Study on the Evolutionary Characteristics of Spatial and Temporal Patterns and Decoupling Effect of Urban Carbon Emissions in the Yangtze River Delta Region Based on Neural Network Optimized by Aquila Optimizer with Nighttime Light Data

Xichun Luo, Chaoming Cai and Honghao Zhao ()
Additional contact information
Xichun Luo: The Institute for Sustainable Development, Macau University of Science and Technology, Taipa, Macao 999078, China
Chaoming Cai: School of Geography, South China Normal University, Guangzhou 510631, China
Honghao Zhao: Department of Decision Sciences, School of Business, Macau University of Science and Technology, Taipa, Macao 999078, China

Land, 2024, vol. 14, issue 1, 1-23

Abstract: China produces the largest amount of CO 2 emissions since 2007 and is the second largest economy in the world since 2010, and the Yangtze River Delta (YRD) area plays a crucial role in promoting low-carbon development in China. Analyzing its evolutionary characteristics of spatial and temporal patterns and its decoupling effect is of great importance for the purpose of low-carbon development. However, this analysis relies on the estimation of CO 2 emissions. Recently, neural network-based models are widely used for CO 2 emission estimation. To improve the performance of neural network models, the Aquila Optimizer (AO) algorithm is introduced to optimize the hyper-parameter values in the back-propagation (BP) neural network model in this research due to the appealing searching capability of AO over traditional algorithms. Such a model is referred to as the AO-BP model, and this paper uses the AO-BP model to estimate carbon emissions, compiles a city-level CO 2 emission inventory for the YRD region, and analyzes the spatial dependence, spatial correlation characteristics, and decoupling status of carbon emissions. The results show that the CO 2 emissions in the YRD region show a spatial distribution pattern of “low in the west, high in the east, and developing towards the west”. There exists a spatial dependence of carbon emissions in the cities from 2001 to 2022, except for the year 2000, and the local spatial autocorrelation test shows that high-high is concentrated in Shanghai and Suzhou, and low-low is mainly centered in Anqing, Chizhou, and Huangshan in southern Anhui. Furthermore, there exist significant regional differences in the correlation levels of CO 2 emissions between cities, with a trend of low in the west and high in the east in location, and a decreasing and then increasing trend in time. From 2000 to 2022, the decoupling of carbon emissions and economic growth shows a steadily improving trend.

Keywords: CO 2 emission; nighttime light data; aquila optimizer neural network; spatial and temporal patterns; decoupling effect (search for similar items in EconPapers)
JEL-codes: Q15 Q2 Q24 Q28 Q5 R14 R52 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2073-445X/14/1/51/pdf (application/pdf)
https://www.mdpi.com/2073-445X/14/1/51/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jlands:v:14:y:2024:i:1:p:51-:d:1556044

Access Statistics for this article

Land is currently edited by Ms. Carol Ma

More articles in Land from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().