DSSAE-BBOA: deep learning-based weather big data analysis and visualization

The weather forecasting process is used to predict the future atmospheric condition of a specified location. The evolution of the big data era gives the chances to significantly increase the prediction accuracy of weather conditions. In this paper, a deep learning-based stacked sparse autoencoder (D...

Full description

Saved in:
Bibliographic Details
Published in:Multimedia tools and applications Vol. 80; no. 18; pp. 27471 - 27493
Main Authors: G, Madhukar Rao, Dharavath, Ramesh
Format: Journal Article
Language:English
Published: New York Springer US 01.07.2021
Springer Nature B.V
Subjects:
Accuracy
Algorithms
Atmospheric models
Big Data
Computer Communication Networks
Computer Science
Data analysis
Data Structures and Information Theory
Deep learning
Feature extraction
Machine learning
Meteorological data
Model accuracy
Multimedia Information Systems
Optimization
Prediction models
Principal components analysis
Special Purpose and Application-Based Systems
Weather forecasting
Feature selection
Stacked sparse autoencoder
Weather forecasting
Optimization
ISSN:1380-7501, 1573-7721
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The weather forecasting process is used to predict the future atmospheric condition of a specified location. The evolution of the big data era gives the chances to significantly increase the prediction accuracy of weather conditions. In this paper, a deep learning-based stacked sparse autoencoder (DSSAE) has been proposed for predicting the weather condition of a particular area. This model requires a pre-processing approach to obtain essential data from big weather data and increase the prediction model’s speed. For this, the principal component analysis (PCA) is utilized to reduce dimensionality and extraction of features with more significant variance. Also, it integrates the feature selection algorithm based on Binary Butterfly Optimization Algorithm (BBOA) along with a deep stack autoencoder to improve prediction accuracy. The proposed model is validated using the weather data taken from the division of weather underground for short term and long term weather prediction. The simulation consequences illustrate that the proposed model overtakes the existing models in terms of computation time, accuracy and error rate.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1380-7501
1573-7721
DOI:10.1007/s11042-021-11059-9