Search

• A framework is proposed to integrate machine learning, ecological footprints and PLUS models. • Coupling of multiple data sources with machine learning algorithms improves classification accuracy. • The random forest algorithm is optimal for comparison accuracy. • Improved ecological footprint models to improve the accuracy of ECC. • Restoration of forest land with the highest ECC potential. Ecological carrying capacity is key to evaluating sustainable development capacity, and land use change has varying degrees of impact on ecosystems. This study explores the ecological carrying capacity based on land use change, which is important for the conservation and scientific and rational use of ecosystems. Therefore, in this study, three machine learning classification 3algorithms, namely support vector machine, random forest and artificial neural network, were selected for accuracy comparison and analysis based on multi-source data, using Southwest Guangxi Karst-Beibu Gulf as the study area. The Patch-generating Land Use Simulation Model is used to dissect the spatial and temporal changes in ecological carrying capaciyt from 1990 to 2040 and future trends. The results showed that (1) Coupling multiple sources of data and machine learning classification algorithms can ultimately improve land use classification accuracy. The RF is compared and found to be the optimal classification algorithm for this study. (2) The area of arable and grassland gradually decreases between 1990 and 2040, mainly encroached upon by build land; the area of forested land gradually recovers, the watershed fluctuates up and down, and the area of build land gradually increases. (3) The ecological carrying capacity from 1990 to 2040 shows a trend of decreasing and then increasing, and the area of low and medium–low decreases from 2020 to 2040, with arable land and forest land having a stronger potential to increase ecological carrying capacity. Nanning City, Qinzhou City and Chongzuo City are severely damaged. The framework provides an effective tool for exploring future ecological carrying capacity to support the ecological conservation and future sustainable development of the region. [ABSTRACT FROM AUTHOR]

• Exploring the change of ESV pattern under "Production-Living-Ecological Space". • Analysis of ESV distribution characteristics in multi-characteristic regions. • Spatial autocorrelation analysis reveals the regional ESV spatial aggregation state. • A standard deviation ellipse inscribes the regional ESV center of gravity migration. • Natural, economic, and social variables all have a role in regional ESV development. In order to investigate the changing patterns and influencing factors of ecosystem service values (ESV) provided by the "production-life-ecological space" (PLES) in the karst-Beibu Gulf of southwest Guangxi under the geographical characteristics of the mountain-river-sea transition zone, this study selected land use data at four time points from 1990 to 2020, clarified the characteristics of regional ESV evolution through spatial autocorrelation analysis and standard deviation ellipse, and explored its formation mechanism with the help of geographic probes. The results showed that: (1) The overall spatial variation of the total ESV in the study area was obvious, with "high in the southwest and low in the northeast" and a decreasing trend in general. (2) The ESV in PLES perspective showed positive spatial autocorrelation overall and exhibited obvious spatial aggregation characteristics. Their center of gravity as a whole shifts to the southeast, the ellipse area keeps expanding, and the center of gravity positions all remain in Nanning City. (3) ESV evolution is closely related to natural, economic, and social factors, with rocky desertification area and Normalized Difference Vegetation Index (NDVI) having the most significant spatial differentiation effect on ESV provided by production space and ecological space, average altitude contributing more to ESV provided by living space, and interaction between various elements improving ESV differentiation from the perspective of PLES. The results of the study provide a scientific basis for optimizing regional territorial spatial planning and improving regional ESV. [ABSTRACT FROM AUTHOR]

• Compared with intelligent classification algorithms of remote sensing, the algorithm with the highest accuracy was selected. • Explore the impact of land use change on ecosystem service value. • Analyze implications for SDGs reporting and regional sustainable development. Ecosystem services provide a variety of benefits for mankind, and their sustainable use plays an important role in achieving the Sustainable Development Goals (SDGs). This study takes Guangxi as the research object and compares multiple intelligent classification algorithms for land cover based on multi-source data. Selects Random Forest (RF) classification algorithms for land cover classification, analyses their temporal and spatial changes, and the extracted results produce SDG 15.1.1, 15.1.2, 15.1.4 indicators, and assess the degree of completion of Guangxi's SDGs 15.2 indicators. On this basis, the equivalent factor method was used to evaluate the change of ecosystem value caused by land use change, and the direct impact of land use change on SDG15.9 was evaluated. The results indicate that:(1) From 1990 to 2020, forest was the most important land use mode in Guangxi, and the most serious wetland shrinkage was in Beihai and Nanning; The overall trend of land use changes is that wetlands, forests, and grasslands have decreased, dry land and construction land have increased, and bare land has remained basically remained unchanged. (2) From 1990 to 2020, the SDG 15.1.1 indicator showed a slow rise and then a rapid decline. The SDG 15.1.2 indicator showed a continuous downward trend. The SDG 15.1.4 indicator showed a steady upward trend. Guangxi failed to achieve the target of SDG15.2 by 2020. (3) From 1990 to 2020, the overall ecosystem service value in Guangxi showed a decreasing trend, and the one-way ecosystem service value in Guangxi was dominated by hydrological regulation and climate regulation. The ecosystem service value showed a spatial pattern of "low in the central region and high in the surrounding areas." (4) Grassland to forest and dryland to forest were the main types of ecological service income; Forest conversion to dryland is the most important type of ecological service loss. (5) As a whole, only dryland sensitivity index less than 0 during 2010–2015 had a negative impact on Ecosystem services values (ESV), while other time and land use type sensitivity index were all greater than 0 had a positive impact on ESV. [ABSTRACT FROM AUTHOR]