Vietnam Journal of Earth Sciences

Establishment of climate and weather catastrophe maps for prevention and reduction of hazard

To apply information-mathematic models in order to solve to explore solid minerals for weathered clay deposit

Some features of biocllmatic conelitions in NorthernPart of Gentral Region of Viet Nem based onanalyzing of its climatodiagrams

The study examined the performance of six regional climate experiments conducted under the framework of the Southeast Asia Regional Climate Downscaling/Coordinated Regional Climate Downscaling Experiment-Southeast Asia (SEACLID/CORDEX-SEA) project and their ensemble product (ENS) in simulating temperature at 2 m (T2m) and rainfall (R) in seven climatic sub-regions of Vietnam. The six experiments were named following the names of their driving Global Climate Models (GCMs), i.e., CNRM, CSIRO, ECEA, GFDL, HADG and MPI. The observation data for the period 1986–2005 from 66 stations in Vietnam were used to compare with the model outputs. Results showed that cold biases were prominent among the experiments and ENS well reproduced the seasonal cycle of temperature in the Northeast, Red River Delta, North Central and Central Highlands regions. For rainfall, all the experiments showed wet biases and CSIRO exhibited the best. A scoring system was elaborated to objectively rank the performance of the experiments and the ENS experiment was reported to be the best.

The paper deals with the concepts and research experiences for resources and environmental assessment and building a capacity for establishing sustainable ecological economic systems. For the past several decades, some urgent problems have been emerged in the Central Highland region of Vietnam, such as poverty, conflicts between economic development and environment protection, the raising of natural hazards and its effects, and etc. It is therefore sustainable development is considered as the priority goal for both of this region and its four typical sub-regions,including plateaus of Da Lat, Pleiku and Dak Nong, and Cheo Reo - Phu Tuc lowland. For this study, we proposed some specific economic development models and ecological economic ones as well as followings: model for local key industrial production; Highlands-specific model for agro-forestry production and business; model for tourism and servicedevelopment; model for sustainable agriculture business; model for sustainable development for the frontier post and borderland corridor economics for Central Highlands and some its key geographic areas. As the main result of this study, these specific types of ecological economic system which are proposed for future applying in this region could be played its roles as driving forces for promoting the sustainable development of this region in the new tendency.

With the rapid advancement of technology, monitoring forest cover changes has become increasingly quantifiable through various techniques and methods. In this study, we developed a procedure that utilizes the Deep Neuron Network (DNN) model and the Geographic Information Systems (GIS) based on high-resolution imagery captured at different time points to create forest cover change maps in Nui Luot, Chuong My, Hanoi. Two RGB (Red-Green-Blue) spectral images were captured by Unmanned Aerial Vehicle (UAV) at two different time points (pre-scene and post-scene) and used to extract information for the DNN model to produce land cover maps for these two time points. The land cover classification was divided into four classes: (1) Trees, (2) Vacant, (3) Built area and others, and (4) Water surface. Combined with GIS analysis, the forest cover change maps were developed to quantify detailed increases or losses in forest cover based on the "Trees" class. The model's accuracy was evaluated using parameters such as the area Under the ROC Curve (AUC), Accuracy (ACC), Precision, Recall, F1-Score, Kappa, and Root Mean Square Error (RMSE). The analysis results indicate that from January 31, 2023, to October 20, 2023, the forest cover in the study area decreased by 0.53%. The accuracy metrics for the pre-change scene were: average AUC = 0.922, ACC = 76.86%, average Precision = 0.743, average Recall = 0.73, average F1-Score = 0.723, Kappa = 0.692, and RMSE = 0.297. For the post-change scene, the accuracy metrics were: average AUC = 0.954, ACC = 81.89%, average Precision = 0.823, average Recall = 0.815, average F1-Score = 0.818, Kappa = 0.758, and RMSE = 0.262. A deforestation scenario was constructed to evaluate the effectiveness of the DNN models in assessing and monitoring forest dynamics.

Flash floods continue to emerge as a serious and growing natural hazard for many communities worldwide, especially in areas affected by tropical storms. These floods damage critical infrastructure and severely strain economic resources, underscoring the urgent need for advanced flood prediction tools. This study presents an innovative integrated machine learning approach, BCMO-RF, which merges Balancing Composite Motion Optimization (BCMO) with Random Forest (RF) to map flash flood susceptibility. In the BCMO-RF approach, the RF algorithm is applied to develop the flash flood model, while BCMO is used to explore and optimize the model's parameters. The study concentrates on areas in Thanh Hoa Province, Vietnam, frequently impacted by flash floods. Accordingly, various geospatial data sources were utilized to compile a geodatabase comprising 2,540 flash flood locations and 12 influencing factors. The geodatabase served as the basis for training and validating the BCMO-RF model. Results show that the BCMO-RF model attained high prediction accuracy (93.7%), achieving a Kappa coefficient of 0.874 and an AUC score of 0.988, outperforming the Deep Learning model benchmark. The study finds that the BCMO-RF model is reliable for accurately mapping areas susceptible to flash floods.

Drought is one of the most pervasive and complex natural hazards, significantly impacting ecosystems, agriculture, and communities, particularly in Vietnam. The study constructed a hybrid model to explore the sensitivity of drought forecast over Vietnam, utilizing bias-corrected precipitation and temperature data from regional climate models, RegCM, and clWRF. The resulting 6-month scale Standardized Precipitation Evapotranspiration Index (SPEI-6), is then processed through two different multi-model ensemble approaches: a simple averaging method (ENS) and a more complex artificial neural network (CTL), forming the basis of our two experimental setups. CTL consistently outperformed ENS, demonstrating more substantial drought-predictive skills. CTL effectively captured the spatio-temporal distribution of SPEI-6, showing high accuracy at a 1-month lead time. Its performance is promising, particularly in regions with complex climate patterns like the Central of Vietnam (R4 and R5), though discrepancies in predicting SPEI-6 amplitudes become slightly evident at a 5-month lead time. The geographic extent analysis further supports CTL's strengths in short-term forecasting, highlighting its utility in early warning systems and immediate drought response planning. Nonetheless, the decrease in accuracy at extended lead times underscores the need for model refinement. The study contributes to the growing body of literature on ANN-based drought forecasting, emphasizing the potential and limitations of these models in the context of Vietnam.

Slope instability is a common geological hazard along mountainous roads in Vietnam, leading to significant damage to infrastructure, traffic disruptions, and loss of life. Predicting slope stability, typically quantified by the Factor of Safety (FS), is challenging due to the complex interactions between geotechnical, topographical, and environmental factors. This study aims to develop efficient and accurate models for predicting the FS of natural slopes using advanced machine learning techniques, including Gradient Boosting (GB), Support Vector Machine (SVM), Multi-layer Perceptron (MLP) Neural Networks, Random Forest (RF), and AdaBoost (AB). 371 slope stability cases were used to create a comprehensive database for model training. Both geotechnical and topographical parameters were considered in the FS prediction process. The performance and reliability of these models were evaluated using standard metrics such as R², MAE, and MSE. The results demonstrated that all models exhibited satisfactory prediction capabilities, with the optimized GB model achieving the highest accuracy (R² = 0.975, MAE = 0.079, and RMSE = 0.120). Additionally, SHAP analysis was employed to assess the importance of input variables in predicting the FS. The findings revealed that slope ratio (X1), slope height (X2), and the number of steeps (X3) were the most influential parameters in the FS prediction.

SUMMARYThe soil degaradation and desertification in South Central VietnamThe soil degaradation and desertification are affects resulting from the loss of the ecological balance by the natural processes and socio-economical activities in the arid, semi-arid and dry sub-humidareas. According the geo-synthetization, the soil degradation is a main cause leading to the desertification.In Central Southern of Vietnam, the condition of the soil originating (from Da Nang to Binh Thuan area) is belonged to the monsoon of the tropical climate with 6-9 dry months. Particularly, the NinhThuan - Binh Thuan area has 8-9 dry months that is identical to a semi-arid area, occupying ~45,000 km2. The structure of the soil layer is complicated with 10 groups, 20 types of the soil layer, morethan 65,000 ha of the mountain land, and 265,000 ha of the sand-dune and sand beach.The area has high potential of soil degradation and it is happening strongly after seasons. One of the main reason of the soil erosion is water current in the steep area, by winds in the coastal sandy area, laterization in the hill area, and salinization in the coastal area, etc... In this area, the average soil loss by the water current is ranging from 400-800 ton/ha per year, in the places this number is up to1,000 ton/ha per year. Consequently, 48 % of the area in the upper-land has thin soil layer below 30 cm and over 30 % of the area in the lowland has light mechanical components. Furthermore, it is leading to the low water - bearing capacity of the soil, as well as increasing of the evaporation rate, promoting desertification processes in these areas.According to the world’s classification, 4 types of desertification are presented in the Central Southern of Vietnam as followed :- Sandy desert : this type is occupy about of 260,000 ha, mainly locating in Binh Thuan, Ninh Thuan and Binh Dinh provinces ;- Rocky-stone desert : this type of desert has about of 100,000 ha, distributing in Quang Ngai, Binh Dinh, Khanh Hoa, Ninh Thuan and Binh Thuan provinces ;- Dust desert : the total area of this type of desert has about 290,000 ha, comprising infertile gray soil and erode soil with grave and stone. They are distributed along the foot of the Truong Son Mountain to the plain land near the coastal line, from Quang Ngaito Binh Thuan provinces;- Salt desert: It has about of 49,000 ha and concentrated in Ninh Thuan and Binh Thuan pro-vinces. The rule of the distribution of the desertification is increase from the North to the South and from the East to the West in the South Central Vietnam, so that, creating the two desert bands, one is near the coast and other is at the foot of the Truong Son mountain. The trend of the soil degradation and desertification is increasing and spreading out, requiring more attention in controlling, managing, as well as recovering.