Global warming-induced climate change evolved to be one of the most important research topics in Earth System Sciences, where remote sensing-based methods have shown great potential for detecting spatial temperature changes. This study utilized a time series of Landsat images to investigate the Land Surface Temperature (LST) of dry seasons between 1989 and 2019 in the Bac Binh district, Binh Thuan province, Vietnam. Our study aims to monitor LST change, and its relationship to land-cover change during the last 30 years. The results for the study area show that the share of Green Vegetation coverage has decreased rapidly for the dry season in recent years. The area covered by vegetation shrank between 1989 and 2019 by 29.44%. Our findings show that the LST increase and decrease trend is clearly related to the change of the main land-cover classes, namely Bare Land and Green Vegetation. For the same period, we find an average increase of absolute mean LST of 0.03 °C per year for over thirty years across all land-cover classes. For the dry season in 2005, the LST was extraordinarily high and the area with a LST exceeding 40 °C covered 64.10% of the total area. We expect that methodological approach and the findings can be applied to study change in LST, land-cover, and can contribute to climate change monitoring and forecasting of impacts in comparable regions.

Da Nang City, a rapidly urbanizing area in Central Vietnam, is experiencing significant changes in Land Use/Land Cover (LULC). This study aims to monitor and predict LULC changes in the Da Nang area up to the year 2035. The use of free, open-source, and highly consistent data, combined with JavaScript programming on the Google Earth Engine (GEE) platform and machine learning algorithms, allowed for fast and efficient data processing. The study employed the Random Forest (RF) algorithm to classify six land cover types from Landsat-8 satellite imagery, achieving high classification accuracy with a Kappa coefficient exceeding 0.8. These classification results were then used for the future LULC change prediction model. To simulate and predict LULC changes for 2035, an integrated model of Cellular Automata (CA) and Artificial Neural Network (ANN) was applied to the Da Nang area. The CA-ANN model addresses the limitations of traditional statistical models (such as Markov Chain) by integrating spatial control factors and neighborhood influences. The prediction results clearly indicate an expansive trend in urban development; the residential area is forecasted to increase, reaching 6.22% by 2035, while the agricultural cultivation area shows a notable decrease of approximately 2.81% compared to 2015. The research affirms the superior efficiency of the integrated CA-ANN model for predicting LULC changes in fast-developing areas. These detailed and continuous multi-year results can effectively support fields such as spatial planning, land management, real estate, environmental resource management, and contribute to the development of Da Nang.

Gia Lam is a district in the eastern part of Hanoi, Vietnam, undergoing rapid development and urbanization. Predicting land use/land cover changes is crucial for supporting policymakers in designing effective local development strategies. This study aims to forecast land use/land cover changes in Gia Lam District through 2028. Sentinel-2 optical satellite imagery serves as the primary data source, with the classification of five land use/land cover types at different times performed using the Random Forest (RF) algorithm, and forecast results generated using a Cellular Automata (CA) model combined with an Artificial Neural Network (ANN) model. The results indicate a significant expansion of built-up areas, projected to cover 68.92% of the natural area by 2028. On the contrary, the area under annual vegetation is expected to decline to just 7.71%. These findings provide valuable insights for researchers and land use planners.

Although short-cycle Acacia plantation has caused negative impacts on the mountainous soil environment, the understanding of these impacts is still unknown in Vietnam. Therefore, this study evaluated the effects of short-cycle Acacia plantation on soil properties under successive seven-year cycles in some areas of Vietnam. A total of 182 soil samples randomly stratified by the Acacia cycles were collected at the topsoil depth of 30 cm to analyse the effects of Acacia cycles on changes in the soil properties. Non-parametric Kruskal-Wallis & Mann-Whitney tests were used to assess the differences in soil properties under different Acacia cycles and natural forest. Then, the Analytical Hierarchy Process (AHP) was applied to combine the soil properties into the soil quality index for assessing soil quality in the different cycles. The results showed that changes in the soil properties among the Acacia cycles and the natural forest were statistically different (p<0.05). The AHP-based soil quality assessment shows clearly the varying levels of soil deterioration in the successive cycles. It was also found that the indicators of OM, TN, and pH were more closely correlated with the SQI; therefore, soil conservation measures are indispensable for the Acacia soils. The study is a practical contribution to the understanding of soil quality change in short-cycle Acacia plantation areas that are common in many parts of the world, especially in the tropics.