Land cover and land use change related to shrimp farming in coastal areas of Quang Ninh,Vietnam using remotely sensed data

Rapid development of shrimp farming may lead to unrecognized and undesirable changes of land cover/land use patterns in coastal areas. Of special concern is the loss of mangrove forest in coastal areas such as Quang Ninh, Vietnam, which is adjacent to the World Heritage-listed Ha Long Bay. Understanding the status and changes of land cover/land use for coastal shrimp farms and mangrove forests can support environmental protection and decision-making for sustainable development in coastal areas. Within this context, this paper uses the 1999/2001 Landsat ETM+ and the 2008 ALOS AVNIR-2 imagery to investigate the contraction and expansion of shrimp farms and mangrove forests in coastal areas of Ha Long and Mong Cai, which now have a high concentration of intensive and semi-intensive shrimp farms. Images were separately analyzed and classified before using post-classification comparisons to detect land cover/land use changes in the study area. The results of this study found that the area of mangrove forest has been reduced by an estimated 927.5 ha in Ha Long and 1,144.4 ha in Mong Cai, while shrimp farming areas increased by an estimated 1,195.9 and 1,702.5 ha, respectively, over the same period. The majority of shrimp farms in Mong Cai were established at the expense of mangrove forest (49.4 %) while shrimp farms in Ha Long were mainly constructed on areas previously occupied by bare ground (46.5 %) and a significant proportion also replaced mangroves (23.9 %). The remarkable rate of mangrove loss and shrimp farming expansion detected in this study, over a relatively short time scale indicate that greater awareness of environmental impacts of shrimp farm expansion is required if this industry is to be sustainable, the important estuarine and coastal marine ecosystems are to be protected over the long term, and the capturing and storing of carbon in mangrove systems are to be enhanced for global climate change mitigation and for use as carbon offsets.     

Influence of synoptic processes on the vietnamese current (the South China Sea) Dynamics during the Winter–Summer 1999 transition period

Demonstrated is an influence of synoptic processes on the seasonal dynamics of the Vietnamese Current in the South China Sea varying its direction under the influence of the monsoon. The spring season of 1999 is used as an example of the transition from the winter to summer. In winter, under the influence of the northeastern monsoon, the current is directed from north to south and in the summer, at the southwestern monsoon, in the opposite direction. In the spring, two zones of different water modification are formed: an impact is observed of both the leaving winter monsoon and the coming summer monsoon. Considered is an atmospheric process of low-gradient field type, when the pressure field is characterized by the low pressure gradient over the whole South China Sea. It is revealed that the Vietnamese Current moves in the summer regime (from south to north) in the northern and southern parts and keeps the winter regime (from north to south) in the central part.     

Origin of aragonite in a continental saline seep,north Queensland

Aragonite, low‐magnesian calcite, gypsum and halite were identified by X‐ray diffraction and electron microbeam techniques in mineral precipitates near a salt seep 50 km southwest of Charters Towers in north Queensland. The chemistry of water from the creek and from the groundwater at the salt seep shows that Mg:Ca ratios are greater than or equal to 1.5 throughout the year. The formation of halite and gypsum is due to evaporative concentration of the water at the seep and that of the carbonates, in particular aragonite, is probably due to a combination of evaporation and photosynthetic activity by diatoms.     

Hyper-parameter optimization of gradient boosters for flood susceptibility analysis

Properly choosing hyper-parameters improves machine learning models' performance and reduces training time and resource requirements. In this study, we investigated the uses of the Bayesian optimization algorithm for hyper-parameter searches of two classifiers, namely LightGBM and XGBoost. The models were verified with a dataset from Vietnam, including historical flood locations from satellite images and survey data, and 11 features from three groups, namely physical, hydrological, and human-related factors. The models' performance was evaluated using Area under Receiver Operating Characteristic curves (AUC-ROC). Several strategies were applied to avoid over-fitting, and the results show that two tuned Gradient boosters reached considerably high AUC values (approximately 0.98) compared with the previous study with a similar dataset. The model interpretation was also implemented using the Shapley (SHAP) values to understand better how models work and the interactions between features. The search for optimal hyper-parameters is worth investigating in the future, particularly when there is growing work for novel optimization algorithms. The verification of such an approach is scientifically sound, and the models can be used as an alternative solution for natural hazard analysis in countries prone to hazards.     

Introduction to the China-Vietnam Cooperation Project: A Comparative Study of the Holocene Sedimentary Evolution of the Yangtze and Red River Deltas

Both China and Vietnam confront the challenges of natural geohazards and environmental changes in their deltas and coastal zones due to rapid urbanization, economic development, and the impacts of global climate change. China and Vietnam initiated a comparative study of the Holocene sedimentary evolution of the Yangtze River Delta(YRD) and Red River Delta(RRD) for the period 2015–2018 in order to improve the understanding of the two delta evolution histories in the Holocene. Previous investigative data of the two rivers, onshore delta plains, and offshore subaqueous deltas have been explored and reinterpreted. New data gleaned from boreholes, piston cores, shallow seismic and hydrodynamic sources have been collected from the offshore YRD and the East China Sea inner shelf, and surface sediments and short cores have been collected from the RRD near-shore areas. Six focal areas of the joint project have been defined for comparative studies of the two deltas, including morphological development, sequential stratigraphy, coastline shifting, sedimentary characteristics, sedimentary dynamics, and correlation with anthropogenic global climate change. The results of these study areas are presented herein. The joint project also includes cooperative capacity building; exchanges of young scientists have been organized during the project period, and hands-on training in laboratory geochemical analysis, numerical modeling, and seismic data processing and interpretation have been provided by China and its Vietnamese geoscientist partners. Joint field excursions were organized to the upstream of the Yangtze and Red Rivers in Yunan Province, China, all the way downstream along the Vietnamese portion of the Red River. These joint studies have, over the past three years, improved understanding of the evolutionary history of these two major rivers and their mechanisms of source to sink. Joint project results of these two major deltas are not limited to the geosciences; the cooperative mechanical and operational experiences have been helpful for future cooperation in the field of marine geoscience between China and Vietnam, as well for cooperative activities with other ASEAN member countries.     

A novel fuzzy <Emphasis Type="Italic">K</Emphasis>-nearest neighbor inference model with differential evolution for spatial prediction of rainfall-induced shallow landslides in a tropical hilly area using GIS

This research represents a novel soft computing approach that combines the fuzzy k-nearest neighbor algorithm (fuzzy k-NN) and the differential evolution (DE) optimization for spatial prediction of rainfall-induced shallow landslides at a tropical hilly area of Quy Hop, Vietnam. According to current literature, the fuzzy k-NN and the DE optimization are current state-of-the-art techniques in data mining that have not been used for prediction of landslide. First, a spatial database was constructed, including 129 landslide locations and 12 influencing factors, i.e., slope, slope length, aspect, curvature, valley depth, stream power index (SPI), sediment transport index (STI), topographic ruggedness index (TRI), topographic wetness index (TWI), Normalized Difference Vegetation Index (NDVI), lithology, and soil type. Second, 70 % landslide locations were randomly generated for building the landslide model whereas the remaining 30 % landslide locations was for validating the model. Third, to construct the landslide model, the DE optimization was used to search the optimal values for fuzzy strength (fs) and number of nearest neighbors (k) that are the two required parameters for the fuzzy k-NN. Then, the training process was performed to obtain the fuzzy k-NN model. Value of membership degree of the landslide class for each pixel was extracted to be used as landslide susceptibility index. Finally, the performance and prediction capability of the landslide model were assessed using classification accuracy, the area under the ROC curve (AUC), kappa statistics, and other evaluation metrics. The result shows that the fuzzy k-NN model has high performance in the training dataset (AUC?=?0.944) and validation dataset (AUC?=?0.841). The result was compared with those obtained from benchmark methods, support vector machines and J48 decision trees. Overall, the fuzzy k-NN model performs better than the support vector machines and the J48 decision trees models. Therefore, we conclude that the fuzzy k-NN model is a promising prediction tool that should be used for susceptibility mapping in landslide-prone areas.     

Bagging based Support Vector Machines for spatial prediction of landslides

A hybrid Bagging based Support Vector Machines (BSVM) method, which is a combination of Bagging Ensemble and Support Vector Machine (SVM) classifier, was proposed for the spatial prediction of landslides at the district of Mu Cang Chai, Viet Nam. In the present study, 248 past landslides and fifteen geo-environmental factors (curvature, elevation, distance to rivers, slope, aspect, river density, plan curvature, distance to faults, profile curvature, fault density, lithology, distance to roads, rainfall, land use, and road density) were considered for the model construction. Different evaluation criteria were applied to validate the proposed hybrid model such as statistical index-based methods and area under the receiver operating characteristic curve (AUC). The single SVM and the Naïve Bayes Trees (NBT) models were selected for comparison. Based on the AUC values, the proposed hybrid model BSVM (0.812) outperformed the SVM (0.804) and NBT (0.8) models. Thus, the BSVM is a promising and better method for landslide prediction.     

Apatite Reference Materials for SIMS Microanalysis of Isotopes and Trace Elements

Twelve apatite samples have been tested as secondary ion mass spectrometry (SIMS) reference materials. Laser ablation-inductively coupled plasma-mass spectrometry (LA-ICP-MS) analysis shows that the SLAP, NUAN and GR40 apatite gems are internally homogeneous, with most trace element mass fractions having 2 standard deviations (2s) ≤ 2.0%. BR2, BR5, OL2, AFG2 and AFB1, which have U > 63 μg g^-1, ²⁰⁶Pb/²⁰⁴Pb > 283, and homogeneous SIMS U-Pb data, have respective isotope dilution thermal ionisation mass spectrometry (ID-TIMS) ages of 2053.83 ± 0.21 Ma, 2040.34 ± 0.09 Ma, 868.87 ± 0.25 Ma, 478.71 ± 0.22 Ma and 473.25 ± 0.09 Ma. Minor U-Pb heterogeneity exists and accurate SIMS results require correction with the 3D Concordia-constrained common Pb composition. Among the studied samples, AFG2 and BR5 are the most homogeneous U-Pb reference materials. The SIMS sulfur isotopic compositions of eight of the apatites shows they are homogeneous, with 2s for both 10³δ³⁴S and 10³δ³³S < 0.55‰. One apatite, BR96, has Δ³³S = -0.36 ± 0.2‰. The apatite samples have ID-TIMS ⁸⁷Sr/⁸⁶Sr between 0.704214 ± 0.000030 and 0.723134 ± 0.000035.     

A Novel Hunger Games Search Optimization-Based Artificial Neural Network for Predicting Ground Vibration Intensity Induced by Mine Blasting

Innovation efforts in developing soft computing models (SCMs) of researchers and scholars are significant in recent years, especially for problems in the mining industry. So far, many SCMs have been proposed and applied to practical engineering to predict ground vibration intensity (BIGV) induced by mine blasting with high accuracy and reliability. These models significantly contributed to mitigate the adverse effects of blasting operations in mines. Despite the fact that many SCMs have been introduced with promising results, but ambitious goals of researchers are still novel SCMs with the accuracy improved. They aim to prevent the damages caused by blasting operations to the surrounding environment. This study, therefore, proposed a novel SCM based on a robust meta-heuristic algorithm, namely Hunger Games Search (HGS) and artificial neural network (ANN), abbreviated as HGS–ANN model, for predicting BIGV. Three benchmark models based on three other meta-heuristic algorithms (i.e., particle swarm optimization (PSO), firefly algorithm (FFA), and grasshopper optimization algorithm (GOA)) and ANN, named as PSO–ANN, FFA–ANN, and GOA–ANN, were also examined to have a comprehensive evaluation of the HGS–ANN model. A set of data with 252 blasting operations was collected to evaluate the effects of BIGV through the mentioned models. The data were then preprocessed and normalized before splitting into individual parts for training and validating the models. In the training phase, the HGS algorithm with the optimal parameters was fine-tuned to train the ANN model to optimize the ANN model's weights. Based on the statistical criteria, the HGS–ANN model showed its best performance with an MAE of 1.153, RMSE of 1.761, R² of 0.922, and MAPE of 0.156, followed by the GOA–ANN, FFA–ANN and PSO–ANN models with the lower performances (i.e., MAE?=?1.186, 1.528, 1.505; RMSE?=?1.772, 2.085, 2.153; R²?=?0.921, 0.899, 0.893; MAPE?=?0.231, 0.215, 0.225, respectively). Based on the outstanding performance, the HGS–ANN model should be applied broadly and across a swath of open-pit mines to predict BIGV, aiming to optimize blast patterns and reduce the environmental effects.