Perspectives on Development of Optoelectronic Materials in Artificial Intelligence Age

Area of Science:

• Materials Science
• Optoelectronics
• Machine Learning

Background:

• Optoelectronic devices, like LEDs, are vital for displays and lighting due to their efficiency and quality.
• Developing new functional materials for these devices is traditionally slow and resource-intensive.
• Machine learning (ML) offers a promising approach to expedite material discovery and performance enhancement.

Purpose of the Study:

• To review the workflow of machine learning in the discovery of optoelectronic materials.
• To highlight recent applications of ML in various optoelectronic functional materials.
• To discuss challenges and future directions for ML-assisted optoelectronic material design.

Main Methods:

• Data collection and preprocessing for optoelectronic materials.
• Feature engineering to represent material properties effectively.
• Model selection, evaluation, and application in material discovery workflows.

Main Results:

• Demonstrated ML applications in discovering and enhancing semiconductor quantum dots (QDs), perovskite QDs, organic molecules, and carbon-based nanomaterials.
• Summarized the end-to-end ML workflow from data to material application.
• Identified key areas where ML significantly accelerates the design cycle.

Conclusions:

• Machine learning is a powerful tool for accelerating the discovery of high-performance optoelectronic materials.
• Overcoming current challenges will unlock the full potential of ML in optoelectronics.
• Interdisciplinary collaboration is essential for ML-guided innovation in optoelectronic devices.