Accuracy achieved by the Intensified LSTM based rainfall prediction model is 87.99%. Figure 9. Comparison of accuracy for Neural Network based prediction models. The comparison of accuracies and RMSE of the predictive models, including the statistical methods, is shown in the form of a bar chart in Figure 10.

Intensified LSTM based Recurrent Neural Network is constructed to predict rainfall. This approach is compared with other methods, namely, Holt–Winter, ARIMA, ELM, RNN and LSTM, in order to demonstrate the improvement of rainfall prediction in the proposed approach. For attaining good accuracy, it is necessary to consider previous datasets.

The LSTM network has been widely used for rainfall prediction due to its ability to capture long-term dependencies in time series data. In this study, we trained and evaluated an LSTM network for rainfall prediction using the sequential input and data window input approaches.

From the literature reviewed, three models based on the LSTM and Stacked-LSTM Networks were adapted for the task of forecasting hourly rainfall using time-series data from five major UK cities.