The UV Index Prediction aims to tackle the serious public health concern of ultraviolet radiation exposure, which can result in serious health disorders such as skin cancer, cataracts and other UV-related illnesses. Because of the temporal interdependence and complex structure of environmental data, traditional methods of UV index prediction are not always accurate. This study aims to implement Long Short Term Memory (LSTM) neural networks, a kind of recurrent neural network (RNN) renowned for its adeptness in processing sequential input, to overcome these obstacles. The research methodology consists of several important stages, including literature review, data collection from dependable sources including environmental agencies and meteorological departments, and LSTM model deployment. The gathered data is pre-processed to make sure it is relevant and of high quality before being processed by the LSTM model. To maximize the prediction performance of the model, historical UV index data is used for training and validation. The LSTM model is chosen because of its capability to recognize and understand long-term dependencies in data. The developed model demonstrated prediction performance with MAE at 0.074 and MSE at 0.008 as well as RMSE at 0.091. A moderate level of relationship exists between the model inputs and outputs as shown in the R-squared value of 0.41. Additionally, the system successfully predicted UV index levels with accuracy of 81.46%. The LSTM model has also demonstrated higher performance when compared to Random Forest algorithm. Among future works are to include more and real time data for better prediction accuracy.