Prediction and Analysis of CO2 Emissions Based on Regularized Extreme Learning Machine Optimized by Adaptive Whale Optimization Algorithm
Wei Sun 1,   Yawen Wang 1  
More details
Hide details
Department of Business Administration, North China Electric Power University, Baoding 071000, China
Yawen Wang   

Department of Business Administration, North China Electric Power University, China
Submission date: 2020-09-23
Final revision date: 2020-10-19
Acceptance date: 2020-11-02
Online publication date: 2021-02-22
With the rapid increase in CO2 emissions, there is a profound impact on global climate change, seriously hindering the sustainable development of the low-carbon economy. Therefore, it is particularly significant to predict CO2 emissions. To improve the accuracy and robustness, a new hybrid model (KPCA-CEEMDAN-AWOA-RELM) is proposed when considering multiple factors about historical CO2 emissions, energy consumption, economic and social. First, factors are determined by Pearson doubly significant test, and the principal component is extracted by kernel principal component analysis (KPCA) to realize nonlinear dimension reduction. Then, the CO2 emissions sequence is decomposed by the ensemble empirical model with adaptive noise (CEEMDAN) model to reduce noise interference and abate reconstruction error. Finally, CO2 emissions can be predicted via the extreme learning machine with regularization parameter modification optimized by an improved input weight matrix and the deviation matrix of the adaptive optimization whale algorithm (AWOA-RELM). Taking Hebei and China as examples, it is found that the selected model is better than other comparative models.