Flood-prone area mapping using machine learning techniques: a case study of Quang Binh province,Vietnam

Natural Hazards - Vietnam’s central coastal region is the most vulnerable and always at flood risk, severely affecting people’s livelihoods and socio-economic development. In...     

Cenozoic basement structure of the South China Sea and adjacent areas by modeling and interpreting gravity data

The South China Sea and adjacent areas is a large region with diversely complicated geological conditions. In spite of investigations carried out over the past many years, the marine geological structure in many places has remained poorly understood because of the deficient data, a thick seawater layer as well as of the sensitive areas among the countries in the region. In this paper, the authors study and apply a model-based methodology of the modeling and interpretation of the newest gravity data and others, which are 3D modeling, frequency filtering, horizontal gravity gradient and maximum horizontal gravity gradient, in order to determine clearly the basement structure. The basement features such as the main faults systems, uplift-depression zones and seafloor spreading axis, oceanic boundary in the region have been defined. The achieved results are checked by the seismic data available for the region. From the studied results, the authors have brought out some initial remarks on the structure and form of the basement in the South China Sea and adjacent areas.     

Spatio-temporal analysis of recent groundwater-level trends in the Red River Delta, Vietnam

A groundwater-monitoring network has been in operation in the Red River Delta, Vietnam, since 1995. Trends in groundwater level (1995?C2009) in 57 wells in the Holocene unconfined aquifer and 63 wells in the Pleistocene confined aquifer were determined by applying the non-parametric Mann-Kendall trend test and Sen??s slope estimator. At each well, 17 time series (e.g. annual, seasonal, monthly), computed from the original data, were analyzed. Analysis of the annual groundwater-level means revealed that 35?% of the wells in the unconfined aquifer showed downward trends, while about 21?% showed upward trends. On the other hand, confined-aquifer groundwater levels experienced downward trends in almost all locations. Spatial distributions of trends indicated that the strongly declining trends (>0.3?m/year) were mainly found in urban areas around Hanoi where there is intensive abstraction of groundwater. Although the trend results for most of the 17 time series at a given well were quite similar, different trend patterns were detected in several. The findings reflect unsustainable groundwater development and the importance of maintaining groundwater monitoring and a database in the Delta, particularly in urban areas.     

Regional prediction of landslide hazard using probability analysis of intense rainfall in the Hoa Binh province, Vietnam

The main objective of this study is to assess regional landslide hazards in the Hoa Binh province of Vietnam. A landslide inventory map was constructed from various sources with data mainly for a period of 21 years from 1990 to 2010. The historic inventory of these failures shows that rainfall is the main triggering factor in this region. The probability of the occurrence of episodes of rainfall and the rainfall threshold were deduced from records of rainfall for the aforementioned period. The rainfall threshold model was generated based on daily and cumulative values of antecedent rainfall of the landslide events. The result shows that 15-day antecedent rainfall gives the best fit for the existing landslides in the inventory. The rainfall threshold model was validated using the rainfall and landslide events that occurred in 2010 that were not considered in building the threshold model. The result was used for estimating temporal probability of a landslide to occur using a Poisson probability model. Prior to this work, five landslide susceptibility maps were constructed for the study area using support vector machines, logistic regression, evidential belief functions, Bayesian-regularized neural networks, and neuro-fuzzy models. These susceptibility maps provide information on the spatial prediction probability of landslide occurrence in the area. Finally, landslide hazard maps were generated by integrating the spatial and the temporal probability of landslide. A total of 15 specific landslide hazard maps were generated considering three time periods of 1, 3, and 5 years.     

An Application of HFE-D for Evaluating Sea Water Intrusion in Coastal Aquifers of Southern Vietnam

The coastal aquifers and inland waters of the Long Xuyen Quadrangle and Ca Mau Peninsula of southern Vietnam have been significantly impacted by sea water intrusion (SI) as a result of recent anthropogenic activities. This study identified the evolution and spatial distribution of hydrochemical conditions in coastal aquifers at this region using Hydrochemical Facies Evolution Diagram (HFE-D) and Geographical Information System mapping. Hydraulic heads and water chemistry were measured at 31 observation wells in four layered aquifers during dry and rainy seasons in early (2005), and more recent (2016), stages of agricultural development. Hydrochemical facies associated with intrusion or freshening stages were mapped in each aquifer after assigning mixing index values to each facies. The position of groundwater freshening and SI phases differed in Holocene, Upper Pleistocene, Middle Pleistocene, and Lower Pleistocene aquifers. The geographic position of freshening and intrusion fronts differ in dry and rainy seasons, and shifted after 11 years of groundwater abstraction in all four aquifers. The spatial and temporal differences in hydrochemical facies distributions according to HFE-D reflect the relative impact of SI in the four aquifers. The study results provide a better understanding of the evolution of groundwater quality associated with SI in a peninsular coastal aquifer system, and highlight the need for improving groundwater quality and management in similar coastal regions.     

Sources of sedimentary PAHs in tropical Asian waters: Differentiation between pyrogenic and petrogenic sources by alkyl homolog abundance

We collected surface sediment samples from 174 locations in India, Indonesia, Malaysia, Thailand, Vietnam, Cambodia, Laos, and the Philippines and analyzed them for polycyclic aromatic hydrocarbons (PAHs) and hopanes. PAHs were widely distributed in the sediments, with comparatively higher concentrations in urban areas (∑PAHs: ∼1000 to ∼100 000 ng/g-dry) than in rural areas (∼10 to ∼100 g-dry), indicating large sources of PAHs in urban areas. To distinguish petrogenic and pyrogenic sources of PAHs, we calculated the ratios of alkyl PAHs to parent PAHs: methylphenanthrenes to phenanthrene (MP/P), methylpyrenes + methylfluoranthenes to pyrene + fluoranthene (MPy/Py), and methylchrysenes + methylbenz[a]anthracenes to chrysene + benz[a]anthracene (MC/C). Analysis of source materials (crude oil, automobile exhaust, and coal and wood combustion products) gave thresholds of MP/P = 0.4, MPy/Py = 0.5, and MC/C = 1.0 for exclusive combustion origin. All the combustion product samples had the ratios of alkyl PAHs to parent PAHs below these threshold values. Contributions of petrogenic and pyrogenic sources to the sedimentary PAHs were uneven among the homologs: the phenanthrene series had a greater petrogenic contribution, whereas the chrysene series had a greater pyrogenic contribution. All the Indian sediments showed a strong pyrogenic signature with MP/P ≈ 0.5, MPy/Py ≈ 0.1, and MC/C ≈ 0.2, together with depletion of hopanes indicating intensive inputs of combustion products of coal and/or wood, probably due to the heavy dependence on these fuels as sources of energy. In contrast, sedimentary PAHs from all other tropical Asian cities were abundant in alkylated PAHs with MP/P ≈ 1-4, MPy/Py ≈ 0.3-1, and MC/C ≈ 0.2-1.0, suggesting a ubiquitous input of petrogenic PAHs. Petrogenic contributions to PAH homologs varied among the countries: largest in Malaysia whereas inferior in Laos. The higher abundance of alkylated PAHs together with constant hopane profiles suggests widespread inputs of automobile-derived petrogenic PAHs to Asian waters.     

Prediction of Rock Size Distribution in Mine Bench Blasting Using a Novel Ant Colony Optimization-Based Boosted Regression Tree Technique

Natural Resources Research - In this paper, we used artificial intelligence (AI) techniques to investigate the relation between the rock size distribution (RSD) and blasting parameters for rock...     

Flash flood susceptibility mapping using a novel deep learning model based on deep belief network,back propagation and genetic algorithm

Flash floods are responsible for loss of life and considerable property damage in many countries.Flood susceptibility maps contribute to flood risk reduction in areas that are prone to this hazard if appropriately used by landuse planners and emergency managers.The main objective of this study is to prepare an accurate flood susceptibility map for the Haraz watershed in Iran using a novel modeling approach(DBPGA) based on Deep Belief Network(DBN) with Back Propagation(BP) algorithm optimized by the Genetic Algorithm(GA).For this task, a database comprising ten conditioning factors and 194 flood locations was created using the One-R Attribute Evaluation(ORAE) technique.Various well-known machine learning and optimization algorithms were used as benchmarks to compare the prediction accuracy of the proposed model.Statistical metrics include sensitivity,specificity accuracy, root mean square error(RMSE), and area under the receiver operatic characteristic curve(AUC) were used to assess the validity of the proposed model.The result shows that the proposed model has the highest goodness-of-fit(AUC = 0.989) and prediction accuracy(AUC = 0.985), and based on the validation dataset it outperforms benchmark models including LR(0.885), LMT(0.934), BLR(0.936), ADT(0.976), NBT(0.974), REPTree(0.811), ANFIS-BAT(0.944), ANFIS-CA(0.921), ANFIS-IWO(0.939), ANFIS-ICA(0.947), and ANFIS-FA(0.917).We conclude that the DBPGA model is an excellent alternative tool for predicting flash flood susceptibility for other regions prone to flash floods.     

An improved SPH method for saturated soils and its application to investigate the mechanisms of embankment failure: Case of hydrostatic pore‐water pressure

The method of smoothed particle hydrodynamics (SPH) has recently been applied to computational geomechanics and has been shown to be a powerful alternative to the standard numerical method, that is, the finite element method, for handling large deformation and post‐failure of geomaterials. However, very few studies apply the SPH method to model saturated or submerged soil problems. Our recent studies of this matter revealed that significant errors may be made if the gradient of the pore‐water pressure is handled using the standard SPH formulation. To overcome this problem and to enhance the SPH applications to computational geomechanics, this article proposes a general SPH formulation, which can be applied straightforwardly to dry and saturated soils. For simplicity, the current work assumes hydrostatic pore‐water pressure. It is shown that the proposed formulation can remove the numerical error mentioned earlier. Moreover, this formulation automatically satisfies the dynamic boundary conditions at a submerged ground surface, thereby saving computational cost. Discussions on the applications of the standard and new SPH formulations are also given through some numerical tests. Furthermore, techniques to obtain the correct SPH solution are also proposed and discussed throughout. As an application of the proposed method, the effect of the dilatancy angle on the failure mechanism of a two‐sided embankment subjected to a high groundwater table is presented and compared with that of other solutions. Finally, the proposed formulation can be considered a basic formulation for further developments of SPH for saturated soils. Copyright © 2011 John Wiley & Sons, Ltd.     

Predicting rock size distribution in mine blasting using various novel soft computing models based on meta-heuristics and machine learning algorithms

Blasting is well-known as an effective method for fragmenting or moving rock in open-pit mines. To evaluate the quality of blasting, the size of rock distribution is used as a critical criterion in blasting operations. A high percentage of oversized rocks generated by blasting operations can lead to economic and environmental damage. Therefore, this study proposed four novel intelligent models to predict the size of rock distribution in mine blasting in order to optimize blasting parameters, as well as the efficiency of blasting operation in open mines. Accordingly, a nature-inspired algorithm (i.e., firefly algorithm – FFA) and different machine learning algorithms (i.e., gradient boosting machine (GBM), support vector machine (SVM), Gaussian process (GP), and artificial neural network (ANN)) were combined for this aim, abbreviated as FFA-GBM, FFA-SVM, FFA-GP, and FFA-ANN, respectively. Subsequently, predicted results from the abovementioned models were compared with each other using three statistical indicators (e.g., mean absolute error, root-mean-squared error, and correlation coefficient) and color intensity method. For developing and simulating the size of rock in blasting operations, 136 blasting events with their images were collected and analyzed by the Split-Desktop software. In which, 111 events were randomly selected for the development and optimization of the models. Subsequently, the remaining 25 blasting events were applied to confirm the accuracy of the proposed models. Herein, blast design parameters were regarded as input variables to predict the size of rock in blasting operations. Finally, the obtained results revealed that the FFA is a robust optimization algorithm for estimating rock fragmentation in bench blasting. Among the models developed in this study, FFA-GBM provided the highest accuracy in predicting the size of fragmented rocks. The other techniques (i.e., FFA-SVM, FFA-GP, and FFA-ANN) yielded lower computational stability and efficiency. Hence, the FFA-GBM model can be used as a powerful and precise soft computing tool that can be applied to practical engineering cases aiming to improve the quality of blasting and rock fragmentation.