Application and Effectiveness Evaluation of BP Neural Network Model Based on Rafflesia Optimization Algorithm Optimization in Daily Average Temperature Prediction

With economic and social development, the impact of climate change on human social life is constantly deepening. The ability to accurately predict trends in meteorological data has become an important area of research at present. The main focus of this research is to explore the application and evaluation of the effectiveness of a BP neural network model based on the optimization of the Rafflesia Optimization Algorithm(ROA) for daily average temperature prediction. The data for this study uses a large amount of historical meteorological data as the training set, including date, time and the corresponding daily mean temperature. The prediction model was constructed using a BP neural network-based temperature prediction model, and the ROA was used to optimise the weights and biases of the BP neural network to improve the accuracy and reliability of the prediction model. The experimental results show that the optimized BP neural network model has higher accuracy and stability in predicting the daily average temperature compared with the traditional BP neural network model. The optimised model is also able to better capture the non-linear relationships and time-series features in the meteorological data, thus improving the accuracy and reliability of the prediction. This research can provide a reliable tool for meteorological prediction and climate research, which helps to accurately predict future climate change trends and provide scientific basis and decision support for future economic and social development and human life progress.