This study proposes a novel method for predicting the discharge capacity of lithium-ion (Li-ion) batteries using a digital twin (DT) model. By combining advanced machine learning techniques, such as AdaBoost and long short-term memory (LSTM) networks, with a semiempirical mathematical structure, the DT model is constructed to mimic the behavior of actual batteries in real time. Various metaheuristic optimization methods, including antlion, grey wolf optimization (GWO), and improved grey wolf optimization (IGWO), are used to adjust hyperparameters and optimize the models. Performance indicators such as mean absolute error (MAE) and root-mean-square error (RMSE) are applied after extensive training and ten-fold cross-validation. The IGWO-AdaBoost DT model emerges as the standout performer, achieving exceptional accuracy with MAE of 0.01 and RMSE of 0.01. The study demonstrates the potential of the DT model to accurately predict battery discharge capacity. The research highlights the integration of machine learning and metaheuristic optimization techniques to enhance predictive accuracy and model performance. The proposed DT model is validated using the NASA battery aging dataset, a widely accepted benchmark for battery research. The findings indicate that the IGWO-AdaBoost DT model provides the most accurate predictions, showcasing its effectiveness in estimating battery discharge capacity. The study contributes to the development of reliable and efficient battery management systems, supporting sustainable energy solutions and reducing environmental impact. The results emphasize the importance of hyperparameter tuning and metaheuristic optimization in improving model accuracy and robustness. The proposed method offers a promising approach for real-time battery health monitoring and predictive maintenance, aligning with global sustainability goals.This study proposes a novel method for predicting the discharge capacity of lithium-ion (Li-ion) batteries using a digital twin (DT) model. By combining advanced machine learning techniques, such as AdaBoost and long short-term memory (LSTM) networks, with a semiempirical mathematical structure, the DT model is constructed to mimic the behavior of actual batteries in real time. Various metaheuristic optimization methods, including antlion, grey wolf optimization (GWO), and improved grey wolf optimization (IGWO), are used to adjust hyperparameters and optimize the models. Performance indicators such as mean absolute error (MAE) and root-mean-square error (RMSE) are applied after extensive training and ten-fold cross-validation. The IGWO-AdaBoost DT model emerges as the standout performer, achieving exceptional accuracy with MAE of 0.01 and RMSE of 0.01. The study demonstrates the potential of the DT model to accurately predict battery discharge capacity. The research highlights the integration of machine learning and metaheuristic optimization techniques to enhance predictive accuracy and model performance. The proposed DT model is validated using the NASA battery aging dataset, a widely accepted benchmark for battery research. The findings indicate that the IGWO-AdaBoost DT model provides the most accurate predictions, showcasing its effectiveness in estimating battery discharge capacity. The study contributes to the development of reliable and efficient battery management systems, supporting sustainable energy solutions and reducing environmental impact. The results emphasize the importance of hyperparameter tuning and metaheuristic optimization in improving model accuracy and robustness. The proposed method offers a promising approach for real-time battery health monitoring and predictive maintenance, aligning with global sustainability goals.