Leveraging Machine Learning to Predict Volcanic Eruptions by Function Neural Networks

When it comes to volcanic eruption surveillance, techniques that rely on seismic analysis of data tend to use automatic methods that ignore the fact that volcanic formations are varied and flexible. Sophisticated procedures for data categorization and assessment, evaluation, investigation and interpretation are needed to identify small variations in seismic sequences linked with volcanic instability. Machine Learning (ML) and Deep Learning (DL) technologies are continually being devised to better machine extraction and processing of valuable data. The proposed study has employed Radial Basis Function Neural Networks (RBFNN) to predict volcanic eruptions in Indonesia. Further, the proposed RBFNN model is compared with other Neural Network (NN) models and it was observed that RBFNN has outperformed all other models in terms of accuracy.