The field of degradation modelling is witnessing significant advancements, driven by the increasing adoption of data-driven methods and machine learning techniques. Researchers are exploring innovative approaches to improve the accuracy and reliability of predictive models, enabling better maintenance and optimization of complex systems. A key trend is the integration of multi-source data and the development of hybrid models that combine different techniques, such as regression analysis, Bayesian statistics, and deep learning. These advancements have far-reaching implications for various applications, including energy storage, transportation, and medicine. Noteworthy papers in this area include:

• A study that presents a hybrid learning framework for accurate battery lifespan prediction, achieving significant improvements in prediction accuracy.
• A comparative study of deep learning and ensemble learning methods for long-term traffic forecasting, highlighting the importance of time embedding and periodicity modelling.