Key points are not available for this paper at this time.
Artificial Intelligence (AI) and machine learning (ML) are revolutionizing science and engineering by enabling researchers to analyze vast amounts of data, uncover patterns, and make predictions with unprecedented accuracy. The integration of AI and ML techniques are driving innovation across disciplines, paving the way for groundbreaking discoveries and technological advancements. On another corner, sustainability in core engineering disciplines is taking hold. Much work has been done on transient technologies, with a particular emphasis on transient electronics. The research in this domain explores the new materials, architectures, and functionalities of devices with a time-bound lifetime. We present a whole landscape view of the field with a focus on the most recent developments, focusing mainly on transitory materials such as metals, polymers, and semiconducting materials. The development and optimization of commercially viable materials are being accelerated by the rapid integration of AI and molecular design tools for high-throughput experimentation. There is a discussion of the difficulties in expanding data-driven technologies from small molecules to polymers, highlighting the importance of AI in finding new molecular designs and revamping existing molecules for innovative applications. The paper emphasizes how crucial it is to define and standardize polymer systems for ML models to generate a cohesive data collection system for AI and automation improvements. It also highlights the need for improvements in ML methods to fully utilize the advantages of data-driven polymer chemistry, highlighting the significance of reliable and varied datasets for predictive models in the synthesis of polymers. The article's conclusion addresses the necessity of fundamental studies in polymer classification and standardization to fully capitalize on the potential of polymer development.
Motadayen et al. (Mon,) studied this question.