The current and long-term regional economic imbalance in China requires ongoing attention. To ensure the balanced development of China’s renewable energy, it is therefore important to examine the causes of the differences in China’s renewable energy from a variety of perspectives. The spatial distribution pattern and characteristics of China’s per capita GDP (gross domestic product) from 2012 to 2021 were examined in this study using the exploratory spatial data analysis tool. In addition, it conducts an empirical investigation into the spatial spillover effect of RED and the manufacturing agglomeration in China (regional economic development). The findings indicate that in the eastern region, the total backward link value of the feedback effect of 17 industrial sectors is 0.8524, and in the central region, the value is 0.8139. The real per capita GDP of neighboring provinces will increase by 0.118% for every 1% increase in manufacturing agglomeration level. According to the overall ranking, China’s RED level is very uneven due to a number of factors. We should direct and encourage the manufacturing industry to congregate in various regions, optimize the spatial pattern of manufacturing industry agglomeration, and fully exploit SSE in order to promote China’s RED and reduce the difference in RE.

Accurate prediction of crude oil prices (COPs) is a challenge for academia and industry. Therefore, the present research developed a new CEEMDAN-GA-SVR hybrid model to predict COPs, incorporating complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), a genetic algorithm (GA), and support vector regression machine (SVR). First, our team utilized CEEMDAN to realize the decomposition of a raw series of COPs into a group of comparatively simpler subseries. Second, SVR was utilized to predict values for every decomposed subseries separately. Owing to the intricate parametric settings of SVR, GA was employed to achieve the parametric optimisation of SVR during forecast. Then, our team assembled the forecasted values of the entire subseries as the forecasted values of the CEEMDAN-GA-SVR model. After a series of experiments and comparison of the results, we discovered that the CEEMDAN-GA-SVR model remarkably outperformed single and ensemble benchmark models, as displayed by a case study finished based on a time series of weekly Brent COPs.