Artificial intelligence (AI) is set to transform materials science research and unlock new opportunities in display manufacturing. With the potential to accelerate material discovery, enhance performance and durability, reduce manufacturing costs, and enable customizable display technologies, AI-driven material development is poised to revolutionize the future of display technologies.
In one example of the value of AI, it is worth reviewing the work of a research team at the University of Science and Technology, Pohang, Korea (POSTECH) that made significant strides in the development of core materials for OLED displays using AI. The team’s groundbreaking use of machine learning algorithms enabled the creation of an AI “brain” that can predict the performance of organic molecules in OLED screens. This AI-driven approach allows for the rapid identification of molecules with desired properties, leading to more efficient, durable, and cost-effective display technologies.
Accelerating Material Discovery Through AI in Materials Science
So, one of the main benefits of incorporating AI in materials science research is the accelerated discovery of materials. AI algorithms can rapidly screen and identify materials with desirable properties, greatly reducing the time and resources needed for traditional trial-and-error experimentation. This acceleration enables scientists and researchers to focus their efforts on refining and improving the materials that show the most potential. AI models have facilitated the efficient screening of vast libraries of materials, allowing for the identification of promising candidates with desired properties. Data-driven approaches have led to the creation of comprehensive databases of materials properties, enabling rapid identification and comparison of materials for various applications.
Enhancing Material Performance and Durability with AI
AI-driven approaches can also optimize material properties to enhance display performance. This includes improving aspects such as brightness, color accuracy, and efficiency, which can significantly elevate user experiences. In addition, AI can aid in the development of materials with greater stability and longer lifetimes, minimizing the need for frequent replacement or repair of display components. AI-driven design methods, such as generative models, have been employed for the discovery of novel materials and optimization of their properties. Machine learning algorithms have been used to optimize experimental parameters and reduce trial-and-error in materials synthesis and processing.
Reducing Manufacturing Costs through AI Optimization
By optimizing the material composition and synthesis processes, AI can contribute to lowering production costs. This ultimately results in more affordable displays for consumers without compromising on quality. The reduced manufacturing costs can potentially make advanced display technologies accessible to a wider range of customers, further driving the growth of the industry.
Despite the significant progress, there are still challenges that need to be addressed to further the use of AI in materials science:
- Data scarcity: Materials science often suffers from a lack of high-quality, large-scale data required for training robust AI models.
- Interpretable models: Developing AI models that provide meaningful explanations for their predictions is essential for fostering trust and adoption in the materials science community.
- Multi-objective optimization: Many materials design problems involve optimizing multiple conflicting objectives, which can be challenging.
However, the advantages of AI far outweigh the teething problems that materials scientists will encounter. AI can be used to automate laboratory experiments, accelerating the materials discovery process. Robotics and AI-driven optimization algorithms will enable the efficient exploration of the experimental parameter space, reducing the time and resources needed to identify optimal conditions for material synthesis and processing. Furthermore, the combination of AI with quantum computing has the potential to revolutionize materials science by accelerating the simulation and optimization of materials at the quantum level. This integration could lead to the discovery of novel materials with unprecedented properties and functionalities.
The Display Materials Space Race
The integration of AI in material development has the potential to disrupt traditional display manufacturing approaches by accelerating material discovery, optimizing performance, and reducing costs. The successful translation of AI-driven materials development into volume manufacturing opportunities will require close collaboration between research institutions, material scientists, and industry stakeholders to ensure seamless scaling of novel materials and processes.
Moreover, nanotechnology plays a pivotal role in this development, as it enables the manipulation of materials at the atomic and molecular scale, providing the foundation for AI algorithms to identify and design innovative materials with unprecedented properties. As AI and nanotechnology continue to advance, their convergence is expected to transform the display manufacturing landscape by delivering cutting-edge materials and fostering sustainable, efficient, and cost-effective production processes.
References
- Kulik, H.J., Tiwary, P. Artificial intelligence in computational materials science. MRS Bulletin 47, 927–929 (2022). https://doi.org/10.1557/s43577-022-00431-1
- Monroe, D. (n.d.). Artificial intelligence for materials discovery. Retrieved May 9, 2023, from https://cacm.acm.org/magazines/2023/4/271229-artificial-intelligence-for-materials-discovery/fulltext
- Park, S., Seong, S., Jeon, G., Ji, W., Noh, K., Kim, S., Chung, Y., Highly Linear and Symmetric Analog Neuromorphic Synapse Based on Metal Oxide Semiconductor Transistors with Self-Assembled Monolayer for High-Precision Neural Network Computation. Adv. Electron. Mater. 2023, 9, 2200554. https://doi.org/10.1002/aelm.202200554
- Pyzer-Knapp, E.O., Pitera, J.W., Staar, P.W.J. et al. Accelerating materials discovery using artificial intelligence, high performance computing and robotics. npj Comput Mater 8, 84 (2022). https://doi.org/10.1038/s41524-022-00765-z
