with high performance computing, the computational cost of the necessary calculations is high, prohibiting an exhaustive search of the theoretical space of materials. Therefore, there is a pressing need for an alternative method that can make this “materials prospecting” process more comprehensive and efficient.
Enter the reverse design. As its name suggests, the reverse design concept reverses the conventional design process, allowing new materials and compounds to be “reverse-engineered” simply by inputting a set of desired properties and characteristics, then using a optimization algorithm to generate a predicted solution. The recent advent of inverse design has sparked particular interest in the field of photonics, which is increasingly turning to unconventional technologies to circumvent the challenges inherent in designing ever smaller but more powerful devices. . Current methods involve traditional design, in which a designer designs a fixed shape or structure as a starting point. This process is labor intensive and excludes a wide range of other devices with different shapes or structures, some of which may have more potential than traditional shapes or structures.
Inverse design eliminates this problem and instead allows the fabrication of devices with the most optimal or efficient shape, structure, chemical composition, or other characteristics or properties. Although inverse design is not new, SMART researchers have taken the technology one step further by discovering a viable method of “general” inverse design, in which the ability to inverse design is not limited to a particular set. of elements or crystal structure, but is able to access a diversity of elements and crystal structures.
This breakthrough is described in a paper titled “An Invertible Crystallographic Representation for General Inverse Design of Inorganic Crystals with Targeted Properties,” recently published in the journal Matter. In the research, the team demonstrates a framework for the general inverse design (variable composition and structure) of inorganic crystals, called FTCP (Fourier-Transformed Crystal Properties), which allows the inverse design of crystals with user-specified properties. by sampling, decoding and post-processing. Even more promising, the researchers show that FTCP is able to design new crystalline materials that are different from known structures – a significant development in the exploration of this nascent technology with potentially game-changing implications for materials science and industrial applications. .
The algorithm developed by SMART researchers trains on more than 50,000 compounds in a materials database, then learns and generalizes the complex relationships between chemistry, structure and properties to predict new compounds or materials which possess characteristics targeted by the user. The algorithm predicts materials with target formation energies, band gaps, and thermoelectric power factors, and validates these predictions with simulations through density functional theory, in turn demonstrating a reasonable degree of accuracy .
“This is an incredibly exciting development for the field of materials research. Materials science researchers now have an efficient and comprehensive tool that allows them to discover and create new compounds and materials by simply entering the desired characteristics,” says Tonio Buonassisi, Principal Investigator at LEES and Professor of Mechanical Engineering at LEES. MIT.
S. Isaac P. Tian, NUS graduate student and co-first author of the paper, adds, “In the next stage of this journey, an important step will be to refine the algorithm to be able to better predict stability and manufacturability. These are exciting challenges that the SMART team is currently working on with collaborators in Singapore and around the world. »
Zekun Ren, lead author and post-doctoral fellow at LEES, says: “The goal of finding more efficient and effective ways to create materials or compounds with user-defined properties has long been a central concern of researchers. in materials science. Our work demonstrates a viable solution that goes beyond specialized inverse design, allowing researchers to explore potential materials of varying composition and structure and thus enabling the creation of a much wider range of compounds. This is a pioneering example of successful general inverse design, and we hope to build on this success in further research efforts.
The research is conducted by SMART and supported by the National Research Foundation (NRF) of Singapore under its Campus for Research Excellence and Technological Enterprise (CREATE) programme.
SMART’s interdisciplinary LEES research group creates new integrated circuit technologies that result in increased functionality, reduced power consumption and superior performance for electronic systems. These integrated circuits of the future will impact applications in wireless communications, power electronics, LED lighting and displays. LEES has a vertically integrated research team with expertise in materials, devices and circuits, consisting of several people with professional experience in the semiconductor industry. This ensures that research is targeted to meet the needs of the semiconductor industry, both in Singapore and globally.
SMART was created by MIT and the NRF in 2007. SMART is the first entity of CREATE developed by the NRF. SMART serves as the intellectual and innovation hub for research interactions between MIT and Singapore, undertaking cutting-edge research in areas of interest to both parties. SMART currently includes an Innovation Center and five interdisciplinary research groups: Antimicrobial Resistance, Critical Analytics for Personalized Medicine Manufacturing, Disruptive and Sustainable Technologies for Precision Agriculture, Future Urban Mobility, and LEES.