Số báo hiện thời

Abstract: 

Air pollution caused by fine particulate matter (PM2.5) has become a serious environmental problem in many large urban areas, especially in rapidly urbanizing regions. Accurate prediction of PM2.5 concentrations plays an important role in air quality management and the development of early warning systems for air pollution. This study evaluates the applicability of machine learning and deep learning approaches for forecasting PM2.5 concentrations using time-series data combined with meteorological variables. The dataset includes PM2.5 concentrations together with meteorological variables such as temperature, relative humidity, and wind speed collected in Hanoi. Data preprocessing steps include outlier detection using the Interquartile Range (IQR) method, data normalization using the Z-score approach, and the construction of time-series features. Several forecasting models were implemented and compared, including ARIMA, Random Forest, LSTM, GRU, and Transformer models. The experimental results show that deep learning models outperform traditional statistical approaches in PM2.5 prediction. Among the evaluated models, the Transformer model achieved the best performance with lower prediction errors and a better ability to capture temporal variations in PM2.5 concentrations. The results demonstrate the potential of deep learning techniques for air quality forecasting and provide a scientific basis for developing early warning systems for air pollution in large urban areas.

Abstract:

This study was conducted in Hong Van Commune, Hanoi, to evaluate the current status of land use right certification and the issuance of ownership certificates for assets attached to land during the 2021–2025 period. The research employed both primary and secondary data collection and analytical methods. Following administrative consolidation, Hong Van Commune comprises seven sub-communal units (Hong Van, Ha Hoi, Lien Phuong, Van Tao, Duyen Thai, Ninh So, and Dong My), with a total natural land area of 2,439.35 hectares. During the study period, a total of 139 land use right certificates were issued for residential land, achieving 92.05% of the required target, while 10,690 certificates were granted for agricultural land, corresponding to 90.32% of the total demand. Additionally, 1,516 land-use change registration applications were processed and approved, reaching a completion rate of 97.18%. Despite these achievements, several limitations were identified. A number of applications remain unresolved, primarily due to complex land origins, incomplete documentation, or insufficient legal eligibility. Furthermore, cadastral records across different periods lack consistency, and delays in data updating have negatively affected the efficiency of administrative processing. Based on these findings, the study proposes five groups of solutions aimed at improving the effectiveness of land registration and certification processes in the coming years.

Abstract:

Sand mining in river channels has increasingly altered river morphology and intensified riverbank erosion in many areas of the Mekong Delta. This study applies the two-dimensional hydrodynamic model MIKE 21 to simulate flow dynamics and sediment transport in the Hau River reach between Long Xuyen City and Cho Moi District, An Giang Province, in order to evaluate the impacts of sand mining on riverbed morphology. In addition, the geotechnical model Geo-Slope/W was used to assess riverbank stability under different sand-mining scenarios. Model calibration results show good agreement between simulated and observed data, with a correlation coefficient R²>0.85 for water level and R²≈0.86for suspended sediment concentration (SSC). Simulation results indicate that sand mining may locally lower the riverbed elevation by up to approximately 2.5 m after 270 days of excavation, while the morphological changes are mainly concentrated within the mining area and gradually decrease toward both riverbanks. After the mining activities cease, the riverbed tends to be naturally refilled by sediments transported from upstream sections and adjacent channels. The riverbank stability analysis using the Geo-Slope/W model shows that the minimum safety factor ranges from 1.448 to 1.761, which is higher than the design safety threshold, indicating that the riverbanks remain stable under the considered mining scenarios. The results provide a scientific basis for assessing the impacts of sand mining on river morphology and support sustainable river-sand management in the Mekong Delta.

Abstract:

This scientific article explores the objectives and fundamental principles of engineering geodetic surveys to detect structural deformations, identify the types and causes of subsidence and displacements, and analyze the monitoring processes for deformations in buildings and structures. It presents a methodology for predicting the movement of structures by accurately determining their deformations, displacements, and potential failures using high-precision geodetic techniques. The study assesses the current geodetic methods for monitoring deformations in hydraulic structures, draws conclusions on the most effective approaches, and provides suggestions for future research.

Abstract:

In recent years, satellite image data has been increasingly widely used in many areas of economic and social life. Over time, the accumulated image data lake have increased rapidly in both quantity and capacity. This gives organizations that research, apply and produce geospatial data more opportunities to exploit information, but also poses some challenges in managing them. A basic need of online users is to search, locate and look up information about satellite images in the data lake they are interested in. The main contribution in this study include two aspects. Firstly, an effective scientific practical approach to design data architecture for storing satellite image data and managing satellite image metadata based on three technologies: Hadoop, Hbase and PostGis was proposed and tested. Secondly, a Web service that allows quick search and look up of satellite image metadata information in big data lake was implemented and tested. Experimental results on the Sentinel2 image warehouse has shown promising results. Satellite images are queried and located in the database in near real-time mode. Smart, easy-to-use client interface creates a smooth experience, Web APIs are fast and seamless (www.geoview.vn).

Abstract:

This study presents an integrated approach utilizing multispectral Sentinel-2, hyperspectral PRISMA, and Synthetic Aperture Radar (SAR) COSMO-SkyMed (CSK) data to map land use/land cover (LULC) patterns in the Can Gio mangrove ecosystem. The analysis is supplemented with biophysical variables (LAI, FAPAR) and an in-situ spectral library to enhance the spectral discriminability of vegetation and spectrally similar surfaces. A Linear Spectral Mixture Model (LSMM) is applied to the PRISMA data to address the severe spectral mixing commonly encountered in coastal environments. Furthermore, CSK data are exploited to delineate urban settlements and aquaculture ponds. The classification results yielded an overall accuracy of 88% (Kappa = 0.83), demonstrating the efficacy of the multisensor approach in characterizing heterogeneous landscapes. This methodology exhibits significant potential for application in next-generation hyperspectral missions.