No abstract

Coping with the relation between the increase in carbon emissions and energy consumption in the transportation sector is a pressing issue today. Machine learning and deep neural networks were used in this study to explore the influential factors and trends in future transportation carbon emissions. First, the least absolute shrinkage and selection operator (LASSO) regression was adopted to screen out the key influencing factors in transportation carbon emissions. Second, the prediction performance of the long short-term memory (LSTM) network, generalized regress neural network (GRNN), and back propagation (BP) network were compared, and an improved LSTM optimized by the sparrow search algorithm (SSA) was proposed. Third, LASSO-SSA-LSTM was used to predict the transportation sector’s future carbon emissions trends under different scenarios. The results suggested that transportation carbon emissions in China presented a trend of “rapid increase - fluctuating decrease - continuous increase” from 2010 to 2019. Although the main determinant in curbing the rising rate of carbon emissions effectively is the continuous development of new clean energy technology, the variation in transportation carbon emissions in China under eight scenarios showed significant differences. Generally, systemic changes and innovations are crucial to accommodate China’s future low-carbon and sustainable transportation development.

As a nature-inspired metaheuristic algorithm, salp swarm algorithm (SSA) still suffers from low searching efficiency and easily falling into local optimum, especially when solving composite problem. In order to enhance the performance of SSA, an improved SSA equipped with sine cosine algorithm and normal cloud generator (CSCSSA) is proposed in this paper. The sine and cosine operator can prevent the salp leader from ineffective search for possible food position, and speed up the search rate of SSA. In addition, the normal cloud generator is employed to replace the position update mechanismof salp followers, and enhance the diversity by generating cloud drops around the salp leader. Comprehensive comparison of CSCSSA and seven other optimization algorithms was conducted on CEC2017 benchmark functions. The statistical results and convergence curves prove that the CSCSSA can be considered as highly competitive algorithm according to the searching efficiency, convergence accuracy and the ability of local optimum avoidance.

No abstract

No abstract