Time Series Weather Prediction Through Recurrent Neural Network
International Journal of Science, Strategic Management and Technology · 20.03.2026 · 02 (03) · 1-9
DOI: 10.55041/ijsmt.v2i3.160 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Science, Strategic Management and Technology, online erschienen am 20.03.2026. Verfasst von SAYANTAN CHAKRABORTY.
Abstract (Originalsprache)
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
Zitieren
APA
CHAKRABORTY, S. (2026). Time Series Weather Prediction Through Recurrent Neural Network. International Journal of Science, Strategic Management and Technology, 02(03), 1-9. https://doi.org/10.55041/ijsmt.v2i3.160
Vancouver
CHAKRABORTY S. Time Series Weather Prediction Through Recurrent Neural Network. International Journal of Science, Strategic Management and Technology. 2026;02(03):1-9. doi:10.55041/ijsmt.v2i3.160
BibTeX
@article{CHAKRABORTY2026,
author = {CHAKRABORTY, SAYANTAN},
title = {Time Series Weather Prediction Through Recurrent Neural Network},
journal = {International Journal of Science, Strategic Management and Technology},
year = {2026},
volume = {02},
number = {03},
pages = {1--9},
doi = {10.55041/ijsmt.v2i3.160}
}
EUVIMED