Luong Van Viet

Vegetation degradation, particularly due to deforestation and urbanization, has substantially increased local surface air temperatures in many regions. This study aims to quantify the impact of land use and land cover change (LUCC) on surface air temperature trends in the South Central Coast region of Vietnam. Monthly mean datasets covering the past 26 years were used, including the Normalized Difference Vegetation Index (NDVI), land surface temperature (LST), and 2 m air temperature (T2m). Statistical analyses and artificial neural network (ANN) modeling were employed. The main explanatory variables included the mean values and temporal trends of NDVI and LST extracted from buffer zones surrounding meteorological stations. The results indicate that the influence of LUCC T2m is most pronounced during the warm season (April–August). Analyses for this period show that the selected remote sensing variables exhibit the strongest relationships with T2m when extracted within buffer radii of 2–8 km, while the prevailing wind direction has no significant influence on temperature trends. After selecting the optimal predictors, the ANN model successfully reproduced the observed temperature trends with high reliability. Relative contribution analysis showed that the NDVI trend and mean NDVI accounted for approximately 65% and 23% of the model performance, respectively, demonstrating that NDVI effectively captures the influence of LUCC on T2m. A scenario assuming no land use change, represented by zero trends in the explanatory variables, produced smaller and more spatially uniform temperature increases among stations, reflecting the background warming associated with climate change. The proposed framework provides a practical approach for assessing the environmental impacts of LUCC and for estimating its contribution to observed temperature trends.

Dak Nong Province is located in the Asian tropical monsoon region, where vegetation is highly vulnerable during the dry season due to elevated temperatures and limited precipitation. In addition to climate change, rapid population growth further intensifies pressures on vegetation. This study aims to quantify the relative contributions of climate change and human activities to trends in vegetation types during the dry season in this regions and to analyze future trends. The normalized difference vegetation index (NDVI), together with temperature and precipitation data obtained from meteorological stations, were used in this study. These data were used in monthly average form, from 2000 to 2024. The multiple regression residual analysis method was employed to quantify the relative contributions of climate change and human activities to NDVI variations. Trend detection was subsequently conducted using the Mann–Kendall test and Sen’s slope estimator, and the Hurst index was applied to project future NDVI trends. The results indicate that human activities are the primary driver of degradation across all vegetation types in the study area. The most pronounced degradation was observed in perennial agriculture and paddy rice areas, where approximately 75% of the area exhibited either extremely significant or significant degradation. Climate change exerts a pronounced negative impact on production forests and annual crops, with approximately 40% of the area classified as experiencing extremely significant degradation. In contrast, irrigated crops such as perennial agriculture and paddy rice show significant improvement. These findings indicate that when crop water requirements are not adequately met, increasing temperatures are associated with a decline in NDVI, and vice versa. The Hurst exponent analysis indicates that NDVI will continue to decline significantly in the future, with up to 58% of the study area classified as significant decrease and consistent, primarily driven by human activities.

This study examines the interaction between river discharge and satellite-derived vegetation indices to construct discharge prediction variables for an artificial neural network model. The study area is the Srepok River Basin, located in a tropical monsoon region characterized by a long dry season and frequent droughts that severely affect agricultural production, making early discharge forecasting essential. The vegetation indices from remote sensing used in the analysis include the Vegetation Condition Index (VCI) and the Temperature Condition Index (TCI). Monthly averaged data from 2000 to 2023 were used in the analysis. The results reveal a clear interaction between river discharge and vegetation condition, as indicated by remote sensing–derived indices. Compared with VCI, TCI more effectively captures this relationship. River discharge in the dry season and early rainy season exhibits a strong relationship with the TCI of preceding months. Autocorrelation analysis demonstrated that historical river discharge and antecedent TCI values are effective predictors of river discharge from the dry season to the onset of the rainy season. The model results further indicate that river discharge during February–May can be forecast with lead times ranging from 1 to 3 months. For the four gauging stations, the NSE values for 1–3-month lead time forecasts ranged from 0.80–0.86, 0.77–0.83, and 0.60–0.73, respectively, with corresponding MAPE values of 13.2–16.3%, 14.9–19.4%, and 18.4–25.8%. The results indicate that incorporating TCI significantly enhances forecast performance during the late dry season and early rainy season.

Drought has a serious impact on household income in the Vietnamese Mekong Delta. To improve the effectiveness of drought monitoring, it is necessary to analyze the impact of drought by space, time and income source, and income quintile. The data used in the study are rainfall at weather stations, average income per capita by income quintile, by income source and by province. The methods used in the study were analysis of income differences between dry and wet conditions, correlation between income and drought index, and clustering. Compared to using the correlation coefficient, using the income difference between dry and wet conditions provides a clearer picture of the time when drought has a strong impact on income. When drought occurs during the period from the end of the dry season to the beginning of the rainy season, it will affect all income quintiles and income sources, and the Standardized Precipitation Index with a 3-month time scale (SPI3) and taken in April can be used to early assess the effects of drought on income of the year. The lowest quintile and farm income sources are most vulnerable to drought, and SPI7 taken in August is the most appropriate choice to assess the impact of drought. Compared to wet years, dry years can reduce the income of these groups by about 15% on average. In addition, the study results also show that the impact of drought depends on the natural and social characteristics of each province. Provinces with poor irrigation water conditions, low urbanization rate and low urbanization growth rate are also provinces where the lowest quintile is vulnerable to drought.

Flow irregularities seriously affect agricultural production and ecosystems, so early forecasting of river discharge contributes to minimizing its impacts. This study analyzes the relationship between El Niño–Southern Oscillation (ENSO) and river discharge in the Srepok basin, thereby building a forecast model using the stepwise linear regression method. The Srepok Basin located in the Central Highlands of Vietnam, is an sub-basin of the Mekong River system. In this study, the dependent variable is monthly mean river discharge, and the independent variables are sea surface temperature (SST) in Niño regions, Southern Oscillation Index (SOI), river discharge in the previous month. These data cover the period from 1982 to 2022. Analysis results show that the independent variables have a good relationship with the dependent variable in the period from February to May and the dependent variable is taken from 1 to 6 months in advance. The evaluation results show that it is possible to forecast monthly average river discharge based on ENSO variables and river discharge in the previous month. With forecast periods from 1 to 6 months, the mean absolute percentage error ranges from 17.5% to 27.4% and the Nash-Sutcliffe efficiency ranges from 0.70 to 0.85. Compared to results from other reports, the forecast quality has improved. ENSO variables participating in forecast models only include SOI and SST in Niño 4 regions with time scale from 3 to 4 months. These are also the variables that have the best relationship with river discharge. The relative contribution of these variables to the forecasting equation is from 25% to 49%.

This study developed machine learning models to predict the Vegetation Health Index (VHI) using predictors derived from the Standardized Streamflow Index (SSI), Standardized Precipitation Index (SPI), and lagged VHI values. Three machine learning approaches were evaluated: Stepwise Quadratic...

The study aimed to forecast early the vegetation health index (VHI) in the Srepok river basin and evaluate the contribution of drought indices to the forecast accuracy. Stepwise Multiple Linear Regression (SMLR) is used to build forecast models. The model input variables include the Standardized Precipitation Index (SPI), Standardized Streamflow Index (SSI), and VHI in the previous period. The analysis shows that VHI during the dry and early wet seasons is strongly dependent on rainfall and streamflow at the end of the previous wet season. Vegetation shows high sensitivity to drought indices at the end of the dry season and the beginning of the wet season, when streamflow is at its lowest. The evaluation results show that VHI can be forecasted in the dry and early rainy season months with a 3-month lead time. The contribution of the variables to the forecast quality depends on the forecast time. With a 1-month forecast, VHI is dominant and from 2 to 3 months it is replaced by SPI and SSI. The t-Test shows that the forecast accuracy is higher for agricultural crops than for forests. The study provides a useful tool for drought monitoring and early warning in agricultural management in this basin.

Monitoring and predicting vegetation health are essential for agricultural activities and food security. This study aimed to select a model and evaluate the factors contributing to predicting the vegetation health index (VHI) in the Dak Nong Province, Vietnam. Machine learning algorithms were evaluated, including multiple linear regression, xGBoost, and artificial neural networks (ANN). The input variables of the models included the standardized precipitation evapotranspiration index (SPEI), soil moisture (SM), and VHI in the previous periods. Research results showed that the ANN model gave the best prediction results. The accuracy of prediction results depended on the season of the year, in which the dry season gave a result with high accuracy. The results also indicated that SM from one to two previous months, SPEI1 from one to three previous months, SPEI3 and SPEI5 from three to six previous months, and VHI from one previous month contributed mainly to the prediction model. The relative contribution of SM and SPEI ranged from 42% to 52% in the last 4 months of the dry season. In addition, land use type also affected prediction quality.

Drought has major impacts on agriculture, society, and ecosystems, so early prediction of drought plays an important role in mitigating its impacts. This study investigates the relationship between the Standardized Precipitation Index (SPI) in the Mekong Delta and global sea surface temperature (SST) in order to find potential variables for improving SPI forecast quality. The method used in determining potential predictors is based on the analysis of multiple correlation coefficients. Based on these potential predictors, SPI is predicted by stepwise regression along with the application of Leave-one-out cross-validation technique. The data used in this study is the rainfall of 15 stations in the Vietnamese Mekong Delta and the global SST from 1977 to 2020. Research results show that there is a pair of variables that have the best relationship with SPI in the study area, they are SST on Niño 3.4 region and SST in the region with latitude from 13 °N to 23 °N and longitude from 116 °E to 126 °E. When the forecast term is from 1 to 2 months, using this pair of variables gives better forecast quality than using only the predictors from the Niño indices.

This study aims to evaluate the effects of natural and human conditions on vegetation covers using VCI and TCI indices (the satellite-based Vegetation Health Indices (VHIs)) in Dak Nong province. Factors affecting the VHIs included in the analysis involve land use, soil, population, topography, distance to roads and surface water. The data analysis period is the dry season from 2000 to 2020. The trend of the VHIs’ change in this study is analyzed using Sen’s method with monitoring data from Modis. The effects of factors affecting the VHIs are based on logistic regression and discriminant analysis. The analysis results show that the VHIs are clear and show both increasing and decreasing trends. Based on logistic regression analysis, the influence of land use types on the trend of the VHIs in the direction of increasing from negative to positive will be from PdF, UnL, AnC, SpF, PtF, PeA and then to PdR. Corresponding to the soil will be from ACa, FRp, FRx, FRr, ACh, LVx, FLg and then to LVg. Based on the discriminant analysis method, it was found that there are only four primary factors affecting the trend of the VHIs in order of decreasing level of closure: population density, land use, soil and population growth rate and to the road. These results show that in places where labour resources are available, plants are interested in investment due to high profits, nutrient-rich soil and convenience for plant care; the VHIs tend to increase and vice versa. Compared with VCI, the trend of TCI tends to be sloping negative and more pessimistic. Through the coefficients of the logistic regression equation and the difference function, the TCI is more sensitive than the VCI when the independent variables change, especially for changes in population density and land use. Thus, TCI can be considered the preferred option for assessing vegetation health trends in the context of climate change.