Soil organic carbon (SOC) in mangrove ecosystems represents a vital blue carbon resource; however, accurate characterization of its spatial heterogeneity remains challenging. Traditional approaches treat mangroves as homogeneous entities, which overlooks variations in carbon sequestration capacity among species and severely limits precise assessments of carbon sink functionality. To address this issue, this study pioneers the integration of multiple intelligent optimization algorithms with an ensemble learning regression model (PSO-ELR), fusing hyperspectral data simulated by the PROSPECT-PRO and 4-SCALE models with multisource satellite data (Gao Fen (GF), Sentinel-2 (S2), and Sentinel-1 (S1)), providing an indirect physical link between canopy remote sensing data and subsurface SOC, thereby enabling high-precision estimates of SOC content for seven typical mangrove species in China. The study revealed that different mangrove species exhibit unique spectral responses at the leaf scale, with the red edge, near-infrared, and shortwave infrared bands being the most sensitive for estimating SOC. Additionally, compared with genetic algorithm optimization (GAO) and the grid search method (GSM), the particle swarm optimization (PSO) algorithm significantly outperforms the other algorithms. The PSO-ELR model exhibits the highest SOC estimation accuracy (R2 = 0.873–0.925) across the various datasets and demonstrated robust generalizability. Finally, the results of this study confirmed that mangrove species identity is the primary driver of spatial variation in SOC, with Bruguiera gymnorrhiza (BG) and Aegiceras corniculatum (AC) being the mangrove species with the highest carbon density (301.46 and 300.29 Mg/ha, respectively). This study recommends prioritizing the conservation and planting of existing high-carbon-density species (BG and AC) and optimizing the maintenance of widespread pioneer species such as Avicennia marina (AM) and Kandelia candel (KC) to achieve precise protection of mangrove ecosystems and maximize carbon sink benefits in restoration practices.

The highly fragmented and complex typology of urban wetlands poses substantial challenges for achieving high spatial resolution and detailed mapping using remote sensing. This study employs Sentinel-1/2 imagery and the Google Earth Engine (GEE) platform to develop an object-based hierarchical wetland classification (OHWC) framework supported by high-quality training samples, producing 10-m wetland distribution maps for five periods from 2016 to 2024 in Changshu (China), Changnyeong (Republic of Korea), and Saint Omer (France). Spatiotemporal patterns of wetland dynamics were analyzed. The results show that (1) average overall accuracies for Changshu, Changnyeong, and Saint Omer reached 94.84%, 90.9%, and 90.7%, respectively, outperforming existing wetland datasets; (2) wetlands in Changshu first expanded then declined, with a net loss of 20.42 km & sup2;, whereas those in Changnyeong grew continuously, with a net gain of 9.58 km & sup2;, and those in Saint Omer showed a fluctuating upward trend, with a net increase of 1.04 km & sup2;; and (3) changes in inland wetlands were the main drivers of wetland pattern evolution across the three cities. The proposed framework demonstrates strong generalizability and provides a valuable reference for detailed urban wetland mapping, as well as scientific support for wetland restoration and implementation of the Sustainable Development Goals (SDGs).

Urban land use serves as the fundamental foundation for human survival and development, providing essential natural resources. Simulation is an important tool for assessing the impacts of urban planning and construction new urban. To support policy implementation for the development of the Xiongan New Area and promote sustainable urban management, we use the "Data-Information-Knowledge-Wisdom" (DIKW model) as a framework for predicting future land spatial changes considering sustainable development of urban planning. We developed a novel New Urban Multi-objective Land Use Prediction (NUMLUP) method, integrating a Genetic Algorithm (GA), Multi-Objective Planning (MOP), and the Conversion of Land Use and its Effects at Small Region Extent (CLUES) model. Using this approach, we obtained urban land spatial distribution data for three scenarios. Urban land spatial distribution data for the Historical Continuation Scenario (HCS), Policy Planning Scenario (PPS), and Planned Sustainable development scenario (PSDS) were obtained. To evaluate Sustainable Development Goal (SDG) 11.3.1 and Regional Planning Goals (RPGs), we assessed 19 consecutive years of construction effectiveness-covering both past (2017-2023) and future (2023-2035) periods under the three scenarios. The dataset achieved a multi-year overall accuracy (OA) exceeding 0.87 and a kappa index above 0.83, demonstrating strong integration of the NUMLUP model. The area of built up gradually increased, and the wetland was mainly dominated by Baiyangdian, which declined significantly from 2017 to 2023. In the three scenarios, from 2023 to 2035, the expansion of the built-up slows down, and the degree of change in the HCS area is minimal. Under the PPS, forest and wetland areas underwent the most drastic changes, with overall improvement rates ranked as PPS > PSDS > HCS. In contrast, the PSDS led to a significant increase in grassland. Under PSDS, grassland increased significantly. The construction of the three scenarios from 2017 to 2035 has achieved certain results. While PPS and PSDS closely aligned with planning targets, the HCS would fail to meet the 2035 requirements. The PSDS also prompted adjustments in the regional policy's spatial layout. There were adjustments to the spatial layout of the policy as a result of PSDS. The LCRPGR is consistently greater than 1 from 2023 to 2035, reflecting a rational and comfortable urban plan that provides land use to meet population growth and demand.Furthermore, the PSDS introduced reasonable modifications to the regional plan's spatial configuration. Our research provides robust support for monitoring sustainable urban development and implementing regional policies.

Mangrove ecosystems are extremely sensitive to compounded stress, as evidenced by the widespread degradation and mortality of the pioneer mangrove species Avicennia marina along the Guangxi coast in recent years. However, research on how mangrove ecosystems respond to compound biotic stressors remains limited. Therefore, the present study aimed to systematically examine the ecological response mechanisms of A. marina under dual threats from the burrowing isopod Sphaeroma terebrans and the defoliating moth Hyblaea puera. Two contrasting sites were selected: Guchengling (subject to chronic stem-boring and sudden defoliator outbreaks) and Tieshangang (free from compounded stress). Photosynthetic capacity, metabolic function, and root structural integrity were all compromised considerably by chronic boring stress. During insect outbreaks, 15.33 ha of mangroves were destroyed due to impairments that breached the ecological threshold. In contrast, the healthier Tieshangang community exhibited strong ecological resilience, with rapid green canopy regeneration following defoliation and notable recovery in the normalized difference vegetation index. To enable early identification and precise intervention in mangrove decline, a comprehensive health index model was developed that includes root-canopy coordination, root length, and boring density. Field validation results, showing 100% agreement with expert evaluations across 19 validation sites (Cohen's kappa = 1.0), confirmed the high accuracy of the model. This study highlights the importance of identifying sensitive zones and undertaking timely ecological restoration, thereby providing a scientific basis and a practical tool that could facilitate early warning and timely management of mangrove degradation events.

The implementation of International Wetland City certification and associated conservation measures coincided with changes in the potential distribution of waterbirds in China's coastal wetlands. However, it remains unclear how the certification affects the overall distribution patterns of multi-species waterbird habitats and the specific mechanisms by which different species respond to environmental factors. Moreover, identifying key habitats for these guilds is essential for targeted species conservation and habitat restoration. Therefore, based on the DataInformation-Knowledge-Wisdom (DIKW) framework, this study classified 166 waterbird species into four ecological guilds: shorebirds, wading birds, open-water birds, and waterfowl. Using a coupled MaxEnt and hotspot analysis approach, we evaluated habitat suitability for these four waterbird guilds before and after the designation of Panjin, Dongying, and Yancheng as International Wetland Cities (2018-2024) and identified their distribution hotspots.The results indicated that: (1) After 10 iterations of training, the MaxEnt models for all four waterbird guilds achieved a mean AUC above 0.8 and a mean TSS above 0.60, demonstrating good predictive accuracy in simulating waterbird habitats. From 2018 to 2024, the total area of suitable waterbird habitat increased significantly in Panjin, Dongying, and Yancheng, with net expansions of 346.26 km2, 602.48 km2, and 40.51 km2, respectively; (2) Pronounced regional heterogeneity was evident in waterbird distribution patterns across the wetland cities. In Panjin, waterbirds showed a stronger preference for natural habitats such as herbaceous marshes and tidal flats, whereas in Dongying and Yancheng, they demonstrated greater adaptability, with a marked increase in occurrence probability in human-modified landscapes such as cropland; (3) Suitable waterbird habitats in all three wetland cities demonstrated a spatial pattern of "overall improvement despite localized contraction." Although some coastal areas experienced partial habitat loss, these habitats continued to expand inland, with shorebirds facing the more significant pressure from habitat contraction, particularly in coastal zones; (4) Land use/land cover (LULC) and distance to farmland (DFC) were the dominant factors influencing waterbird distribution in Panjin. In Dongying, distribution was significantly affected by LULC, distance to roads (DFR), NDVI, mean diurnal range (BIO2), and precipitation seasonality (BIO15). In Yancheng, habitat selection was primarily influenced by climatic factors such as BIO2 and isothermality (BIO3), as well as DFC and distance to constructed surfaces (DFS); (5) Hotspots of suitable waterbird habitat continued to expand, forming a trend centered on nature reserves and gradually extending outward.This study reveals the spatiotemporal evolution patterns and driving mechanisms of habitat suitability for multiple waterbird guilds under the context of International Wetland City designation, identifies key habitat hotspots, and provides specific recommendations for the conservation and management of waterbird habitats in internationally recognized wetland cities.

Abstract Evapotranspiration (ET) is a critical factor in determining the water cycle and energy exchange between soil, vegetation, and atmosphere. Under the dual influences of climate change and human activities, ET in the Dongting Lake basin is undergoing gradual changes. This study quantitatively analyzed the spatiotemporal variation of ET in the basin and its drivers at annual and seasonal time scales with a 20-yr dataset (2001–20) and statistical methods, including the linear regression method, correlation analysis, and ridge regression analysis. Results show that 1) ET in the Dongting Lake basin exhibited pronounced spatiotemporal variability. Annually, it increased at different rates in the area with significant ET change (1.37 mm yr −1 ) and the entire basin (0.24 mm yr −1 ). Seasonally, it decreased in summer but increased in winter. The western mountainous regions and the northeastern areas surrounding Dongting Lake present distinct differences in variation magnitudes. 2) Sunshine duration (SSD) consistently demonstrated the greatest relative contribution to annual ET changes, and fractional vegetation cover (FVC) ranked second. SSD and PRE cocontrolled summer ET, while FVC and PRE dominated winter ET. FVC influences ET via transpiration, canopy interception, and surface resistance. In the Dongting Lake basin, dense vegetation promotes transpiration and modulates the local microclimate, thereby constituting the key controlling factor. 3) Water-related factors PRE and soil moisture (SM) exhibited weak instantaneous correlations but imposed notable lagged effects on ET. PRE presented a 2-month lag, whereas SM presented a 1-month lag. These results enhance understanding of ET dynamics in humid subtropical monsoon basins and support regional water resources and ecological management. Significance Statement The Dongting Lake basin is a vital component of the Yangtze River basin, playing a crucial role in flood regulation, water-sediment balance, and regional climate regulation. Under the combined impacts of climate change and human activities, the basin’s evapotranspiration (ET) dynamics have undergone significant changes, which directly affect regional water security, agricultural production, and ecological stability. However, most existing studies on the drivers of ET in the Dongting Lake basin focus primarily on climatic factors, with limited consideration of land surface characteristics. Additionally, most analyses are conducted at the annual scale, neglecting seasonal variations, and few studies have examined the lagged effects of water-related variables [PRE and soil moisture (SM)] on ET. This study fills these gaps by systematically analyzing ET spatiotemporal variations and quantifying the relative contributions of both climatic and land surface factors at annual and seasonal time scales, including the lagged effects of PRE and SM. The findings not only advance the mechanistic understanding of ET driving mechanisms in humid subtropical monsoon basins but also provide actionable scientific support for regional water resource management, drought–flood disaster mitigation, and ecological restoration. Given the global significance of subtropical monsoon regions in the global water cycle, this study also offers a reference for similar basin-scale ET research worldwide.

The long-term utilization of mangroves has led to the degradation of their ecosystems. China has initiated a number of action plans for mangrove restoration and protection at different levels over the years to rehabilitate mangrove ecosystems. However, existing restoration plans have failed to distinguish suitable restoration areas for different mangrove species at the national level. Furthermore, they have failed to establish restoration priorities across different regions. This is because traditional species distribution models struggle to handle multi-species prioritisation and lack spatial assessments of restoration resistance. This study selected multiple factors influencing mangrove growth and coupled the genetic algorithm (GA)-maximum entropy (MaxEnt) model and eXtreme Gradient Boosting (XGBoost) algorithm. For the first time, national-scale restoration priority rules were established for 15 mangrove species. Finally, a map of mangrove restoration priorities was produced. Results indicate that mangrove restoration areas still hold significant potential, with an average area 1.4 times larger than existing mangroves across multiple datasets. Most regions in China fall under moderate resistance levels, with 25% of areas showing restoration potential. Polder farming and growth bases are the main resistance to redwood restoration. 60% of the priority areas in China are distributed in Guangxi and Hainan. Kandelia obovata and Acrostichum aureum should be prioritized for planting. Overall, it is necessary to select the appropriate types of mangroves and the appropriate restoration areas. China still needs an area 1.1 times larger than the current distribution of mangroves. Our study reveals a roadmap for constructing sustainable mangrove restoration, which provides a critical foundation for mitigating climate change and realizing conservation action plans for mangrove restoration.

Sustainable land-use systems require balancing water security, wetland conservation and food production under increasing pressures from agricultural intensification, urban expansion and climate change. This study develops an integrated water-wetland-food framework to assess ecosystem service trade-offs, synergies and governance pathways in China from 2000 to 2020. Water yield, flood regulation, leisure and recreation, and grain yield are quantified using multi-source spatial data and ecosystem service models. Trade-offs and synergies are examined across provincial, city, county and pixel scales, and interpretable machine learning and structural equation modelling to identify the key predictors, nonlinear responses, and structural pathways of individual ecosystem services. Results show that China's water-wetland-food system was spatially heterogeneous but temporally stable. Low-synergy areas covered nearly 80% of the country, while strong trade-off zones accounted for 30-50% across scales. Persistent conflicts were concentrated in major grain-producing regions, especially between wetland regulation or recreation services and agricultural production, whereas wetland-rich Yangtze River and coastal regions showed stronger multifunctional synergies. Scale aggregation amplified apparent synergies but concealed local conflict hotspots, indicating that coarse administrative assessments may underestimate ecological risks in intensive land-use regions. Climate conditions mainly controlled water and wetland services, while land-use intensity and vegetation conditions shaped grain production. Four functional governance zones were identified to support differentiated strategies, including water-resource constraints, wetland protection, high-standard farmland management, nature-based solutions and ecological compensation. This framework provides spatially explicit evidence for improving resource efficiency, ecological conservation and food security in sustainable land-use systems.

Ramsar Wetland Cities (RWCs) is a global paradigm for harmonizing urban development with wetland conservation, hosting wetland ecosystems of important representative value. However, the failure of existing wetland products to comprehensively encompass the Ramsar classification system hinders rigorous accreditation and renewal evaluation. To fill this gap, this study developed the Object-Knowledge-based Hierarchical Optimization Cascade method, utilizing Sentinel-1/2 time series imagery aligned with the 5 accreditation and renewal key nodes of RWCs (2016, 2018, 2020, 2022, and 2024). The Object-Knowledge-based Hierarchical Optimization Cascade method employs a hierarchical extraction strategy: First, an optimized Random Forest model separates wetlands from nonwetlands based on spectral separability; subsequently, fine wetland types are delineated by integrating geometric features and seasonal inundation variations. For complex wetland classes during the subdivision process, cascaded spectral clustering and XGBoost algorithm are applied to enable nonlinear decision making for enhanced precision. Furthermore, a geometric similarity inheritance was introduced to ensure reliable temporal migration for complex wetland types. Consequently, we produced the first Global Wetland City Fine Classification System 10-m product, distinguishing 18 Ramsar wetland classes and 6 nonwetland classes. Results indicate that Global Wetland City Fine Classification System 10-m product achieves an overall classification accuracy of 94.98%. The dataset reveals a net increase of approximately 145,781.41 ha in wetland area across 43 RWCs globally from 2016 to 2024, with a total area reaching 3,063,592.66 ha by 2024, corroborating the positive protective efficacy of RWC accreditation. This dataset is publicly available, serving as a robust resource for RWC monitoring, ecological evaluating, international strategic indicator assessment, and sustainable management.

The intensifying pressures of urbanization and climate change on coastal zones necessitate a holistic understanding of the interplay between human activity and ecological integrity for sustainable development. However, prevailing methods for assessing coastal vibrancy often overlook direct measures of human presence and fail to quantitatively capture its complex relationship with ecological vulnerability. To address these gaps, this study develops a novel multi-dimensional assessment framework for Coastal Landscape Vibrancy (CLV) and empirically examines its interaction with ecological vulnerability factors in Beihai, China. Moving beyond built-environment-centric approaches, our framework integrates the 'Crowd' dimension, directly quantified using Baidu Heat Index data, with the 'Place' dimension, characterized by urban features, natural attributes, and visual experience. Principal Component Analysis (PCA) was employed to objectively weight these indicators and construct a composite CLV index. We then applied multiple linear regression to analyze the influence of ecological factors constructed based on the Sensitivity-Resilience-Pressure (SRP) model. The results revealed that vibrancy was highly concentrated in urban cores and exhibited significant spatiotemporal variations. Regression analysis revealed that while ecological quality factors like green coverage (beta = 0.236, p < 0.001) positively influenced vibrancy, anthropogenic stressors such as slope (beta = -0.457, p < 0.001) and the impervious surface index (beta = -0.092, p < 0.001) had significant negative impacts, highlighting a critical trade-off between human activity and ecological conditions. The findings provide a quantitative, evidence-based foundation for spatial planning, demonstrating that sustainable coastal vibrancy is achieved through a balanced integration of human activity and ecological conservation, rather than through unchecked development. This framework offers critical insights for formulating strategies that simultaneously enhance ecological resilience and optimize human service facilities.

Leaf mass per area (LMA) plays an important role in vegetation productivity, carbon cycling, and remote sensing-based ecosystem monitoring. However, remotely predicting LMA from hyperspectral reflectance remains challenging due to the weak and strongly overlapping spectral response of LMA and spectral variability across species. To address these limitations, this study proposed an integrated framework that combines a fractional-order spectral derivative (FOD) with a one-dimensional convolutional neural network (1D-CNN) to enhance LMA prediction accuracy and cross-species generalization. Leaf hyperspectral reflectance was processed using FOD with 0–2 orders, and the relationship between FOD-enhanced spectra and LMA was analyzed. Model performance was assessed using (i) overall prediction accuracy by an 8:2 random split between training and test sets, and (ii) cross-species generalization through leave-one-species-out validation. The results demonstrated that the 1D-CNN using a 1.5-order derivative achieved the best performance (R2 = 0.85; RMSE = 11.57 g/m2), outperforming common machine-learning models including partial least squares regression (PLSR), random forest (RF), and support vector regression (SVR). The proposed method also demonstrated great generalization in cross-species prediction. These results indicate that integrating FOD with 1D-CNN effectively enhances LMA-related spectral information and improves LMA prediction across various species. It provides a promising pathway for applying airborne and satellite hyperspectral images in vegetation biochemical parameter mapping, crop monitoring, and ecological assessment.

Global wetlands are experiencing severe degradation due to climate change and human activities. Under the Ramsar Convention, the Wetland City Accreditation promotes cities to protect and sustainably manage their urban wetlands. The accreditation system was launched in 2015. To date, 43 cities worldwide have obtained this certification, whose dynamic assessment depends on precise mapping of land use and wetlands. Existing global land cover datasets often show low accuracy in identifying wetlands and limited capacity to characterize wetland types within urban areas. we developed a hybrid Wetland City Map (WCM), by fusing three global 10 m-resolution products: Dynamic World, ESA WorldCover, and ESRI Land Cover. We applied a Weighted Voting and Knowledge-based Decision Rule method to achieve this fusion. This method overcomes the limitations of the input datasets by combining their complementary strengths to improve overall wetland classification and by applying expert-derived rules to enhance the delineation of wetland types within cities. The WCM achieves an average overall accuracy of 86.93 % and a kappa of 0.825. In all cities, its accuracy surpasses the three land cover products by 2 %-26 %. The visual comparison shows WCM performs better in wetland classification and spatial detail, with F1 scores of 90.33 % (water), 64.09 % (marsh), 71.67 % (tidal flat/flooded flat), and 92.17 % (mangrove). It more accurately reflects wetland coverage and changes. Wetland coverage varies across cities, with higher coverage in Asia and lower in Europe and Africa. Individual cities experienced a maximum increase of 6.5 % and decrease of 1.3 % from 2020 to 2021.The WCM supports wetland monitoring, city accreditation, and research aligned with the Ramsar Strategic Plan and Sustainable Development Goals.

Mangroves are crucial ecosystems with significant ecological and economic roles, providing habitat for diverse species, storm protection, and carbon sequestration. While many mangroves worldwide have faced substantial losses, China has seen notable recovery. Understanding the expansion patterns of mangroves necessitates high-resolution, large-scale monitoring of their coverage over time. In this study, we divided coastal zones based on geomorphic and sedimentary environments and generated annual mangrove coverage from 2016 to 2022 using multi-source high-resolution data and a U-Net model. By analyzing morphological changes of mangrove patches in different coastal zones of the Guangxi Beibu Gulf, we summarized expansion patterns and calculated expansion and degradation rates from area changes. Our findings reveal a 1,413 ha increase in mangrove area from 2016 to 2022. Estuarine mangroves experienced an initial increase followed by a decrease, while gulf mangroves showed an initial decrease followed by an increase. Three distinct expansion patterns were identified: (1) regular mangroves expanding parallel to coastlines; (2) mangroves expanding in estuarine areas where freshwater and seawater meet; and (3) independent mangrove patches expanding into surrounding wetlands. In summary, stable and changing mangrove areas were in a ratio of 7:3, with expansion areas at 70.5% and degradation areas at 29.5%. The loss of mangroves in Guangxi Beibu Gulf is primarily due to intense human activities, with minimal contributions from sea level rise and marine dynamics.

Wetlands are characterized by high diversity and complexity and present formidable challenges for global-scale remote sensing mapping. A high-quality, robust global wetland sample dataset (GWSD) is essential for overcoming these challenges. However, yet the absence of a reliable methodology for generating long-term, consistent wetland samples has persisted as a critical gap. Herein, we propose a novel hybrid approach that combines automated generation - index thresholding - spectral matching (AG - IT - SM) to produce the first multicategory global wetland sample dataset from 1985 to 2020. Using the full Landsat 5/7/8 archive within the Google Earth Engine (GEE), we generated 349,952 training samples and 67,952 validation samples. Globally, wetland samples are distributed predominantly in the Northern Hemisphere, with a relatively sparse representation in the Southern Hemisphere. Independent expert validation through crosschecking confirmed that all wetland-type samples achieved an accuracy exceeding 90%. A comparative analysis with the GLC_FCS30D dataset demonstrated strong temporal consistency across all evaluated years. Classification experiments demonstrated that the refined wetland samples achieved accuracies exceeding 80%. The proposed method was validated as an effective approach for producing reliable wetland samples, resulting in the first global wetland reference dataset that may serve as a fundamental data resource for large-scale wetland mapping applications.

The "International Wetland City" certification proposed by the Ramsar Convention is a new initiative to promote wetland protection and restoration. Taking Changde City, an International Wetland City, as an example, based on the refined classification data of wetlands from 2000 to 2022, this study monitored the changes in wetland protection and restoration, quantitatively analyzed the importance and contribution rate of the driving factors for every single refined wetland types, and finally explored the spatial distribution pattern of the dominant driving factors. The results showed that: (1) During 2000-2022, the effectiveness of wetland protection and restoration in Changde City was significant, increasing from 1298.53 km(2) to 1399.61 km2. (2) Wetland stability was the main type of wetland change (61.86%), followed by wetland restoration (22.10%) and wetland damage (16.04%). (3) Attribution analysis found that wetland restoration was mainly attributed to the return of farmland to wetland, while wetland damage was mainly caused by climate dryness; mudflats, grassland, and reed wetlands, pits, and rivers were mainly affected by arable land while lakes by construction land; reservoirs and canals were affected by rainfall. (4) In terms of attribution zoning, agricultural activities drove 68.76% of wetland changes, urbanization and climate change contributed 22.03% and 9.21% respectively.

Although both the Millennium Development Goals (MDGs) and the Sustainable Development Goals (SDGs) proposed by the United Nations have established clear indicator systems to promote the sustainable improvement of ecological quality (EQ), few existing studies have systematically conducted comparative studies and correlation analyses on the characteristics of EQ changes between these two periods. Therefore, this study takes the Inner Mongolia Autonomous Region (IMAR) as an example and innovatively proposes a research framework of remote sensing information extraction-spatio-temporal evolution trajectory analysis-sustainability assessment-analysis of typical regional driving forces for EQ assessment. The results show that a spatial distribution of EQ in the IMAR features eastern dominance, western deficiency, and staggered in the center. Temporally, improvement was observed across 65.09% of the regional area. In terms of trajectory change, 32.56% of the area shows a positive trend in EQ, with a linear growth trajectory accounting for 58.48%. Ecological engineering and restoration policies in the SDGs stage have significantly improved EQ, successfully reversed the degradation trend in some areas in the MDGs stage, and are gradually working to meet the SDGs standards. Climatic factors play the pivotal role in determining the spatial configuration of EQ across the typical region. This study systematically analyzes the sustainability of EQ and the driving mechanism of spatial differentiation under the dual framework of MDGs and SDGs, offering critical decision-making support for IMAR's sustainable development.

Accurate mapping of leaf area index (LAI) is essential for mangrove conservation and restoration. This study proposes a new approach to the retrieval of the mangrove LAI by combining a one-dimensional convolutional neural network (1D-CNN) with adaptive ensemble learning regression (AELR) and deep learning regression (DNNR) algorithms. We further evaluated the performance of OHS (Zhuhai-1) hyperspectral and GF-3 SAR images in mapping the spatial distribution of the LAI in mangroves. Finally, the outputs of the AELR and DNNR models were interpreted, and the interactions between different image features were clarified to select the sensitive spectral ranges and vegetation indexes for estimating the mangrove LAI using SHAP (Shapley additive explanation). We confirmed that 1D-CNN + DNNR provided an effective approach to estimating the mangrove LAI, as it produced a higher-accuracy inversion (R2 = 0.8685) than that of the AELR model. It was found in this study that the 1D-CNN improved the retrieval accuracy (R2) of the mangrove LAI from 0.097 to 0.1297 when compared with the traditional data dimension reduction (DDR) method, which demonstrated that the 1D-CNN was able to improve the inversion accuracy of the mangrove LAI. This study revealed that the synergistic use of OHS hyperspectral and GF-3 SAR images (R2 = 0.8685, RMSE = 0.134) outperformed any of the lone datasets in the inversion of the mangrove LAI. Finally, this study provided explanations and interpretations of the outputs of the DNNR and AELR models, and it was found that the optimal spectral ranges for estimating the mangrove LAI are 637-671 nm and 802-822 nm; H19 ((NIR/Red)/Red), the NDVI, H14 (Red edge/Red), and the EMVI ((Green-SWIR2)/(SWIR1-Green)) provided important contributions for mapping the mangrove LAI. These results provide a scientific foundation for the preservation and restoration of coastal mangroves.

Mangroves have ecological functions and disaster prevention and mitigation functions. Simulation prediction is an important tool for mangrove restoration, protection work and future response to disaster risks. To address the existing gaps in spatial data regarding mangroves and their capacity for disaster risk reduction. In this study, multiple scenarios were set up to predict future spatial changes in mangroves. A spatial optimization simulation and prediction method for mangrove restoration and conservation has been established, integrating Coupled Artificial Neural Networks (ANN), Multi-Objective Planning (MOP), and Cellular Automata (CA) models. Future spatial simulations of mangroves from 2025 to 2035 were conducted under three scenarios: Trend Continuation Scenario (TCS), Policy Planning Scenario (PPS), and Human-Nature Harmonious Coexistence Scenario (H-NHCS). Based on this, an analysis of future changes under the three scenarios was carried out. Mangrove disaster prevention and mitigation functions were ultimately predicted for SDG13.1. The resulting dataset has a multiyear OA of more than 0.89, a kappa index of more than 0.86, and good integration with the ANN-MOP-CA model. Based on the analysis of mangrove remote sensing data set extracted by Sentinel from 2016 to 2024, the mangrove area increased by 34 %. From 2024 to 2035, most of the TCS area showed a seaward expansion trend. The stability of mangrove changes over the years was greater than 50 %, and the degradation rate of H-NHCS mangroves was less than 5 %. The future wave dissipation capacity and ability of mangroves to withstand storm surges have improved annually, and areas with a relatively weak ability to cope with disasters are dominated by open bays and built-up areas. This study provides strong support for the tracking and monitoring of the entire process of regional mangrove restoration and protection.