A new neurocomputing approach for medium-range temperature prediction

Authors

  • PRAVATRABI NASKAR Meteorological office Port Blair, India Meteorological Department, MoES, Port Blair – 744 106, India
  • SOMNATH NASKAR Department of Industrial Engineering, Maulana Abul Kalam Azad University of Technology, Kolkata – 700 064, India

DOI:

https://doi.org/10.54302/mausam.v73i3.5931

Keywords:

Neurocomputing, Long short term memory, Variational mode decomposition, Port Blair

Abstract

To predict medium-range temperature with appreciable accuracy this study has been undertaken. We have tried to predict max-min temperature time series (signal) 5, 7 and 9 days ahead with the help of a new machine learning (neurocomputing) technique. Variational Mode Decomposition (VMD) has been used to decompose temperature time series and decomposed modes obtained from VMD have been individually used as input to Long Short Term Memory (LSTM). The LSTM predicted the modes individually and predicted modes are combined to generate the predicted signal. The signal predicted by this method closely matches with the actual test signal and minimizes the error in predicting the signal.

Downloads

Published

01-07-2022

How to Cite

[1]
P. . NASKAR and S. . NASKAR, “A new neurocomputing approach for medium-range temperature prediction”, MAUSAM, vol. 73, no. 3, pp. 537–554, Jul. 2022.

Issue

Vol. 73 No. 3 (2022): MAUSAM

Section

Research Papers

License

Copyright (c) 2022 MAUSAM

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

All articles published by MAUSAM are licensed under the Creative Commons Attribution 4.0 International License. This permits anyone.

Anyone is free:

  • To Share - to copy, distribute and transmit the work
  • To Remix - to adapt the work.

Under the following conditions:

  • Share - copy and redistribute the material in any medium or format
  • Adapt - remix, transform, and build upon the material for any purpose, even
    commercially.