Identifying influencing factors and characterizing key issues in urban sustainable development capacity through machine learning

In response to the United Nations Sustainable Development Goals and China’s“Dual Carbon”Goals(DCGs means the goals of“Carbon Peak and carbon neutrality”),this paper from the perspective of the construction of China’s Innovation Demonstration Zones for Sustainable Development Agenda(IDZSDAs),combines carbon emission-related metrics to construct a comprehensive assessment system for Urban Sustainable Development Capacity(USDC).After obtaining USDC assessment results through the assessment system,an approach combining Least Absolute Shrinkage and Selection Operator(LASSO)regression and Random Forest(RF)based on machine learning is proposed for identifying influencing factors and characterizing key issues.Combining Coupling Coordination Degree(CCD)analysis,the study further summarizes the systemic patterns and future directions of urban sustainable development.A case study on the IDZSDAs from 2015 to 2022 reveals that:(1)the combined identification method based on machine learning and CCD models effectively quantifies influencing factors and key issues in the urban sustainable development process;(2)the correspondence between influencing factors and key subsystems identified by the LASSO-RF combination model is generally consistent with the development situations in various cities;and(3)the machine learning-based combined recognition method is scalable and dynamic.It enables decision-makers to accurately identify influencing factors and characterize key issues based on actual urban development needs.

Assessing forest sustainability trajectory with temporal changes in timber output and ecological reserve: the case of China

We classified forest resources into four modes：high timber output and high ecological reserve（Mode T-E）; high timber output and low ecological reserve（Mode T-e）; low timber output and low ecological reserve（Mode t-e）; and low timber output and high ecological reserve（Mode t-E）. Ecological reserve is stand volume per unit area of natural forests and total area of natural forests;timber output is defined as total area of timber forests and unit area of timber production. We used this classification system to examine forest development in China between1950 and 2013. Data were acquired mainly from forest inventory statistics published by China’s Forestry Administration between the 1970 s and 2013. I Information from the 1950 s was acquired from relevant literature. Our analysis suggests that China’s forest resources transitioned from Mode t-E to Mode T-e during the period between the early 1950 s and late 1970 s, resulting in the destruction of both ecological vigor and timber resources. During the following 20 years, strategies were implemented to improve the ecological reserve and increase timber supply,resulting in a decline in the rate of forest degradation. Over the past decade, China’s forest resources have reached Mode T-E as a result of improvements in both the ecological reserve and the timber supply. Currently, the total area of timber forests is relatively low, representing the limiting factor for improvement in overall forest functionality. Nevertheless, along with increased efforts to protect natural forests and develop fast-growing forest plantations, it is hopeful that China’s forest resources will achieve a sustainable state. The four-mode TOER（timber output, ecological reserve） method introduced in this paper is a simple but an effective approach for characterizing the overall quality and quantity of forest resources. The data used for this type of evaluation are typically easy to obtain and reliable. This methodology has potential to be applied to forests in various regions and countries.

Factor decomposition of carbon emissions in Chinese megacities

In this article, per capita urban carbon emissions were decomposed into manufacturing,transportation, and construction sectors using logarithmic mean Divisia index(LMDI)method. This new decomposition method can provide information about specific drivers of carbon emissions, including urban growth and resident living standards, rather than general demographic and economic factors identified by traditional methods. Using four Chinese megacities(Beijing, Tianjin, Shanghai, and Chongqing) as case studies, we analyzed the factors that influenced per capita carbon emissions from 2010 to 2015. The results showed that per capita carbon emissions increased in Tianjin and Chongqing whereas decreased in Beijing and Shanghai, and that manufacturing was a key driving force. In these four megacities,energy conservation strategies were successfully implemented despite poor energy structure optimization during 2010–2015. Development of manufacturing and improvement of resident living standards in the cities led to an increase in carbon emissions. The unique dual-core urban form of Tianjin might mitigate the increased carbon emissions caused by the transportation sector. Reductions in carbon emissions could be achieved by further optimizing energy structures, limiting the number of private cars, and controlling per capita construction.