Work

CGAOA-AttBiGRU: A Novel Deep Learning Framework for Forecasting CO2 Emissions

Year: 2024

Type: article

Abstract: Background: Accurately predicting carbon dioxide (CO2) emissions is crucial for environmental protection. Currently, there are two main issues with predicting CO2 emissions: (1) existing CO2 emission prediction models mainly rely on such as Long Short-Term Memory (LSTM) and Gate Recurrent Unit (GRU), which can only model unidirectional temporal features, resulting in insufficient accuracy: (2) existing research on CO2 emissions mainly focuses on designing predictive models, without paying attention to model optimization, resulting in models being unable to achieve their optimal performance. Methods: To address the aforementioned issues, this paper proposed a framework for predicting CO2 emissions, named as CGAOA-AttBiGRU. In this framework, Attentional-Bidirectional Gate Recurrent Unit (AttBiGRU) is a prediction model that uses BiGRU units to extract bidirectional temporal features from the data, and adopts an attention mechanism to adaptively weight the bidirectional temporal features, thereby improving prediction accuracy. CGAOA is an improved Arithmetic Optimization Algorithm (AOA) used to optimize the 5 key hyperparameters of the AttBiGRU. Results: We first validated the optimization performance of the improved CGAOA algorithm on 24 benchmark functions. Then, CGAOA was used to optimize AttBiGRU and compared with 12 optimization algorithms. The results indicate that the AttBiGRU optimized by CGAOA has the best predictive performance. Finally, the optimized AttBiGRU was compared with the BiGRU, LSTM, GRU, ANN, and SVM on predicting CO2 emissions from 4 sectors in China. The experimental results showed that AttBiGRU is significantly better than the comparison models. Conclusions: This paper proposed a novel framework, CGAOA-AttBiGRU, for predicting CO2 emissions. This framework not only includes predictive models, but also optimization method for the models. This study will guide researchers to not only focus on proposing new predictive models, but also on model optimization.

Source: Mathematics

DOI: 10.3390/math12182956