Volume 5, Issue 3 (2025) – 13 articles
Cover Picture:
This cover image aims to reflect the process of accelerating the discovery of quantitative relationships in polymer material aging through Symbolic Regression. The broken polymer chain at the top intuitively symbolizes the structural damage occurring in materials due to aging, which is the key focus of the research. The tree-like structure and the multi-node network represent the vast and complex material knowledge system, as well as the intertwined quantitative relationships at the microscopic and macroscopic levels. The Symbolic Regression algorithm serves as an exploration tool within this “knowledge tree,” integrating experimental data to uncover the correlations between microscopic structures and macroscopic properties. This approach helps researchers precisely capture the optimal quantitative relationships, providing scientific support for controlling and predicting material aging behaviors and advancing materials research.
view this paper This cover image aims to reflect the process of accelerating the discovery of quantitative relationships in polymer material aging through Symbolic Regression. The broken polymer chain at the top intuitively symbolizes the structural damage occurring in materials due to aging, which is the key focus of the research. The tree-like structure and the multi-node network represent the vast and complex material knowledge system, as well as the intertwined quantitative relationships at the microscopic and macroscopic levels. The Symbolic Regression algorithm serves as an exploration tool within this “knowledge tree,” integrating experimental data to uncover the correlations between microscopic structures and macroscopic properties. This approach helps researchers precisely capture the optimal quantitative relationships, providing scientific support for controlling and predicting material aging behaviors and advancing materials research.
Back Cover Picture:
This work offers a rapid, efficient and cost-effective approach for the development of new small-molecule hole transport materials (SM-HTMs) by combining molecular splicing algorithm (MSA) with high-throughput computational screening and machine learning (ML). The cover depicts the evolution from initial small molecules to the promising SM-HTMs for perovskite solar cells (PSCs), visualized through a futuristic 3D transition device. A self-developed MSA is employed to construct a database of potential SM-HTMs for PSCs. By integrating density functional theory (DFT), high-throughput calculations are conducted to identify six high performance candidate SM-HTMs for subsequent synthesis and performance evaluation. Furthermore, the molecular structure and property datasets obtained through high-throughput calculations are utilized to develop property prediction models for SM-HTMs using three ML approaches: random forest (RF), gradient boosted decision trees (GBDTs), and extreme gradient boosting (XGBoost).
view this paperThis work offers a rapid, efficient and cost-effective approach for the development of new small-molecule hole transport materials (SM-HTMs) by combining molecular splicing algorithm (MSA) with high-throughput computational screening and machine learning (ML). The cover depicts the evolution from initial small molecules to the promising SM-HTMs for perovskite solar cells (PSCs), visualized through a futuristic 3D transition device. A self-developed MSA is employed to construct a database of potential SM-HTMs for PSCs. By integrating density functional theory (DFT), high-throughput calculations are conducted to identify six high performance candidate SM-HTMs for subsequent synthesis and performance evaluation. Furthermore, the molecular structure and property datasets obtained through high-throughput calculations are utilized to develop property prediction models for SM-HTMs using three ML approaches: random forest (RF), gradient boosted decision trees (GBDTs), and extreme gradient boosting (XGBoost).
