An Improved Multivariate Weather Prediction Model Using Deep Neural Networks and Particle Swarm Optimisation

K U Jaseena and Binsu C Kovoor ()
Additional contact information
K U Jaseena: Division of Information Technology, School of Engineering, Cochin University of Science and Technology, Kochi, Kerala, India†Department of Computer Applications, MES College Marampally, Aluva, Kochi, Kerala, India
Binsu C Kovoor: Division of Information Technology, School of Engineering, Cochin University of Science and Technology, Kochi, Kerala, India

Journal of Information & Knowledge Management (JIKM), 2021, vol. 20, issue 03, 1-24

Abstract: Accurate weather prediction is always a challenge for meteorologists. This paper suggests a Deep Neural Network (DNN) model to predict minimum and maximum values of temperature based on various weather parameters such as humidity, dew point, and wind speed. Particle Swarm Optimisation (PSO) algorithm is applied to select relevant and important features of the datasets to improve the prediction accuracy of the model. The grid search algorithm is employed to determine the hyperparameters of the proposed DNN model. The statistical indicators Mean Square Error, Mean Absolute Error, Mean Absolute Percentage Error, Nash–Sutcliffe model efficiency coefficient, and Correlation Coefficient are used to evaluate the accuracy of the prediction model. Performance comparison of the proposed model is performed with the Support Vector Machine (SVM) and Vector Autoregression (VAR) models. The experimental outcomes show that the proposed model optimised using PSO achieves better prediction accuracy than traditional approaches.

Keywords: Weather forecasting; feature selection; particle swarm optimisation; grid search; deep neural networks (search for similar items in EconPapers)
Date: 2021
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S0219649221500295
Access to full text is restricted to subscribers

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:jikmxx:v:20:y:2021:i:03:n:s0219649221500295

Ordering information: This journal article can be ordered from

DOI: 10.1142/S0219649221500295

Access Statistics for this article

Journal of Information & Knowledge Management (JIKM) is currently edited by Professor Suliman Hawamdeh

More articles in Journal of Information & Knowledge Management (JIKM) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().