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...     

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.     

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...     

Geological and geophysical studies of the Agoudal impact structure (Central High Atlas,Morocco): New evidence for crater size and age

Since the discovery of shatter cones (SCs) near the village of Agoudal (Morocco, Central High Atlas Mountains) in 2013, the absence of one or several associated circular structures led to speculation about the age of the impact event, the number, and the size of the impact crater or craters. Additional constraints on the crater size, age, and erosion rates are obtained here from geological, structural, and geophysical mapping and from cosmogenic nuclide data. Our geological maps of the Agoudal impact site at the scales of 1:30,000 (6 km²) and 1:15,000 (2.25 km²) include all known occurrences of SCs in target rocks, breccias, and vertical to overturned strata. Considering that strata surrounding the impact site are subhorizontal, we argue that disturbed strata are related to the impact event. Three types of breccias have been observed. Two of them (br1‐2 and br2) could be produced by erosion–sedimentation–consolidation processes, with no evidence for impact breccias, while breccia (br1) might be impact related. The most probable center of the structure is estimated at 31°59′13.73?N, 5°30′55.14?W using the concentric deviation method applied to the orientation of strata over the disturbed area. Despite the absence of a morphological expression, the ground magnetic and electromagnetic surveys reveal anomalies spatially associated with disturbed strata and SC occurrences. The geophysical data, the structural observations, and the area of occurrence of SCs in target rocks are all consistent with an original size of 1.4–4.2 km in diameter. Cosmogenic nuclide data (³⁶Cl) constrain the local erosion rates between 220 ± 22 m Ma^?1 and 430 ± 43 m Ma^?1. These erosion rates may remove the topographic expression of such a crater and its ejecta in a time period of about 0.3–1.9 Ma. This age is older than the Agoudal iron meteorite age (105 ± 40 kyr). This new age constraint excludes the possibility of a genetic relationship between the Agoudal iron meteorite fall and the formation of the Agoudal impact site. A chronolgy chart including the Atlas orogeny, the alternation of sedimentation and erosion periods, and the meteoritic impacts is presented based on all obtained and combined data.     

ALMA observations of the circumstellar envelope around EP Aqr

Atacama Large Millimetre/sub-millimetre Array(ALMA) observations of CO(1–0) and CO(2–1) emissions from the circumstellar envelope of the asymptotic giant branch(AGB) star EP Aqr have been made with four times better spatial resolution than previously available. They are analysed with emphasis on the de-projection in space of the effective emissivity and flux of matter using as input a prescribed configuration of the velocity field, assumed to be radial. The data are found to display an intrinsic axisymmetry with respect to an axis making a small angle with respect to the line of sight. A broad range of wind configurations, from prolate(bipolar) to oblate(equatorial) has been studied and found to be accompanied by significant equatorial emission. Qualitatively, the effective emissivity is enhanced near the equator to produce the central narrow component observed in the Doppler velocity spectra and its dependence on star latitude generally follows that of the wind velocity with the exception of an omni-present depression near the poles. In particular, large equatorial expansion velocities produce a flared disc or a ring of effective emissivity and mass loss. The effect on the determination of the orientation of the star axis of radial velocity gradients, and possibly competing rotation and expansion in the equatorial disc, is discussed. In general,the flux of matter is found to reach a broad maximum at distances of the order of 500 AU from the star.Arguments are given that may be used to favour one wind velocity distribution over another. As a result of the improved quality of the data, a deeper understanding of the constraints imposed on morphology and kinematics has been obtained.     

A study of coral reef resilience and implications of adaptive management and rehabilitation in Khanh Hoa Province, Vietnam

The Province of Khanh Hoa, Vietnam, is located in the western South China Sea and boasts a shoreline of 385 km and many islands. Previous studies have indicated the extreme diversity and abundance of coral reefs in its waters as compared with other coastal provinces of Vietnam. A study on the resilience of coral reefs against increased surface water temperature and anthropogenic impact is conducted at 19 reef sites in 2015. At each site, a series of parameters (e.g., coral covers, genus diversity, and coral recruitment, substratum heterogeneity, depth, water exchange level, and sediment deposit and water temperature) are measured quantitatively or semi-quantitatively. The measured data are rated based on the relationship between the parameter values and coral susceptibility; the consideration that reef health reflects the biological capability to adapt to environmental changes and the recruitment potential if bleached; and positive or negative influences of physical factors in the mitigation of thermal stress and protecting corals from bleaching. A cumulative analysis enables researchers to divide the studied reefs into four categories based on varying levels of reef health to support resilience, recovery, and vulnerability in the case of increased water temperature. Relevant management interventions for each category and other supporting activities are suggested to enhance management effectiveness and to plan the rehabilitation of coral reefs for biodiversity conservation and touristic development, taking into account the involvement of related stakeholders.     

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.     

Small-scale marine fisheries policy in Vietnam

Vietnam's marine fisheries are considered to be small scale and are concentrated in coastal near-shore waters. This has resulted in heavy pressure on near-shore fisheries resources. Near-shore fisheries are considered by fishers and the government to be over-exploited, causing hardship for many coastal communities. This paper reviews and analyzes changes in policy towards small-scale fisheries in Vietnam over the last two decades. The primary issues facing the small-scale fisheries in Vietnam are to restructure the near-shore fisheries and to address over-capacity. Recommended actions include improved fisheries statistics, resources for provincial fisheries staff, and a coordinated and integrated approach involving a mixed strategy of resource management; resource restoration; economic and community development; and new governance arrangements.     

Petroleum composition in the Cuu Long Basin (Mekong Basin) offshore southern Vietnam

The Cuu Long Basin (Mekong Basin) is a rift basin off southern Vietnam, and the most important petroleum producing basin in the country. However, information on petroleum type and characteristics has hitherto been largely unavailable to the public. This paper presents petroleum geochemical data on nine oil samples from four different producing fields in the Cuu Long Basin: the Dragon (Rong), Black Lion (Sutu-Den), Sunrise (Rang ?ong) and White Tiger (Bach Ho) Fields. The oils are highly paraffinic with bimodal normal alkane distributions and show moderate pristane to phytane ratios and a conspicuous hyperbolic decrease in abundance with increasing carbon number of hopane homologues from C₃₀ to C₃₅. The TPP-index of Holba et al. (Holba, A.G., Dzou, L.I., Wood, G.D., Ellis, L., Adam, P., Schaeffer, P., Albrecht, P., Greene, T., Hughes, W.B., 2003. Application of tetracyclic polyprenoids as indicators of input from fresh–brackish water environments. Organic Geochemistry 34, 441–469) is equal to 1 in all samples which in combination with tricyclic triperpane T26/T25 ratios >1 and the n-alkane and hopane distributions mentioned above provide a strong indication of an origin from lacustrine source rocks. This is supported by the absence of marine C₃₀ desmethyl steranes (i.e. 24-n-propylcholestanes) and marine diatom-derived norcholestanes. Based on the overall biological marker distributions, the lakes probably belonged to the overfilled or balanced-fill types defined by Bohacs et al. (Bohacs, K.M., Carroll, A.R., Neal, J.E., Mankiewicz, P.J., 2000. Lake-basin type, source potential, and hydrocarbon character. An integrated sequence-stratigraphic–geochemical framework. AAPG Studies in Geology 46, 3–34). The oils were generated from source rocks at early- to mid-oil-window maturity, presumably Oligocene lacustrine shales that are present in the syn-rift succession. Oils from individual fields may, however, be distinguished by a combination of biological marker parameters, such as the oleanane index, the gammacerane index, the relative abundance of tricyclic terpanes, the proportions of diasteranes and 28-norspergulane, complemented by other parameters. The oils of the Cuu Long Basin show an overall similarity to the B-10 oil from the Song Hong Basin off northern Vietnam, but are markedly different from the seepage oils known from Dam Thi Nai on the coast of central Vietnam.     

Effect of open gap in coastal forest on tsunami run-up—investigations by experiment and numerical simulation

The objective of this study is to investigate the effects of an open gap, such as a road, in a coastal forest on tsunami run-up. A numerical model based on two-dimensional nonlinear long-wave equations was developed to account for the effects of drag and turbulence induced shear forces due to the presence of vegetation. Experiments were conducted on a forest simulated with vertical cylinders by changing the gap width. The numerical model was validated in good agreement with the experimental results. The numerical model was then applied to a wide forest of Pandanus odoratissimus, a tree species that is a dominant coastal vegetation on a sand dune in South and Southeast Asia. The effect of vertical stand characteristics of P. odoratissimus with aerial roots was considered on the drag resistance. A straight open gap perpendicular to the shoreline was used to investigate the effect of gap width. As the gap width increases, the flow velocity at the end of the open gap first increases, reaches a maximum, and then decreases, while the run-up height increases monotonously. The maximum velocity in the present condition is 1.7 times the maximum velocity without a coastal forest. The effects of different gap arrangements in the forest on tsunami run-up were also investigated in this paper. The flow velocity at the end of an open gap can be reduced by a staggered arrangement.