Sunspot Number Prediction/Forecast​ing via a Hybrid Regression-Neural Network Based Model

The program predicts/forecasts smoothed sunspot numbers for dates specified by user
249 download
Aggiornato 28 mar 2018

Visualizza la licenza

The program is used to predict/forecast sunspot numbers based on dates input by user. The main program to run is named Main_Program.m. Users should input the dates for their desired SSN predictions in line 2 of the program. The dates are expressed as years (or as year fractions). For example, if a user desires the SSN for 11th January 2019, then the date is entered as 2019+11/365.
Users can also enter a range of dates by using the MATLAB colon operator (:). For example, to request the SSN for all days from years 2018 to middle of 2019, the user should input 2018:1/365:2019.5.
The model is based on a Hybrid Regression-Neural Network (HR-NN) Method for forecasting SSN (detailed in an article in preparation)
SSN Outputs/Predictions are written to a file named Output_SSN_Predictions.txt created within the same folder where the program is ran from.
For this version of the program, reliable prediction is recommended between years 1824 and 2020.

Cita come

Daniel Okoh (2024). Sunspot Number Prediction/Forecasting via a Hybrid Regression-Neural Network Based Model (https://www.mathworks.com/matlabcentral/fileexchange/65686-sunspot-number-prediction-forecasting-via-a-hybrid-regression-neural-network-based-model), MATLAB Central File Exchange. Recuperato .

Compatibilità della release di MATLAB
Creato con R2016b
Compatibile con qualsiasi release
Compatibilità della piattaforma
Windows macOS Linux
Categorie
Scopri di più su Dates and Time in Help Center e MATLAB Answers

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

SSN Predictions/

Versione Pubblicato Note della release
1.1.0.0

The precursor Ap index for Solar Cycle 25 is roughly estimated as 5.6 nT for this version (version 1.1). In the previous version (version 1.0), the value was arbitrarily chosen as 10.8 nT (the mean of year 2017 Ap values).

1.0.0.0

First program update