Time Series Weather Prediction Through Recurrent Neural Network

CHAKRABORTY, SAYANTAN

doi:https://doi.org/10.55041/ijsmt.v2i3.160

Plagiarism Passed

Peer reviewed

Open Access

TIME SERIES WEATHER PREDICTION THROUGH RECURRENT NEURAL NETWORK

AUTHORS:

SAYANTAN CHAKRABORTY

Mentor

Affiliation

DOI: 10.55041/ijsmt.v2i3.160

CC BY 4.0 License:

This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

DOWNLOAD ARTICLE

REVIEW REPORT

CITE THIS ARTICLE

Abstract

This research introduces a predictive system that uses deep learning methods to predict multiple weather variables. The research team created a Long Short-Term Memory (LSTM) model with multiple layers to model the intricate time-dependent relationships present in atmospheric data which includes temperature and humidity and pressure and wind speed. The model successfully solves the meteorological system's non-linear behavior through its implementation of a stacked architecture and a sliding-window sequence generation technique. The evaluation of performance used standard baseline models ARIMA and GRU to measure performance through two metrics which were Mean Squared Error and Mean Absolute Error. The proposed LSTM framework provides better short-term temperature prediction accuracy which functions as an effective tool for modeling local atmospheric conditions

Keywords

Article Information

Article Metrics

Article Views

PDF Downloads

HOW TO CITE

References

Ethics and Compliance

✓ All ethical standards met

This article has undergone plagiarism screening and double-blind peer review. Editorial policies have been followed. Authors retain copyright under CC BY-NC 4.0 license. The research complies with ethical standards and institutional guidelines.

Indexed In