The main objective of this study is to assess the spatio-temporal dynamics of land cover/land use changes in the lower Mekong Delta over the last 40 years with the coastal Tran Van Thoi District of Ca Mau Province, Vietnam as a case study. Land cover/land use change dynamics are derived from moderate to high spatial resolution (Landsat and SPOT) satellite imagery in six time intervals ranging from 1973 to 2011. Multi-temporal satellite images were collected, georeferenced, classified using per-pixel method, validated, and compared in post classification for the land use/land cover change detection in decades. Seven major land cover/land use classes were obtained, including cultivated lands, aquaculture ponds, mangrove forest, melaleuca forest, built up areas, bare lands, and natural water bodies. The accuracies of the land cover/land use maps for 1973, 1979, 1989, 1995, 2004, and 2011 were 81%, 82%, 86%, 87%, 89%, and 89%, respectively. The results show that the area of cultivated lands reduced over the period 1973–2011, however, it still represents the dominant land use in the case study. Aquaculture ponds were almost absent in 1973 but greatly increased from 1995 to 2004, to represent 20% of the land surface in 2011. Overall, from 1973 to 2011, bare lands, cultivated lands, mangrove forest, and melaleuca forest decreased by 104 km², 77 km², 61 km², and 5 km², respectively. In contrast, aquaculture lands and built up areas increased by 123 km² and 120 km², respectively. Temporal analysis highlights that these changes took place mostly between 1995 and 2004. This study is a first step to identify the main drivers of land use changes in this delta region, which include economical policies as well as demographic, socio-economic, and environmental changes.

The Ca Mau Peninsula, situated in the Mekong Delta of Vietnam, features low-lying terrain. In addition to the challenges posed by climate change, land subsidence in the area is exacerbated by the overexploitation of groundwater and intensive agricultural practices. In this study, we assessed the land subsidence susceptibility in the Ca Mau Peninsula utilizing three boosting machine learning models: AdaBoost, Gradient Boosting, and Extreme Gradient Boosting (XGB). Eight key factors were identified as the most influential in land subsidence within Ca Mau: land cover (LULC), groundwater depth, digital terrain model (DTM), normalized vegetation index (NDVI), geology, soil composition, distance to roads, and distance to rivers and streams. The dataset includes 2011 points referenced from the Persistent Scattering SAR Interferometry (PSI) method, of which 1011 points are subsidence points and the remaining are non-subsidence points. The sample points were split, with 70% allocated to the training set and 30% to the testing set. Following computation and execution, the three models underwent evaluation for accuracy using statistical metrics such as the receiver operating characteristic (ROC) curve, area under the curve (AUC), specificity, sensitivity, and overall accuracy (ACC). The research findings revealed that the XGB model exhibited the highest accuracy, achieving an AUC and ACC above 0.88 for both the training and test sets. Consequently, XGB was chosen to construct a land subsidence susceptibility map for the Ca Mau Peninsula. In addition, 31 subsidence points measured by leveling surveys between 2005 and 2020, provided by the Department of Survey, Mapping and Geographic Information Vietnam, were used for validating the land subsidence susceptibility from the XGB method. The findings indicate a 70.9% accuracy rate in predicting subsidence susceptibility compared to the leveling measurement points.

The Ca Mau Peninsula situated in the Mekong Delta of Vietnam, features a low-lying terrain. Over recent years, the region has encountered the adverse impacts of climate change, leading to both land subsidence and rising sea levels. In this study, we assessed the land subsidence susceptibility in the Ca Mau peninsula utilizing three Boosting machine learning models: AdaBoost, Gradient Boosting, and Extremely Gradient Boosting (XGB). Eight key factors were identified as the most influential in land subsidence within Ca Mau: land cover (LULC), Groundwater levels, distance to roads, Digital Terrain Model (DTM), normalized vegetation index (NDVI), geology, soil composition, and proximity to rivers and streams. A dataset comprising 1950 subsidence sample points was employed for the model, with 1910 points obtained from the PSInSAR Radar method, and the remaining points derived from leveling measurements. The sample points were split, with 70% allocated to the training set and 30% to the testing set. Following computation and execution, the three models underwent evaluation for accuracy using statistical metrics such as the ROC curve, Area under the curve (AUC), Specificity, Sensitivity, and Overall Accuracy. The research findings revealed that the XGB model exhibited the highest accuracy, achieving an AUC above 0.9 for both the training and test sets. Consequently, XGB was chosen to construct a land subsidence susceptibility map for the Ca Mau peninsula.