Tidal wetlands, located at the dynamic land-sea interface, provide vital ecosystem services, yet face increasing threats from human activities and climate change. Accurate and up-to-date global mapping of tidal wetlands is essential for assessing their status and advancing conservation efforts. However, challenges such as tidal fluctuations and limited data availability lead to inconsistencies across existing datasets. Moreover, previous studies have largely overlooked the adjacent terrestrial environments of tidal wetlands, reducing our understanding of coastal dynamics and associated environmental drivers. To address these critical issues, this study proposes a novel global coastal mapping framework with three key components. First, using the ocean tide model EOT20, we systematically analyzed tidal variations observed in Sentinel-1 and Sentinel-2 imagery between 2019 and 2021, facilitating the development of an adaptive image selection strategy to ensure low-tide coverage. Second, we integrated multi-source global datasets and employed a knowledge-driven, semi-automatic sampling approach to generate training samples for tidal wetlands and adjacent land covers. Third, we iteratively trained and refined random forest models using tide-level and phenological features extracted from composite optical and radar imagery, producing a global coastal dataset centered on 2020 with 11 distinct land cover types. The mapping result was cross-compared with multiple global and regional coastal datasets and validated using the temporally cleaned external dataset, achieving an overall accuracy of 92.7%. By optimizing the selection of Sentinel scenes to approximately 10-50 in time-series composite mapping, this approach balances computational efficiency with intertidal classification accuracy. The dataset delineates the global distribution of tidal wetlands and their adjacent environments at a 10-m resolution; specifically, tidal wetlands-including mangroves, tidal marshes, and tidal flats, amount to 425,509 +/- 932 km2. This fine-resolution and multi-category mapping framework enables a more precise identification of potential trade-offs between conservation and development, providing valuable references for sustainable coastal management.

High spatial resolution land cover products play a crucial role in urban planning and renewal by providing detailed spatial information for decision-making. However, generating these products through fully supervised classification approaches requires extensive pixel-level annotations, which are time-consuming and costly.Weakly supervised methods offer a practical alternative by using low spatial resolution land cover products as coarse labels.Nevertheless, the mismatch in resolution introduces significant label noise and blurred boundaries, limiting classification accuracy. To address these challenges, this study proposes a Dual-Branch Cross-Resolution Network (DB-CRNet) that uses only low spatial resolution labels and high spatial resolution images for land cover classification. DB-CRNet adopts a non-downsampling dual-branch framework, consisting of a Convolutional Neural Network (CNN) branch, a Wavelet Visual State Space Model (WVSSM) branch, and a Label-Filtering Dual-Branch Hybrid Loss (LFDB-Loss) module. This design enables effective cross-resolution learning while preserving fine spatial details. Experimental results show that DB-CRNet outperforms existing benchmark models (e.g., Paraformer, L2HNet), achieving an mIoU value of 72.46% on the public Chesapeake dataset and 63.48% on the self-built Guilin dataset. The results demonstrate that the proposed network exhibits strong generalization across different data sources and spatial resolutions. Overall, this study provides an efficient and economic method for high spatial resolution land cover mapping using low spatial resolution coarse labels, significantly reducing the labeling cost and ensuring the precision of classification results.

Blue-green spaces serve as the core carriers of urban ecosystems, and their conservation and optimization have emerged as pivotal issues in territorial spatial planning and ecological governance. Taking Guilin, a national innovation demonstration zone for China's Sustainable Development Agenda, as the study area, a deep learning-based DBDTAF-Net classification model is constructed using 2020 Sentinel-2 remote sensing imagery and AW3D30 Digital Surface Model (DSM) data. The model achieves a mean Intersection-over-Union (mIoU) of 86.05% on the test set and an IoU of 94.67% for rocky desertification areas. Based on the classification results, 21 derived indicators (including landscape patterns of BGSs) and six meteorological and topographic factors, alongside three core ecosystem service indicators-Aboveground Biomass (AGB), Net Primary Productivity (NPP), and soil conservation-are extracted to characterize their spatial patterns. The XGBoost-SHAP framework is employed to quantify the driving effects and threshold responses of BGS patterns on ecosystem services. The results indicate that (1) BGSs in Guilin display a spatial pattern of "green-dominated, blue-supplemented, generally contiguous yet locally fragmented," and all three ecosystem services exhibit significant spatial clustering. (2) Landscape pattern factors of green spaces constitute the dominant influencing factors, with contribution rates ranging from 22.3% to 28.6%. Specifically, green space_COHESION demonstrates a stable linear positive effect. A green space ratio below 45% suppresses AGB, whereas exceeding 45% shifts to a positive effect and represents an efficient enhancement interval for NPP while exerting a continuously positive influence on soil conservation. A cultivated land proportion below 30% leads to a strongly increasing inhibitory effect on AGB and soil conservation, whereas its inhibition on NPP weakens beyond 20%. A construction land proportion exceeding 10% significantly suppresses NPP, and the inhibitory effect stabilizes above 20%. Green space patch density below 0.8 shows a pronounced negative effect, which diminishes above 0.8. Blue space factors exert relatively weak effects. (3) The ecosystem service supply capacity varies across functional zones in Guilin, with the ecological barrier zone performing the best, the modern agricultural zone performing moderately, and the six central urban districts of the Shanshui Metropolis Area exhibiting the lowest levels. This study provides a technical framework for high-precision extraction of urban BGSs and quantitative analysis of factors influencing ecosystem services, offers decision support for ecological conservation and restoration in Guilin, and furthermore proposes insights for the coordinated development of rational land resource utilization and ecosystem service enhancement in other karst cities.

Gas flaring is a major source of greenhouse gas and a waste of nonrenewable resources. Remote sensing is suggested to be a capable proxy to provide independent, reliable, and regular observations on global gas flaring. Multiple satellite sensors, especially nighttime imagers, have been used to detect and characterize gas flares. However, the hundred-meter level coarse resolution of current nighttime sensors impacts the accuracy of detection and estimation with small fires undetected. In this study, we explore the potential of high resolution multispectral SDGSAT-1 glimmer imager for urbanization (GIU) data and we propose a fine-grained gas flaring detection and estimation method based on the visible optical structure zones of gas flares. The study area of this work locates mainly in eight Persian Gulf countries. Existences, locations, volumes, and extents of gas flares within the study area are captured and analyzed. The proposed method achieves a detection accuracy of 90.46% with 891 active fire sites correctly recognized. Comparisons with daytime approach for gas flaring investigation V2 data show that our method generates less miss-detection especially when detecting small-sized gas flares, which demonstrates the utility of high resolution nighttime imagery and the proposed optical-based method.

Image stitching is a critical preprocessing step in unmanned aerial vehicle (UAV)-based remote sensing, however, it remains challenging for conventional methods due to large parallax, high resolution, and scene complexity, which often lead to visible seams or high computational overhead. To address these challenges, an unsupervised, mask-based image stitching approach is proposed in this study. The proposed approach reframes UAV image stitching as a 2D dense prediction and assigns the optimal pixel from source images to every pixel in the overlap. The proposed approach comprises two key components, i.e., Siamese-Residual Mask Network (SRMN) and Accelerated Inference via Scale Decoupling (AISD). The SRMN component leverages a Siamese architecture to extract multi-level features and compute residual discrepancies, guided by loss constraints of spatial consistency, smoothness, and quality-aware to generate seamless binary masks. By exploiting the strong entropy stability of binary masks across scales, the AISD component predicts masks at a low resolution. This allows for the accurate restoration of full-resolution masks for blending without requiring network retraining or structural changes. By decoupling mask prediction from high resolution processing, the proposed approach avoids expensive nonlinear operations while preserving fine details. Experiments on four UAV image datasets show that the proposed approach outperforms state-of-the-art methods. The proposed approach improves PSNR by up to 28.58% and SSIM by up to 56.00%, while reducing processing time by up to 88.9% compared to state-of-the-art methods. These results validate the proposed approach as a robust solution for large-scale UAV image stitching, successfully balancing computational efficiency with visual fidelity.

The interpretation of remote sensing images is pivotal in extracting geological elements of interest. Recent studies using deep learning models often fail to provide accurate boundaries between geological elements due to high interclass similarity and imbalanced data distribution. Furthermore, these models are computationally intensive. Inspired by expert interpretation practices, which involve first delineating boundaries and then identifying semantics, we leverage the vision foundation model and propose a distributed interpretation framework including distributed training and inference phases based on data parallelism in distributed architectures. First, a conventional semantic segmentation model, DeepLabV3, is trained. Subsequently, we integrate the Segment Anything Model (SAM) with the trained model, completing the final mapping during the inference phase. Specifically, the inference model features two branches: one for extracting masks by SAM and another for categorizing geological elements. Then, a semantic voting module combines the information from both branches to determine the category for each mask. Experiments demonstrate that the method enhanced the performance metric by more than 2%. Moreover, the method achieves a 3.85x speedup in training and a 3.95x speedup in inference on a 4-GPU machine. We further exploit simulation experiments of 16 GPUs and achieve up to 15.1x training speedup.

Urban electricity power consumption (EPC) prediction plays a crucial role in urban management and sustainable development. Nighttime light (NTL) remote sensing imagery has demonstrated significant potential in estimating urban EPC due to its strong correlation with human activities and energy use. However, most existing models focus on annual-scale estimations, limiting their ability to capture month-scale EPC. To address this limitation, a novel monthly EPC prediction model that incorporates monthly average temperature, and the interaction between NTL data and temperature was proposed in this study. The proposed method was applied to cities within the Yangtze River Delta (YRD) urban agglomeration, and was validated using datasets constructed from NPP/VIIRS and SDGSAT-1 satellite imageries, respectively. For the NPP/VIIRS dataset, the proposed method achieved a Mean Absolute Relative Error (MARE) of 7.96% during the training phase (2017–2022) and of 10.38% during the prediction phase (2023), outperforming the comparative methods. Monthly EPC spatial distribution maps from VPP/VIIRS data were generated, which not only reflect the spatial patterns of EPC but also clearly illustrate the temporal evolution of EPC at the spatial level. Annual EPC estimates also showed superior accuracy compared to three comparative methods, achieving a MARE of 7.13%. For the SDGSAT-1 dataset, leave-one-out cross-validation confirmed the robustness of the model, and high-resolution (40 m) monthly EPC maps were generated, enabling the identification of power consumption zones and their spatial characteristics. The proposed method provides a timely and accurate means for capturing monthly EPC dynamics, effectively supporting the dynamic monitoring of urban EPC at the monthly scale in the YRD urban agglomeration.

High-resolution population data are crucial for various applications, from developing regional plans to disaster risk management. Current population spatialization methods typically apply population mapping relationships established at the regional level to the grid level using multi-source data. However, the significant scale difference between the regional and grid levels, combined with the simple integration of multi-source data features without considering the spatial dependence of the population, results in lower accuracy. To address the scale mismatch issue in the downscaling process, we first construct a spatially heterogeneous population label by combining census data with gridded population datasets. Then, we establish a relationship mapping between population covariates and population at a low-resolution scale (100 m) and apply it to a neighboring high-resolution scale (25 m) to reduce the prediction bias resulting from directly downscaling from the regional level to the grid level. Meanwhile, a deep learning model based on transformer feature attention convolution net (TFACNet) is employed to aggregate each geographic unit's global and local spatial relationships, integrating complementary features learned from multi-source heterogeneous data in an end-to-end manner. The experimental results in Wuhan and Guilin show that our method achieved a more accurate population spatialization (overall $R<^>2\approx$R2 approximate to 0.92) at the street level.

Analyzing the electric power consumption (EPC) patterns of China’s mega urban agglomerations is crucial for promoting sustainable development both domestically and globally. Utilizing 2017–2021 NPP/VIIRS low-light remote sensing imagery to extract total nighttime light data, this study proposed an EPC prediction method based on the K-Means clustering algorithm combined with multiple indicators integrated with socio-economic factors. Combining IPAT theory, regional GDP and population density, the final EPC prediction models were developed. Using these models, the EPC distributions for Beijing-Tianjin-Hebei (BTH), Yangtze River Delta (YRD), and Pearl River Delta (PRD) urban agglomerations in 2017–2021 were generated at both the administrative district level and the 1 km × 1 km grid scale. The spatio-temporal dynamics of the EPC distribution in these urban agglomerations during this period were then analyzed, followed by EPC predictions for 2022. The models showed a significant improvement in prediction accuracy, with the average MARE decreasing from 30.52% to 7.60%, 25.61% to 11.08% and 18.24% to 12.85% for the three urban agglomerations, respectively; EPC clusters were identified in these areas, mainly concentrated in Langfang and Chengde, Shanghai and Suzhou, and Dongguan; from 2017 to 2021, the EPC values of the three urban agglomerations show a growth trend and the distribution patterns were consistent with their economic development and population density; the R2 values and the statistical values for the 2022 EPC predictions using the improved classification EPC models reached 0.9692, 0.9903 and 0.9677, respectively, confirming that the proposed method can effectively predict the EPC of urban agglomerations and is applicable in various scenarios. This method provides a timely and accurate spatial update of EPC dynamics, offering fine-scale characterization of urban EPC patterns using night light images.

Nighttime light (NTL) imagery remotely sensed from outer space has been suggested to be a suitable proxy to investigate socioeconomic dynamics. Since the outbreak of COVID-19, many studies have used NTL imagery to estimate the impacts of the pandemic. However, finer-grained analytics are rarely achieved limited by the spatial resolution of major NTL data sources. In November, 2021, the Sustainable Development Science Satellite-1 (SDGSAT-1) was launched and one of its payloads, Glimmer Imager for Urbanization (GIU) can provide 10m/40 m panchromatic and multispectral NTL images for public use. In this study, we estimate the fine-grained NTL dynamics before and after the COVID-19 surge in the city of Shanghai during the second quarter of 2022 using SDGSAT-1 GIU nighttime imagery. To distinguish the different behaviors among urban functional entities, categorized Point of Interest (POI) data are adopted. The estimation is conducted in three progressive levels: city-level, POI-class-level, and POI-object-level. To characterize each urban objects from multiple angles, two additional NTL indices, NTL and luminous area ratio composite index (NTL-CI) and NTL background relative activeness index (NTL-AI) are introduced and estimated. On the basis of raw NTL, NTL-CI further considers the change of luminous area and NTL-AI further considers the relative change to the average standard. Moreover, detailed visual observations at typical POI objects are conducted, for instance, the Shanghai Disney Resort, the Shanghai Tesla Gigafactory, and multiple cabin hospitals temporarily converted from large stadiums and exhibition centers. This study aims to present a comprehensive investigation of the socioeconomic influence of COVID-19 in Shanghai from the perspective of NTL changes in multiple granularities, and the utility of SDGSAT-1 GIU nighttime imagery in supporting SDG 3 (The Sustainable Development Goals 3: Good Health and Well-Being) is also demonstrated with this set of quantitative analytics.

Accurate and reliable prediction of ship movements is critical for maritime safety and traffic management, yet it remains challenging due to the nonlinearity, stochasticity, and trendiness of ship motions. This paper proposes a deep cross LSTM network (LSTM-DCross) based on AIS time series data to overcome limitations in traditional approaches. The model integrates an encoder-decoder framework with an attention mechanism to predict ship behaviours, including position (longitude, latitude), course (COG), and speed (SOG). The study addresses two critical scenarios: GPS failure and complete AIS failure, utilizing two prediction methods - joint prediction and historical data-based prediction - to forecast the target ship behaviour. Experimental results show that LSTM-DCross outperforms BP, LSTM, LSTM-ATT, and TCN-GRU networks, achieving an MSE of 0.0754 and MAE of 0.1891. Notably, the historical data-based prediction method with LSTM-DCross not only demonstrates high accuracy but also offers greater applicability, successfully predicting future ship behaviours using only historical data, even during complete AIS failure. Additionally, by comparing AIS data with LSTM-DCross predictions, deviation values are calculated to detect abnormal ship behaviours. When deviations exceed a predefined threshold, the system records data and issues warnings, providing a potential tool for enhanced ship monitoring and risk mitigation.

With the rapid economic development in China, air quality issues have emerged as major challenges to the country's sustainable development. This study utilizes ground monitoring data from 1248 monitoring Stations across China, constructs a kilometer network dataset of six air pollutants-PM2.5, PM10, SO2, NO2, O3, and CO-across 19 officially designated city clusters from 2015 to 2023. Comparative analysis with remote sensing inversion data confirms that in regions with dense monitoring coverage, ground-based observations are more reliable. This study represents the first comprehensive analysis integrating multi-pollutant, long-term temporal, and multi-city cluster dimensions, breaking through the existing research paradigm typically limited to single regions, individual pollutants or short-term observations. Results show: Overall pollutant declines, with PM2.5 and SO2 decreasing >40 % in some regions, highlighting the preliminary effectiveness of air pollution control policies. However, O3 increases in many areas, echoing the "PM2.5 decline-O3 rebound" phenomenon seen globally. Furthermore, Temporary NO2 and CO reductions during the COVID-19 lockdowns, reflecting the short-term impact of reduced human activity. Furthermore, the study innovatively combines grey relational analysis and random forest modeling to reveal socioeconomic drivers: population agglomeration and urbanization are key factors affecting SO2 and NO2 concentrations, while ecological development shows significant reduction effects on particulate matter concentrations, and the environmental benefits of scientific and technological investment exhibit time-lag characteristics. The constructed pollutant concentration prediction models (R2 = 0.42-0.58) rely solely on publicly available statistical data, can provide rapid assessment tools for areas with weak monitoring capabilities.

Timely monitoring of greenness dynamics in urban agglomerations and analyzing their driving factors are important for sustainable development. However, current research on vegetation greenness at the scale of urban agglomerations remains limited. This study examines the greenness dynamics and its driving factors in China's four major urban agglomerations Beijing-Tianjin-Hebei (BTH), Yangtze River Delta (YRD), Pearl River Delta (PRD), Chengdu-Chongqing (CC) at a 30-meter spatial resolution over a long period (2000-2023). The use of an innovative integrated approach, combining the Gap Filling and Savitzky-Golay filtering (GF-SG) method, pixel dichotomy model, spatiotemporal dynamic analysis and geographical detector, provides a more comprehensive understanding of greenness dynamics in urban agglomerations. The results indicate several key points: 1.The proportion of areas where vegetation greenness increased (27.69 %, 14.10 %, 31.56 %, 23.09 %) is consistently larger than the proportion of areas where greenness decreased (4.3 %, 6.78 %, 5.11 %, 1.62 %) within BTH, YRD, PRD, CC. Greenness is dramatically increasing in all urban centers, but significantly decreasing at the edges of urban expansion; 2. Land cover conversions emerged as the dominant driver of greenness changes (the highest Qvalue is 0.5743), which indicates that land cover conversions play a greater role than natural factors. 3. The expansion of urban land and ecological land restoration explain the main reasons for the decrease and increase in greenness. Meanwhile, there are differences in the primary land cover conversions corresponding to the greenness changes among the four urban agglomerations. These findings not only contribute to understanding urban greenness dynamics but also offer a new perspective on the role of land cover conversions in shaping vegetation patterns.

Remote-sensing-image-based accurate road extraction plays a pivotal role in smart city planning and geospatial analysis. Despite recent advances, achieving precise road extraction remains challenging due to irregular road topologies and complex environment interference in high-resolution remote sensing images. Inspired by the human visual system’s “local focusing-global verification” mechanism, a novel road extraction network based on multilevel feature fusion (FF) and similarity filtering is proposed. The framework addresses two critical challenges. First, to suppress environmental noise, a dual-branch subsampling and feature similarity filtering network architecture is designed, as each branch is used to downsample the local area and the whole image separately. The auxiliary branch extracts local road features to construct a feature affinity matrix that guides global feature refinement in the main branch. Besides, to mitigate the impact of texture-similar objects and occlusions, a multilevel FF method is proposed integrating bidirectional deformable attention module (BDAM) and dilated skip network (DSN). The BDAM captures long-range dependencies of irregular roads through deformable convolutional kernels and bidirectional attention, while the DSN establishes skip connections with dilated convolutions to preserve edge details during multiscale FF. Comprehensive experiments conducted on publicly available datasets demonstrate that the proposed model outperforms the state-of-the-art methods for road extraction.

Urban agglomerations are critical for regional development, but extracting their built-up areas accurately is challenged by traditional night-time light data's limitations - low resolution (km to hectometre scale), over-saturation in urban cores, and missed detection in low-luminance areas. These issues hinder precise urban analysis, making improved extraction methods vital for urban planning and geographical research. This study focuses on extracting and classifying built-up areas in China's three major urban agglomerations. To address the above challenges, we use 10 m-resolution glimmer data from SDGSAT-1 and POI data to construct a dynamically adjustable weighted NTL-POI index. Combined with OTSU threshold segmentation and weighted K-means clustering, we realize hierarchical extraction of built-up areas. Results show that integrating SDGSAT-1 glimmer imagery and POI data precisely depicts urban internal structures, effectively detects low-luminance built-up areas, and optimizes accuracy and shape indicators. F1 scores for the Beijing-Tianjin-Hebei, Yangtze River Delta, and Guangdong-Hong Kong-Macao Greater Bay Area reach 0.74, 0.78, and 0.87, respectively. This provides accurate data support for urban research and holds value in urban planning and geographical analysis.

Visual 3D reconstruction enables rebuilding 3D scenes from captured images, serving as a fundamental data source for digital earth modeling and intelligent cities. In the foundational step, recent methods leverage learning-based descriptors for image registration and achieve tremendous advances in precision and robustness. However, these methods inevitably execute down sampling towards high-resolution images to fit the needs of neural networks, which leads to precision degradation of feature localization and matching. Thus, we propose GeoRecon: a novel coarse-to-fine visual 3D reconstruction method that optimally utilizes high-resolution images for high-quality visual 3D reconstruction. Firstly, the coarse stage conducts coarse reconstruction from downsampled images by performing neural matching with geometric priors. Secondly, we define the fine-grained stage, proposing a GPU-based algorithm for generating image-patch correspondences based on the neural matching priors to perform fine-grained image registration. Finally, based on the optimized camera poses under this coarse-to-fine paradigm, progressive dense reconstruction leveraging efficient neural radiance fields is proposed to accomplish the high-quality MVS reconstruction. Comparative experiments across various scenarios demonstrate the proposed method’s superior precision, robustness, and reconstruction quality.

Industrial heat sources (IHSs) are key contributors to anthropogenic heat, air pollution, and carbon emissions. Accurately and automatically detecting their production areas (IHSPAs) on a large scale is vital for environmental monitoring and decision making, yet this is challenged by the lack of high-resolution thermal data. Sustainable Development Science Satellite 1 (SDGSAT-1) thermal infrared spectrometer (TIS) data with the highest resolution (30 m) in the civilian field and a three-band advantage were first introduced to detect IHSPAs. In this study, an IHSPA identification model using multi-features extracted from SDGSAT-1 TIS and Landsat OLI data and support vector machine (SVM) was proposed. First, three brightness temperatures and four thermal radiation indices using SDGSAT-1 TIS and Landsat OLI data were designed to enlarge the temperature difference between IHSPAs and the background. Then, 10 features combined with three indices from Landsat OLI images with the same spatial resolution (30 m) and stable data were extracted. Second, an IHSPA identification model based on SVM and multi-feature extraction was constructed to identify IHSPAs. Finally, the IHS objects were manually delineated and verified using the identified IHSPAs and Google Earth images. Some conclusions were obtained from different comparisons in Wuhai, China: (1) IHSPA identification based on SVM using thermal and optical features can detect IHSPAs and obtain the best results compared with different features and identification models. (2) The importance of using thermal features from the SDGSAT-1 TIS to detect IHSPAs was demonstrated by different importance analysis methods. (3) Our proposed method can detect more IHSs, with greater spatial coverage and smaller areas, compared with the methods of Ma and Liu. This new way to detect IHSPAs can obtain higher-spatial-resolution emissions of IHSs on a large scale and help decision makers target environmental monitoring, management, and decision making in industrial plant processing.

Sustainable development depends on the integration of the economy, society, and environment. Yet, escalating environmental challenges pose threats to both society and the economy. Despite progress in addressing environmental issues to promote sustainability, knowledge gaps in scientific research, technological advancement, engineering practice, and policy development persist. In this review, we aim to narrow these gaps by proposing innovation-based solutions and refining existing paradigms. Reviewing past research and actions, we first elucidate the evolution of sustainability science and the essence of sustainable development and its assessment. Secondly, we summarize current major environmental issues, including global warming and climate change, biodiversity loss, land degradation and desertification, and environmental pollution, as well as their relationships with sustainability and the achievement of Sustainable Development Goals (SDGs). Subsequently, this review critically evaluates the role of innovations in science, technology, engineering, and policy (iSTEP) and their synergies in advancing sustainability and SDGs. While their sequential relationships may vary based on specific contexts or sustainability scenarios within the iSTEP framework, each component reinforces the others, fostering continuous improvement. Finally, this review offers recommendations and future perspectives for formulating sustainability roadmaps. Recommendations include fostering a vision of sustainability, promoting interdisciplinary collaboration, and encouraging transboundary cooperation among stakeholders for future sustainability endeavors.