Review article on accelerated materials discovery from SJTU SMSE is published in Nature Reviews Materials
Recently, the internationally renowned academic journal Nature Reviews Materials published a review article "Machine learning for a sustainable energy future" by associate professor Zhenpeng Yao and his colleagues from the School of Materials Science and Engineering, Shanghai Jiao Tong University. The paper offers a forward-looking outlook for the potential employment of machine learning techniques in the fields of energy materials, equipment, management and policy. Zhenpeng leads the authors of the paper with Shanghai Jiao Tong University as the first affiliation.
Transitioning from fossil fuels to renewable energy sources is a critical global challenge; it demands advances — at the materials, devices and systems levels — for the efficient harvesting, storage, conversion and management of renewable energy. Energy researchers have begun to incorporate machine learning (ML) techniques to accelerate these advances. (Fig. 1)
Fig. 1. Traditional and accelerated materials discovery paradigm
In this Perspective, we highlight recent advances in ML-driven energy research, outline current and future challenges, and describe what is required to make the best use of ML techniques. We introduce a set of key performance indicators with which to compare the benefits of different ML-accelerated workflows for energy research. We discuss and evaluate the latest advances in applying ML to the development of energy harvesting (photovoltaics), storage (batteries), conversion (electrocatalysis) and management (smart grids). Finally, we offer an overview of potential research areas in the energy field that stand to benefit further from the application of ML. (Fig. 2)
Fig. 2 Areas of opportunity for machine learning and renewable energy
Meanwhile, the team published another perspective entitled “On scientific understanding with artificial intelligence” in Nature Reviews Physics, which summarizes the recent progress in using advanced computational systems, specifically artificial intelligence, to construct new scientific understanding. In the past several years, Zhenpeng and his colleagues have been making advances in energy storage, high-throughput experiment/computation, and deep learning in materials science, with works published on Science, Nature Energy, Nature Catalysis, Nature Machine Intelligence, Science Advances, Nature Communications, Matter, Accounts of Chemical Research, and so on.
Link to read the paper: https://www.nature.com/articles/s41578-022-00490-5.