Incremental-decremental data transformation based ensemble deep learning model (IDT-eDL) for temperature prediction

Human life heavily depends on weather conditions, which affect the necessary operations like agriculture, aviation, tourism, industries, etc., where the temperature plays a vital role in deciding the weather conditions along with other meteorological variables. Therefore, temperature forecasting has drawn considerable attention from researchers because of its significant effect on daily life activities and the ever-challenging forecasting task. These research objectives are to investigate the transformation of data based on incremental and decremental approaches and to find the practical ensemble approach over proposed models for effective temperature prediction, where the proposed model is called the Incremental-Decremental Data Transformation-Based Ensemble Deep Learning Model (IDT-eDL). The temperature dataset from Delhi, India, has been utilized to compare proposed and traditional deep learning models over various performance measures. The proposed IDT-eDL with BiLSTM deep learning model (i.e., IDT-eDL_BiLSTM ) has performed the best among the proposed models and traditional deep learning model and achieved Performance over measures MSE: 1.36, RMSE: 1.16, MAE: 0.89, MAPE: 4.13 and R2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$R<^>2$$\end{document}:0.999. Additionally, non-parametric statistical analysis of Friedman ranking is also performed to validate the effectiveness of the proposed IDT-eDL model, which also shows a higher ranking of the proposed model than the traditional deep learning models.