Search

Mangrove forests are significant blue carbon pools on the Earth with strong carbon sequestration capacity and play an important role in combating climate change. To improve the capacity of regional carbon sinks, China has implemented a Special Action Plan for Mangrove Protection and Restoration (2020–2025). In this context, based on the MaxEnt model, this study analyzed the important environmental factors affecting the distribution of mangrove forests, combined with the planning objectives and carbon density parameters of different regions; assessed the habitat suitability areas of China's mangrove forests; and predicted their future carbon stock potential. The results showed the following: (1) Elevation was the most important factor affecting the overall distribution of mangrove forests in China, and the optimal elevation of mangrove distribution was 0.52 m. (2) The most suitable areas of mangrove forests in China were mainly distributed in Hainan, Guangxi, and Guangdong, which had great potential for carbon stock. Danzhou Bay and Hongpai Harbor in Hainan, Lianzhou Bay in Guangxi, and the Huangmao Sea in Guangdong are potential areas for habitat suitability but are not yet under high levels of protection. (3) Achieving the goals of this action plan was expected to increase carbon stocks by 4.13 Tg C. Other suitable areas not included in this plan could still increase carbon stocks by 7.99 Tg C in the long term. The study could provide a scientific basis for siting mangrove restoration areas and developing efficient management policies. [ABSTRACT FROM AUTHOR]

Mangrove wetlands are hotspots of global biodiversity and blue carbon reserves in coastal wetlands, with unique ecological functions and significant socioeconomic value. Annual fine-scale monitoring of mangroves is crucial for evaluating national conservation programs and implementing sustainable mangrove management strategies. However, annual fine-scale mapping of mangroves over large areas using remote sensing remains a challenge due to spectral similarities with coastal vegetation, tidal periodic fluctuations, and the need for consistent and dependable samples across different years. In previous research, there has been a lack of strategies that simultaneously consider spatial, temporal, and methodological aspects of mangrove extraction. Therefore, based on an approach that considers mangrove habitat, tides, and a semantic segmentation approach, we propose a method for fine-scale mangrove mapping suitable for long time-series data. This is an optimized hybrid model that integrates spatial, temporal, and methodological considerations. The model uses five sensors (GF-1, GF-2, GF-6, ZY-301, ZY-302) to combine deep learning U-Net models with mangrove habitat information and algorithms during low-tide periods. This method produces a mangrove map with a spatial resolution of 2 m. We applied this algorithm to three typical mangrove regions in the Beibu Gulf of Guangxi Province. The results showed the following: (1) The model scored above 0.9 in terms of its F1-score in all three study areas at the time of training, with an average accuracy of 92.54% for mangrove extraction. (2) The average overall accuracy (OA) for the extraction of mangrove distribution in three typical areas in the Beibu Gulf was 93.29%. When comparing the validation of different regions and years, the overall OA accuracy exceeded 89.84% and the Kappa coefficient exceeded 0.74. (3) The model results are reliable for extracting sparse and slow-growing young mangroves and narrow mangrove belts along roadsides. In some areas where tidal flooding occurs, the existing dataset underestimates mangrove extraction to a certain extent. The fine-scale mangrove extraction method provides a foundation for the implementation of fine-scale management of mangrove ecosystems, support for species diversity conservation, blue carbon recovery, and sustainable development goals related to coastal development. [ABSTRACT FROM AUTHOR]

This paper proposes a spatial data attribute similarity measure method based on granular computing closeness. This method uses the distance and membership degree of different index levels of spatial entities to measure the similarity of attributes. It not only reflects the degree of similarity of spatial entity types at different index levels but also reflects the integration similarity between spatial entity types under a comprehensive index. This method embodies the layered idea of granular computing and can provide a basis for spatial problem decision making and for spatial entity classification. Finally, the feasibility and applicability of the method are verified by taking the similarity measure of the land-use type attribute in Guangxi as an example. [ABSTRACT FROM AUTHOR]

• 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]

• Improved ecological footprint model for assessing ECC. • Constructed an ecological safety pattern based on the "history-present-future" concept. • Constructed an integrated ecological security network of points, lines and surfaces. • Proposed an ecological security optimization scheme of "two belts, three screens, four zones and multiple centres". The construction of ecological security pattern and ecological security network and reasonable ecological security planning are of great significance for ecosystem protection and restoration and optimal regulation. This study takes the Southwest Guangxi Karst - Beibu Gulf as the study area. Based on the improved ecological footprint model and the Patch-generating Land Use Simulation (PLUS) model, the ecological carrying capacity changes and driving mechanisms from 1990 to 2040 were analysed. The study proposed the idea of "history-present-future" to construct an ecological security pattern, We have constructed an integrated "points, lines and surfaces" ecological security network and carried out ecological security optimization planning. The results show that (1) The overall 1990–2040 belongs to the medium-high carrying capacity grade, showing a trend of rising and then falling, and the spatial changes are dominated by the type of unchanging ecological carrying capacity. Nanning is the most severely damaged. Slope and temperature are the main driving factors. (2) A total of 17 ecological source patches were identified in this study. The ecological source patches account for the overall area in general, and their distribution is relatively concentrated, so the ecological security of the central city needs to be focused on. (3) This study extracts 17 ecological corridors and 11 karst ecological corridors, generating an integrated ecological security network structure of "points, lines and surfaces". The ecological optimization planning proposal of "two belts, three screens, four zones and multiple centers" is proposed. [ABSTRACT FROM AUTHOR]

• Spatiotemporal evolution and destruction degree of wetlands from 1990 to 2018. • Comparison and Selection of Four Intelligent Algorithms for Land Cover Classification. • CA-Markov, support vector machine algorithm, wetland evolution prediction in 2018–2035. Wetlands are an important transitional ecosystem, and they play an important role in maintaining ecological balance. However, human activities and climate change have led to a decrease in wetlands. Therefore, to explore the degree of damage and assess the future trends of Guangxi wetlands, this study used the Google Earth Engine (GEE) cloud platform, and the support vector machine algorithm was selected for comparison and analysis to simulate the accuracy of land cover. GIS was used to analyse the evolution and degree of damage of nearly 30 Guangxi wetlands. The geographic detector model was used to explore the driving mechanism, and finally, the CA-Markov model and multi-scenario simulation were used to predict the wetland evolution from 2018 to 2035 to reveal the future direction of development. The results showed that (1) From 1990 to 2018, paddy fields accounted for the largest proportion of wetlands in Guangxi. In the past 30 years, the total area of wetlands in Guangxi has been degraded, with a total decrease of 983.33 km2. (2) The degree of wetland damage results showed that the total damaged area was greater than the total restored area, The wetland damage in Nanning city was the most serious, with an area difference of 503.22 km2 between the damaged and restored areas. (3) The analysis of the driving mechanism of wetland damage showed that distance from cities and towns, average precipitation and population density were the main driving factors. (4) The spatial distribution of natural development and economic construction in 2035 will be slightly damaged; additionally, the spatial distribution of ecological protection will expand as a whole. From 2025 to 2035, wetlands will be basically stable under Natural Development Scenario (NDS), degraded each year under the Economic Construction Scenario (ECS), and steadily increased each year under Ecological Protection Scenario (EPS). [ABSTRACT FROM AUTHOR]