Zhiwei Zhang

Mangrove ecosystems are increasingly threatened by anthropogenic disturbances and climate change, despite providing ecological services, including biodiversity conservation, coastal protection, and blue carbon storage. Long-term evaluations of mangrove dynamics and associated environmental conditions remain limited, particularly in the Sundarbans, the largest mangrove forest in the world. This study examined the spatiotemporal dynamics of the Sundarbans mangrove ecosystem, Bangladesh, using multi-temporal Landsat imagery (1990–2025), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and SHapley Additive exPlanations (SHAP). Model performance was evaluated using the Global Mangrove Watch (GMW) dataset and spatially blocked holdout validation. Classification accuracy was high (94.56–100%) under internal and spatially blocked validation (93.5–99.8%), whereas comparison with GMW yielded lower accuracies (66.4–95.7%). Change detection showed that mangrove area expanded from 2096.66 km² in 1990 to 3875.95 km² in 2025, a net gain of almost 1779.29 km², with substantial inter-period variability and a pronounced mapped decline between 2000 and 2005. SHAP analysis indicated that the relative contributions of model predictors changed over time, with NDVI contributing more strongly to model predictions in recent years than NDWI and NDMI. Mangrove gain, loss, and net change were statistically associated with cyclone exposure and elevation, while precipitation and river discharge showed less consistent relationships. This study highlights a practical method for monitoring spectral dynamics in vulnerable coastal ecosystems and supports mangrove conservation.

Building footprint extraction in high-density urban areas remains difficult because spectral confusion and shadows obscure building–background differences, while dense adjacency and complex boundaries hinder boundary recovery and adjacent-building separation. To address these issues, this study combines Digital Orthophoto Maps (DOM) and normalized Digital Surface Models (nDSM) and develops ACM-PSPNet for high-density built-up areas of Hong Kong. ACM-PSPNet extends the PSPNet baseline by integrating atrous spatial pyramid pooling and convolutional block attention for high-level contextual enhancement and feature recalibration, together with an MS-Fuse decoder for progressive multilevel spatial-detail recovery. The main experiments were independently repeated three times and evaluated on a spatially independent test set. In the input-source comparison, DOM+nDSM yielded a mean IoU of 84.94%, compared with 68.23% for DOM and 83.23% for nDSM alone. Using DOM+nDSM as the common input, the model comparison showed that ACM-PSPNet provided the highest performance among the eight evaluated models, with mean IoU, F1 Score, and Boundary F1 values of 87.81%, 93.13%, and 79.78%, respectively. In selected typical scenes, the under-segmentation proportion decreased from 35.7% for PSPNet to 5.0% for ACM-PSPNet. The results support ACM-PSPNet as an accuracy-oriented framework for dense urban building mapping, particularly where reliable boundary recovery and adjacent-building separation are required, although broader cross-city and cross-sensor validation remains necessary.

It has been well observed that accurate estimation of the aboveground biomass (AGB) of mangrove forests is critical for evaluating ecosystem health, carbon sink capacity, and sustainable development. This study utilizes UAV-LiDAR data and field measurements to develop an AGB inversion model based on 26 feature variables. We employed three machine learning algorithms—random forest (RF), extreme gradient boosting (XGBoost), and support vector machine (SVM)—to estimate mangrove AGB in the Xinyingwan region of Lingao County, Hainan Province, China. The key findings include that: (1) the SVM algorithm demonstrated the highest predictive accuracy, with an R² of 0.8853 and RMSE of 0.4766 kg/m², making it most suitable for this study; (2) the proposed zero-importance feature selection method based on mutual information (MI) outperformed traditional techniques, selecting more effective variables for model development; (3) in the SVM model, variables selected using the zero-importance feature selection method based on MI yielded the best prediction accuracy; and (4) the estimated AGB in the study area ranged from 1.97 to 5.23 kg/m², with an average of 3.83 kg/m². This study not only provides valuable data for mangrove ecosystem conservation and restoration but also offers a scientific basis and technical framework for future biomass estimation and carbon stock assessments.

Accurate shoreline extraction is critical for coastal engineering applications, including erosion monitoring, disaster response, and sustainable management of island ecosystems. However, traditional methods face challenges in large-scale monitoring due to high costs, environmental interference (e.g., cloud cover), and poor performance in complex terrains (e.g., bedrock coastlines). This study developed an optimized DeepLabV3+ model for the extraction of island shorelines, which improved model performance by replacing the backbone network with MobileNetV2, introducing a strip pooling layer into the ASPP module, and adding CBAM modules in both the shallow and deep stages of feature extraction from the backbone network. The model accuracy was verified using a self-built drone dataset of the shoreline of Koh Lan, Thailand, and the results showed: (1) Compared with the control model, the improved DeepLabV3+ model performs excellently in pixel accuracy (PA), recall, F1 score, and intersection over union (IoU), reaching 98.7%, 97.7%, 98.0%, and 96.2%, respectively. Meanwhile, the model has the lowest number of parameters and floating-point operations, at 6.61 M and 6.7 GFLOPS, respectively. (2) In terms of pixel accuracy (PA) and intersection over union (IoU), the CBAM attention mechanism outperforms the SE-Net and CA attention mechanisms. Compared with the original DeepLabV3+ network, PA increased by 3.1%, and IoU increased by 8.2%. (3) The verification results of different types of coastlines indicate that the improved model can effectively distinguish between shadows and water bodies, reducing the occurrence of false negatives and false positives, thereby lowering the risk of misclassification and obtaining better extraction results. This work provides a cost-effective tool for dynamic coastal management, particularly in data-scarce island regions.

The degradation of marine and coastal resources, caused mainly by human activities, underscores the urgent need for conservation. In waters around the Sichang Islands, the Bryde’s whale is listed as an endangered marine species. The extensive human activities in this area have raised serious concerns about the possible negative influence on this species. To conserve the species effectively and efficiently, we need to understand where it distributes and how human activities influence its distribution. For this purpose, we use spatial modeling techniques alongside diverse databases encompassing various spatial and ecological factors to analyze the distribution of, and human activities’ impact on, the Bryde’s whale (Balaenoptera edeni) in the Sichang Islands, Thailand. We also use the MaxEnt model to predict habitat suitability and the result reveals key factors influencing whale occurrence across seasons. During the dry season, TSS (32.8%), chlorophyll-a (20.1%), and DO (15.9%) levels play significant roles, while DO (29.9%), NH₃ (29.4%), and distance to shore (13.3%) are crucial in the wet season. Furthermore, the Species Risk Assessment (SRA) model indicates the mooring area (14.95%) is the high-risk area for the Bryde’s Whale, particularly during the wet season. In contrast, moderate risks are observed during the dry season, notably in fishing zones (99.68%) and mooring areas (99.28%). The study also highlights that the factors mentioned above influence prey availability and habitat suitability for the Bryde’s whale and identifies potential threats posed by human activities, such as fishing and other maritime operations, that are likely to decrease water quality and prey abundance. These results are useful information for identifying sensitive areas and measures for risk mitigation, thus supporting the development of MSP or MPA plans.

Island infrastructure material stock (MS) analysis reveals resource flow and accumulation, providing policymakers with insights for managing resources and planning. This study comprehensively analyzed the MS of infrastructure on Miao Island using a bottom-up approach and multi-source data. Key findings include the following: In 2020, the total in-use MS was 249.8 kt, with stone, gravel, and sand accounting for 80%. Transportation infrastructure held the largest share (40.8%). Over the past 40 years, Miao Island’s infrastructure MS increased by 256%, with a net addition of 179.6 kt. The three distinct development periods were closely linked to China’s reform and local stimulus plans. Miao Island has a lower construction intensity than urban areas, with a per capita MS growth rate of 10.12 t/yr. Despite this, future waste remains a challenge to the island’s capacity. Given the constraints of limited investment due to population decline and the aging of in-use stock, island infrastructure should conform to local resource availability and long-term plans. Priority should be given to environmental compatibility, resilience to resource disruptions, and establishing a circular system to support sustainable island development.

According to the Thailand’s National Strategy (2017-2036) and National Reform Plans, various tools, techniques, or methods are necessary to collect and investigate data for the effective preservation and protection of the country’s natural resources. We aimed to apply various tools and methods for integrated coastal management in Thailand. This study used the InVEST models, including the habitat quality (HQ) and habitat risk assessment (HRA) models, to evaluate the natural habitat quality and cumulative human activity risk in the Sriracha district and Sichang Islands, Thailand. The HQ model revealed the presence of abundant ecological services and high quality natural habitats. We observed habitat degradation in the mooring zone, city area, forests, and coral reefs, with moderate risk to distinct habitats. Our findings identified two potential scenarios. Conservation scenarios exhibited a lower HRA ratio compared to current and development scenarios. Overall, the results showed the effectiveness of the InVEST model in evaluating habitat risk under both present and simulated conditions. Our study highlights the importance of informed management plans and policy-making processes to achieve planned coastal management goals.