Identifying the composition and atomic distribution of Pt-Au bimetallic nanoparticle with machine learning and genetic algorithm

Explainable chemical artificial intelligence from accurate machine learning of real-space chemical descriptors

Machine-learned computational chemistry has led to a paradoxical situation in which molecular properties can be accurately predicted, but they are difficult to interpret. Explainable AI (XAI) tools can be used to analyze complex models, but they are highly dependent on the AI technique and the origin of the reference data. Alternatively, interpretable real-space tools can be employed directly, but they are often expensive to compute. To address this dilemma between explainability and accuracy, we developed SchNet4AIM, a SchNet-based architecture capable of dealing with local one-body (atomic) and two-body (interatomic) descriptors. The performance of SchNet4AIM is tested by predicting a wide collection of real-space quantities ranging from atomic charges and delocalization indices to pairwise interaction energies. The accuracy and speed of SchNet4AIM breaks the bottleneck that has prevented the use of real-space chemical descriptors in complex systems. We show that the group delocalization indices, arising from our physically rigorous atomistic predictions, provide reliable indicators of supramolecular binding events, thus contributing to the development of Explainable Chemical Artificial Intelligence (XCAI) models.

Carbon-Hybridized Hydroxides for Energy Conversion and Storage: Interface Chemistry and Manufacturing

Carbon-hybridized hydroxides (CHHs) have been intensively investigated for uses in the energy conversion/storage fields. Nevertheless, the intrinsic structure-activity relationships between carbon and hydroxides within CHHs are still blurry, which hinders the fine modulation of CHHs in terms of practical applications to some degree. This review aims to figure out the intrinsic role of carbon materials in CHHs with a focus on the interface chemistry and the engineering strategy in-between two components. The fundamental effects of the carbon materials in enhancing the charge/mass transfer kinetics are first analyzed, particularly the extra electron pathways for fast charge transfer and the anchoring sites for boosting the mass transfer. Subsequently, the surface-guided/confined effects of carbon materials in CHHs to modify the morphology and tailor the hydroxides, and functional heterojunction for regulating the inner electronic structure are decoupled. The methods to efficiently construct a stable yet robust solid-solid heterointerface are summarized, including oxygen functional groups engrafting, topological defective sites construction and heteroatom incorporation to activate the inert carbon surface. The smart CHHs in some typical energy applications are demonstrated. Additionally, the methodologies that can reveal the hybridization electron configuration between two components are summed up. At last, the perspective and challenges faced by the CHHs for energy-related applications are outlined.

EFFECTS OF CORE STABILITY TRAINING ON SPECIFIC STRENGTH IN WRESTLERS

ABSTRACT Introduction: Boxing is characterized by a high degree of combination of strength and skill and belongs to the sports group of enduring strength and skill combined with long-term continuous whole-body strength output to achieve good results in competition. Therefore, athletes pay more attention to the skills they use all the time, and it is very important to master the techniques correctly and reasonably distribute physical strength accurately. Objective: Explore the effect of core stability training on the specific strength of wrestlers. Methods: 12 top junior level athletes of a provincial women’s wrestling team as research objects, 12 people in total, and randomly divided into control and experimental groups with six people. Results: After the test, the data changes in the experimental group were highly significant compared to before and after the experiment (P<0.01). The data changes between the experimental and control groups were significantly different before and after the experiment (p<0.05), showing that the special strength of core stability training fighters has a small increase. Conclusion: Core stability training is useful for the specific strength of wrestlers. Level of evidence II; Therapeutic studies - investigation of treatment outcomes.

Machine Learning for Property Prediction and Optimization of Polymeric Nanocomposites: A State-of-the-Art

Recently, the field of polymer nanocomposites has been an area of high scientific and industrial attention due to noteworthy improvements attained in these materials, arising from the synergetic combination of properties of a polymeric matrix and an organic or inorganic nanomaterial. The enhanced performance of those materials typically involves superior mechanical strength, toughness and stiffness, electrical and thermal conductivity, better flame retardancy and a higher barrier to moisture and gases. Nanocomposites can also display unique design possibilities, which provide exceptional advantages in developing multifunctional materials with desired properties for specific applications. On the other hand, machine learning (ML) has been recognized as a powerful predictive tool for data-driven multi-physical modelling, leading to unprecedented insights and an exploration of the system's properties beyond the capability of traditional computational and experimental analyses. This article aims to provide a brief overview of the most important findings related to the application of ML for the rational design of polymeric nanocomposites. Prediction, optimization, feature identification and uncertainty quantification are presented along with different ML algorithms used in the field of polymeric nanocomposites for property prediction, and selected examples are discussed. Finally, conclusions and future perspectives are highlighted.