Explore the vast range of titles available.

Cenozoic basalt regions contain various natural resources that can be used for socio-economic development. Different quantitative and qualitative methods have been applied to understand the geological and geomorphological characteristics of basalt formations. Nowadays the integration of remote sensing and geographic information systems (GIS) has become a powerful method to distinguish geological formations. In this paper, authors combined satellite and fieldwork data to analyze the structure and morphology of highland geological formations in order to distinguish two main volcanic eruption episodes. Based on remote sensing analysis in this study, different spectral band ratios were generated to select the best one for basalt classification. Lastly, two spectral combinations (including band ratios 4/3, 6/2, 7/4 in Landsat 8 and 3/2, 5/1, 7/3 in Landsat 7) were chosen for the Maximum Likelihood classification. The final geological map based on the integration of Landsat 7 and 8 outcomes shows precisely the boundary of the basalt formations with the accuracy up to 93.7%. This outcome contributed significantly to the correction of geological maps. In further studies, authors suggest the integration of Landsat 7 and 8 data in geological studies and natural resource and environmental management at both local and regional scales.

The natural wetland areas in Vietnam, which are transition areas from inland and ocean, play a crucial role in minimizing coastal hazards; however, during the last two decades, about 64% of these areas have been converted from the natural wetland to the human-made wetland. It is anticipated that the conversion rate continues to increase due to economic development and urbanization. Therefore, monitoring and assessment of the wetland are essential for the coastal vulnerability assessment and geo-ecosystem management. The aim of this study is to propose and verify a new deep learning approach to interpret 9 of 19 coastal wetland types classified in the RAMSAR and MONRE systems for the Tien Yen estuary of Vietnam. Herein, a Resnet framework was integrated into the U-Net to optimize the performance of the proposed deep learning model. The Sentinel-2, ALOS-DEM, and NOAA-DEM satellite images were used as the input data, whereas the output is the predefined nine wetland types. As a result, two ResU-Net models using Adam and RMSprop optimizer functions show the accuracy higher than 85%, especially in forested intertidal wetlands, aquaculture ponds, and farm ponds. The better performance of these models was proved, compared to Random Forest and Support Vector Machine methods. After optimizing the ResU-Net models, they were also used to map the coastal wetland areas correctly in the northeastern part of Vietnam. The final model can potentially update new wetland types in the southern parts and islands in Vietnam towards wetland change monitoring in real time.

Synthetic aperture radar (SAR) imaging is used to identify ships, which is a vital task in the maritime industry for managing maritime fisheries, marine transit, and rescue operations. However, some problems, like complex background interferences, various size ship feature variations, and indistinct tiny ship characteristics, continue to be challenges that tend to defy accuracy improvements in SAR ship detection. This research study for multiscale SAR ships detection has developed an upgraded YOLOv5s technique to address these issues. Using the C3 and FPN + PAN structures and attention mechanism, the generic YOLOv5 model has been enhanced in the backbone and neck section to achieve high identification rates. The SAR ship detection datasets and AirSARship datasets, along with two SAR large scene images acquired from the Chinese GF-3 satellite, are utilized to determine the experimental results. This model’s applicability is assessed using a variety of validation metrics, including accuracy, different training and test sets, and TF values, as well as comparisons with other cutting-edge classification models (ARPN, DAPN, Quad-FPN, HR-SDNet, Grid R-CNN, Cascade R-CNN, Multi-Stage YOLOv4-LITE, EfficientDet, Free-Anchor, Lite-Yolov5). The performance values demonstrate that the suggested model performed superior to the benchmark model used in this study, with higher identification rates. Additionally, these excellent identification rates demonstrate the recommended model’s applicability for maritime surveillance.

Land use change due to the development of agriculture and community-based tourism has resulted in an increase in natural hazards (e.g. erosion and landslides) that affect sustainability in the Sapa mountainous area in northern Vietnam. Natural hazard regulating ecosystem services have protected the local people from the destruction of their villages, goods and natural resources, especially in the rainy season. However, it is difficult to identify which kinds of anthropogenic constructions support a co-production of regulating services in human-influenced social–ecological systems and in which specific types of land use and land cover the supply of such services takes place, especially in heterogeneous mountainous areas. Therefore, this research attempts to (1) distinguish between the potential and actual use (flow) of natural hazard regulating ecosystem services and (2) understand how soil erosion and landslide regulating ecosystem services can contribute to a sustainable management of different ecosystems, especially in rice fields and forest areas. Two models (InVEST for soil erosion, Analytic Hierarchy Process for landslide analysis) were used to analyze and map the contributions of natural versus anthropogenic components for regulating natural hazards in Sapa. The results show the incoherent distribution of erosion regulating services and low capacities of landslide regulating services in areas that have seriously been affected by human activities, especially forestry and agricultural development. The contribution of rice ecosystems to soil erosion mitigation is higher than in the case of landslides. Nevertheless, one-third of the area of paddy fields in the case study area have “no” capacity to supply natural hazard regulating ecosystem services and should therefore be re-forested.

Estuaries feature diverse ecosystems with great biological production and favourable resources and landscapes for ecotourism. Increasing natural disasters have threatened the lives and safety of over 70% of the region's population in recent years. Rapid urbanisation and tourism have changed land use. This changes ecosystem structure and function, impacting service provision. This study developed a Bayesian Belief Network (BBN) model to assess the imbalance between socio-economic development and resource conservation using an ecosystem services (ES) approach. The BBN model helps synthesise and exchange information, provide decision-making data, evaluate trade-off possibilities and anticipate future situations when assessing ES. The BBN network model probabilistically evaluates ecosystem services using expertise, statistical modelling, geographic information systems and interviews. We assessed the comprehensive value of 17 forms of ES for four ecosystem groups over a period of 30 years. As a result, the cultural ecosystem services of some estuarial regions in Vietnam have the highest value and are showing an increasing trend, while the regulating ecosystem services are continuously fluctuating and decreasing. Provisioning ecosystem services are stable with small changes. This study also examined ES values in six landscape categories and created two ES change scenarios. The findings can help managers choose land-use and resource exploitation policies, understand the value of ecosystem services at the regional level and develop estuary sustainability strategies for long-term ecosystem service balance.

The monitoring of ecosystem dynamics utilises time and resources from scientists and land-use managers, especially in wetland ecosystems in islands that have been affected significantly by both the current state of oceans and human-made activities. Deep-learning models for natural and anthropogenic ecosystem type classification, based on remote sensing data, have become a tool to potentially replace manual image interpretation. This study proposes a U-Net model to develop a deep learning model for classifying 10 island ecosystems with cloud- and shadow-based data using Sentinel-2, ALOS and NOAA remote sensing data. We tested and compared different optimiser methods with two benchmark methods, including support vector machines and random forests. In total, 48 U-Net models were trained and compared. The U-Net model with the Adadelta optimiser and 64 filters showed the best result, because it could classify all island ecosystems with 93 percent accuracy and a loss function value of 0.17. The model was used to classify and successfully manage ecosystems on a particular island in Vietnam. Compared to island ecosystems, it is not easy to detect coral reefs due to seasonal ocean currents. However, the trained deep-learning models proved to have high performances compared to the two traditional methods. The best U-Net model, which needs about two minutes to create a new classification, could become a suitable tool for island research and management in the future.

Urban flooding is a major challenge to sustainable development in rapidly urbanizing cities. This study applies an integrated approach that combines Sentinel-1 SAR data, geomorphological analysis, and the DPSIR (Drivers–Pressures–State–Impacts–Responses) framework to assess the relationship between urbanization and flooding in Hanoi during the 2010–2024 period (with Sentinel-1 time-series data for 2015–2024). A time series of Sentinel-1 images (2015–2024) was processed on Google Earth Engine to detect inundation and construct a flood frequency map, which was validated against 148 field survey points (overall accuracy = 87%, Kappa = 0.79). The results show that approximately 80% of newly urbanized areas are situated on geomorphologically sensitive units, including inside- and outside-dike floodplains, fluvio-marine plains, paleochannels, and karst terrains, characterized by low elevation and high flood susceptibility. Meanwhile, about 73% of the total inundated area occurs within newly developed urban zones, primarily in western and southwestern Hanoi, where rapid expansion on flood-prone terrain has intensified hazards. The DPSIR analysis highlights rapid population growth, land use change, and inadequate drainage infrastructure as the main pressures driving both the frequency and extent of flooding. To our knowledge, this is the first study integrating geomorphology, Sentinel-1, and DPSIR for Hanoi, thereby providing robust evidence to support sustainable urban planning and climate-resilient development.

The increase of coastal erosion due to intense tropical storms and unsustainable urban development in Vietnam demands vulnerability assessments at different research scales. This study proposes (1) a new approach to classify coastlines and (2) suitable criteria to evaluate coastal vulnerability index (CVI) at national and regional/local scales. At the national scale, the Vietnamese coastline was separated into 72 cells from 8 coast types based on natural features, whereas the Center region of Vietnam was separated into 495 cells from 41 coast types based on both natural and socio-economic features. The assessments were carried out by using 17 criteria related to local land use/cover, socio-economic, and natural datasets. Some simplified variables for CVI calculation at the national scale were replaced by quantitative variables at regional/local scales, particularly geomorphology and socio-economic variables. As a result, more than 20% of Vietnam’s coastline has high CVI values, significantly more than 350 km of the coasts in the center part. The coastal landscapes with residential and tourism lands close to the beaches without protection forests have been strongly affected by storms’ erosion. The new approach is cost-effective in data use and processing and is ideal for identifying and evaluating the CVI index at different scales.