Manufacturing is changing because of a number of factors, one of which is the invasion of AI (artificial intelligence) into materials. Called materials informatics, this is the application of data-driven methods such as machine learning to the field of materials science—and it is going to change manufacturing processes in the future. Personally, this is very intriguing, as we put more data into manufacturing and information for good. Hopefully we are not talking data for data sake. Let me state this upfront. Sometimes we are our own enemies as we get lost in the data and the hyperbole, but if we understand what is possible, perhaps we can really make something worthwhile, as we peel back the layers of the onion and get to the real juicy information.
In a new report titled Materials Informatics 2023-2033, IDTechEx uncovered decarbonization efforts are going to be a big driver of this. Additionally, materials informatics will help companies save money, while accelerating materials innovation. These are prime reasons IDTechEx is anticipating the market for external materials informatics will grow 13.7% through 2023.
Many companies are responding to this rise in innovation. As one example, Meta AI and Carnegie Mellow University are working on the Open Catalyst project, with the objective of identifying catalysts that aid the production of fuels using excess renewable energy. This project open sources the discovery process, making the results of 260 million DFT (density functional theory) calculations publicly available for researchers to train their own surrogate models on.
Another example for materials informatics is solar PVs (photovoltaics). The IDTechEx report discusses nine projects using machine learning to speed up the development of new PVs, including an MIT study using active learning to identify lead-free perovskites and work from Osaka University to produce correlations for bandgap and other properties from the structures of organic PVs. However, AI can facilitate yet more areas of PV development, including accelerated lifetime testing.
A March 2023 working paper from researchers at institutions including MIT and Microsoft details a model called DeepDeg, which its authors say speeds up degradation testing of organic solar cells by up to 20 times. The DeepDeg framework consists of a) a deep-learning model to accurately forecast degradation in novel PV using the initial hours of degradation of multivariate device characteristics in this work, the current voltage, and b) a machine learning explainability framework to attribute and predict the impact of various physical factors during degradation on a given figure of merit. Clearly, research in this area is speeding up.
The IDTechEx report points to yet another example: early-stage firm ExoMatter, which emphasizes sustainability in its materials identification platform. The report shows the platform can predict the carbon impact of the materials candidates it identifies and has been used to identify 90 inorganic adsorbent candidates with better carbon retention properties for Dutch direct air capture startup Carbyon. Carbyon estimated this had saved it at least six months in the lab.
Of course, these are simply a few examples. These types of applications could become a top priority for many of the companies that are looking to enhance their ESG (environmental, social, and governance) toolboxes. This is especially true as many organizations and government are beginning to have deeper discussions about the chemicals found in everyday products from food packaging, to makeup, to clothing, and so much more.
At the end of the day, we are seeing the rise of digital transformation in the materials industry—and it is going to improve the sustainability of materials, all while impacting manufacturing processes. Are you ready for the next evolution? Or should I say are you ready for the next materials evolution in manufacturing?
Want to tweet about this article? Use hashtags #IoT #sustainability #AI #5G #cloud #edge #futureofwork #digitaltransformation #green #ecosystem #environmental #circularworld #manufacturing #materials