In this paper, the ocean acidification prediction problem was studied deeply, and a new prediction model was constructed by using quantum particle swarm optimization algorithm (QPSO) and long short-term memory neural network (LSTM). Firstly, by introducing the quantum particle swarm optimization algorithm, the limitations of the traditional particle swarm optimization algorithm in search accuracy and global search ability are overcome, and the convergence speed and prediction accuracy of the model are improved. Secondly, using the ability of long short-term memory neural network to process time series data, it effectively captures the long-term dependence relationship in ocean acidification data, and further enhances the prediction ability of the model. Finally, through a series of experimental verification and performance evaluation, including root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE) and coefficient of determination (R2), it is proved that the model has high accuracy and generalization ability in ocean acidification prediction. The model provides a new method for the effective prediction of ocean acidification.
Wu D., 2024. Prediction technology of ocean acidification based on quantum particle swarm optimization and long short-term memory network. In 2024 International Conference on Computers, Information Processing and Advanced Education (CIPAE), pp. 361-366. IEEE. Article (subscription required).
