Tạp chí Trắc địa – Bản đồ

Mapping wind turbine tower locations in Ca Mau coastal region using Sentinel-1 synthetic aperture radar images

Tạp chí Trắc địa – Bản đồ — 2026-03-08

Ca Mau province is a coastal region with strong and fairly stable winds, less affected by
storms. By July 2025, Ca Mau province has 13 completed and operational wind farms. The
increasing number of wind energy projects shows that monitoring the development of wind energy
projects is essential. The objective of this study is to detect the persistent construction structures
on sea, specifically wind towers built off the shore of Ca Mau province. This study used the two
dimensional polarization space method on Sentinel-1 time-series radar images to identify the
locations of wind turbine towers off the shore of Ca Mau province. The results showed that the
confounding effects of complex variations in incident and azimuth angles of the Sentinel-1
synthetic aperture radar (SAR) images have been completely eliminated. In addition, the method
used in this study was successful in mapping persistent construction structures with Sentinel-1
time-series SAR images. The accuracy of results was evaluated by observing and collecting
ground truth data in the study area. With very high accuracy, this method can be applied to map
the locations of persistent construction structures at sea at other wind farm projects in the future.

Landslide susceptibity mapping using Analytical Hierarchy Process and Fuzzy- Analytical Hierarchy Process approches: A case study in Binh Dinh province, Viet Nam

Tạp chí Trắc địa – Bản đồ — 2026-03-08

Binh Dinh Province, Vietnam, has recently experienced frequent landslide events,
highlighting the urgent need for effective hazard assessment. This study aims to evaluate landslide
susceptibility using the Analytical Hierarchy Process (AHP) and Fuzzy Analytical Hierarchy
Process (Fuzzy-AHP) models. Ten conditioning factors were considered in both models:
elevation, slope, aspect, Topographic Wetness Index (TWI), Standardized Precipitation Index
(SPI), Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index
(NDWI), distance to roads, distance to rivers, and geological characteristics. The resulting
susceptibility maps were classified into five categories: very low, low, moderate, high, and very
high. Model validation was conducted using the Receiver Operating Characteristic (ROC) curve,
with Area Under the Curve (AUC) values exceeding 0.80, Root Mean Square Error (RMSE) values
around 0.2, and accuracy scores above 0.8 for both models—indicating excellent predictive
performance. Notably, the Fuzzy-AHP model slightly outperformed the AHP model. The analysis
revealed that approximately 15% of the area falls within high and very high susceptibility zones,
30% within the moderate zone, and the remaining areas within low or very low susceptibility
zones. These findings confirm the effectiveness and reliability of both the AHP and Fuzzy-AHP
approaches for landslide susceptibility assessment. The resulting maps provide valuable guidance
for local authorities and stakeholders in implementing disaster risk reduction strategies, early
warning systems, and sustainable land-use planning.

Prediction of daily streamflow using adaptive neuro-fuzzy inference systems and group method of data handling approaches: a case study of kone river, binh dinh province

Tạp chí Trắc địa – Bản đồ — 2026-03-08

ement, and planning. This study evaluates the performance of the Group Method of Data
Handling (GMDH) and Adaptive Neuro-Fuzzy Inference System (ANFIS) models in predicting daily
streamflow. Rainfall and streamflow data, collected from rain gauges and hydrological stations in
the upstream area of the Kone River in Binh Dinh Province, were used as inputs for the models and
tested across various input scenarios. Model performance was assessed using three statistical
metrics: the coefficient of determination (R²), root mean square error (RMSE), and mean absolute
error (MAE). The results revealed that the ANFIS model consistently outperformed the GMDH
model, achieving the highest R² value of 0.94 and the lowest RMSE (64.6 m³/s) and MAE (14.2 m³/s).
Additionally, Scenario 1 demonstrated the best predictive performance across both models. This
study successfully developed reliable approaches for daily streamflow forecasting and provided
valuable insights into the influence of input variables on prediction accuracy.

Spatiotemporal Analysis of Urban Surface Cover Structure in Ho Chi Minh City from 2015 to 2025: A Big Data and Machine Learning Approach

Tạp chí Trắc địa – Bản đồ — 2026-03-08

Land-use structure transformation in megacities such as Ho Chi Minh City (HCMC) not
only reflects rapid economic growth but also constitutes a fundamental driver of geohazards,
particularly land subsidence caused by increasing static and dynamic loads. To quantitatively
assess this process, the study developed an automated monitoring framework on the Google Earth
Engine (GEE) platform, integrating the Random Forest algorithm to process multi-temporal
satellite imagery from Landsat 8/9 and Sentinel-2 over 11 years (2015–2025). Accuracy
assessment results indicate robust classification performance, with Kappa coefficients ranging
from 0.85 to 0.96 and Overall Accuracy between 88.1% and 97.4%. The findings reveal a clear
expansion of built-up impervious surfaces, increasing from 5,500.45 ha in 2015 to 6,395.12 ha in
2025. The study successfully captured the spatiotemporal dynamics of five major land-cover
classes, highlighting the pronounced growth of “built-up impervious surfaces” and the complex
fluctuations of “bare land,” which reflect different construction preparation stages. Statistical
analysis shows a strong spatial correlation between impervious surface expansion and areas
identified as subsidence-prone. The resulting dataset provides reliable input data for geotechnical
models, enabling clearer differentiation between static structural loads and dynamic traffic loads
in ground deformation prediction.

Spatial Heterogeneity Analysis and Machine Learning-Based Forecasting of Land Subsidence in Ho Chi Minh City: A GWR and ConvLSTM Integrated Approach

Tạp chí Trắc địa – Bản đồ — 2026-03-08

This study develops a framework for simulating and forecasting land subsidence in Ho Chi
Minh City, specifically focusing on District 12. By utilizing InSAR time-series subsidence data
from 2015-2020 alongside influencing factors such as building density, distance to water bodies,
and land use types, the research employs Geographically Weighted Regression (GWR) to analyze
the underlying subsidence mechanisms. Experimental results demonstrate significant spatial
heterogeneity in land deformation, where Land Use and Distance to Water emerge as the most
dominant factors, with average regression coefficients of -0.390 and -0.344, respectively.
Furthermore, the study proposes an integrated forecasting system architecture leveraging
advanced Machine Learning models, including Random Forest, XGBoost, and ConvLSTM deep
learning architectures to predict future surface deformation. Risk zonation results derived from
K-means clustering provide effective visual tools for urban planning and early warning systems
for geological hazards.