Long-term forecasting of the dynamics of mean solar magnetic field with the fuzzy inductive reasoning model

Abstract

The accumulation of large amounts of data in a variety of domains creates a demand for the development of new tools for data processing and forecasting for decision support. The article is devoted to the long-term forecast of the mean solar magnetic field obtained with the fuzzy inductive reasoning (FIR) model. The model is generated automatically with the AimDSS computer program developed by the authors earlier. AimDSS is a cross-platform, standalone program which implements the FIR methodology for model creation. Authors generated the model for long-term mean solar magnetic field prediction until 2030. The model was evaluated against the control sample with the RMSE 0.0964. The forecast also matches the long-term solar activity forecast created by the authors with the Wolf number datasets earlier. Further study will be focused on elaboration of the constructed model with the final aim of obtaining a set of inductive models for application in different domains.