The development of reliable and accurate methods for predicting battery degradation is crucial, as energy storage systems are increasingly becoming the backbone of modern applications, such as electric vehicles and renewable energy networks. In this research, secondary data from a dataset compiled by D. U. Sauer [1], which includes 48 commercially available Sanyo/Panasonic UR18650E cylindrical NMC (Nickel Manganese Cobalt)/graphite were used to model and predict cyclic aging behaviour [2]. The dataset provides begin-of-life (BOL) testing results establishing a performance baseline and periodic aging reference parameter (RPT) tests conducted under consistent conditions. All cells in the dataset were maintained at a similar state of charge, as per manufacturer specifications, to minimize aging effects during storage. Furthermore, the dataset includes temperature equalization at 25°C prior to pulse resistance tests to standardize conditions and eliminate unnecessary additional conditioning. This research uses Cellular Neural Network (CeNN) to simulate and predict the evolution of performance metrics as the batteries undergo aging. The CeNN model is suitable for this task, since it is able to learn both spatial and temporal relationships in the time-series data. By analysing the sequences of test cycles, the CeNN learns the pattern that characterizes the aging phenomenon: progressive increase in internal resistance, along with a gradual loss of capacity over time. This deep learning architecture is trained on historical data of battery performance to predict subsequent behaviours, hence providing a method for estimating the RUL (Remaining Useful Life) of the cells with a high degree of accuracy. Results show that CeNNs by predicting such detailed time-series data, the model can undertake the next step of performance and long-term degradation trend prediction. The techniques developed in this work are also not bound to NMC/graphite batteries. The CeNN-based approach can be applied to various battery chemistries, making it a versatile tool for predicting aging across different scenarios. This helps for better-designed next-generation batteries that improve storage to meet demand for more sustainable energy solutions. This work was funded from BatCAT (HEur GA no. 101137725) and DigiPass CSA (HEur GA no. 101138510).