Locally weighted learning based hybrid intelligence models for groundwater potential mapping and modeling: A case study at Gia Lai province,Vietnam

The groundwater potential map is an important tool for a sustainable water management and land use planning,particularly for agricultural countries like Vietnam. In this article, we proposed new machine learning ensemble techniques namely Ada Boost ensemble(ABLWL), Bagging ensemble(BLWL), Multi Boost ensemble(MBLWL),Rotation Forest ensemble(RFLWL) with Locally Weighted Learning(LWL) algorithm as a base classifier to build the groundwater potential map of Gia Lai province in Vietnam. For this study, eleven conditioning factors(aspect, altitude, curvature, slope, Stream Transport Index(STI), Topographic Wetness Index(TWI), soil, geology,river density, rainfall, land-use) and 134 wells yield data was used to create training(70%) and testing(30%)datasets for the development and validation of the models. Several statistical indices were used namely Positive Predictive Value(PPV), Negative Predictive Value(NPV), Sensitivity(SST), Specificity(SPF), Accuracy(ACC),Kappa, and Receiver Operating Characteristics(ROC) curve to validate and compare performance of models. Results show that performance of all the models is good to very good(AUC: 0.75 to 0.829) but the ABLWL model with AUC = 0.89 is the best. All the models applied in this study can support decision-makers to streamline the management of the groundwater and to develop economy not only of specific territories but also in other regions across the world with minor changes of the input parameters.     

Adaptive fisheries management in Vietnam: The use of indicators and the introduction of a multi-disciplinary Marine Fisheries Specialist Team to support implementation

Vietnam is in the process of introducing adaptive management based on indicators and time-series to manage its marine fisheries. The development of indicator-based frameworks for fisheries management has accelerated in recent years. This article describes the suite of indicators being suggested or used in Vietnam including the data-collection system. The Vietnamese approach is supported by an institutional structure consisting of a multi-disciplinary advisory system to facilitate the process of using indicators and to introduce knowledge-based management. The article concludes by identifying current problems and weaknesses and by providing suggestions for future improvement of the system.     

Preliminary Results of Anthropogenic Seismicity Monitoring in the Region of Song Tranh 2 Reservoir,Central Vietnam

Song Tranh 2 hydropower plant and the reservoir containing backed up water are located in the Quang Nam province (Central Vietnam). The region experiences unusual seismic activity related to the reservoir impoundment, with earthquakes of magnitude up to 4.7. In result of cooperation between the Institute of Geophysics, Vietnam Academy of Sciences and Technology and the Institute of Geophysics, Polish Academy of Sciences a seismic network has been built to facilitate seismic monitoring of the Song Tranh 2 area. The network, operating since August 2013, consists of 10 seismic stations. Here we show that the network is sufficient for advanced data processing. The first results of monitoring of the earthquake activity in Song Tranh 2 area in the period between 2012 and 2014, especially the completeness of catalogs, study and comparisons between water level and the seismic activity suggest direct connection between reservoir exploitation and anthropogenic seismicity.     

Freshwater stromatolites with the cone-in-cone structure from the Neogene lacustrine sediments of Vietnam

Morphological features of the columnar-stratiform stromatolites, which resemble the cone-in-cone structure, from Neogene lacustrine sediments of northern Vietnam are analyzed. Their structural-textural peculiarities and interrelations with the host terrigenous sediments of a stromatolitic buildup are discussed. It is shown that stages of the growth of columns are recorded in the succession of vertically oriented carbonate plates, which form stromatolites, and in the serrate surface protrusions of the plates at their contacts with host sediments. It is established that replacement of the columnar stromatolites by the stratiform varieties in the section can be related to variations in the intensity of terrigenous material influx to the sedimentation basin. Stratiform stromatolites were formed during relatively slow accumulation of sedimentary material. Appearance of the columnar varieties is attributed to intensification of sedimentation.     

Non‐local damage modelling of concrete: a procedure for the determination of model parameters

This paper presents a procedure for the determination of parameters of non‐local damage models. This is to assure a consistent response of a non‐local damage model, as choice of the internal length and other parameters of the model are varied. Correlations between the internal length and other parameters governing the local constitutive behaviour of the model are addressed and exploited. Focus is put on the relationship between the internal length of the non‐local model and the width of the fracture process zone. Numerical examples are used to demonstrate the rigour of the proposed method. Copyright © 2006 John Wiley & Sons, Ltd.     

Biogenic carbon flows through the planktonic food web of the Amundsen Gulf (Arctic Ocean): A synthesis of field measurements and inverse modeling analyses

Major pathways of biogenic carbon (C) flow are resolved for the planktonic food web of the flaw lead polynya system of the Amundsen Gulf (southeast Beaufort Sea, Arctic Ocean) in spring-summer 2008. This period was relevant to study the effect of climate change on Arctic marine ecosystems as it was characterized by unusually low ice cover and warm sea surface temperature. Our synthesis relied on a mass balance estimate of gross primary production (GPP) of 52.5 ± 12.5 g C m⁻² calculated using the drawdown of nitrate and dissolved inorganic C, and a seasonal f-ratio of 0.64. Based on chlorophyll a biomass, we estimated that GPP was dominated by phytoplankton (93.6%) over ice algae (6.4%) and by large cells (>5 μm, 67.6%) over small cells (<5 μm, 32.4%). Ancillary in situ data on bacterial production, zooplankton biomass and respiration, herbivory, bacterivory, vertical particle fluxes, pools of particulate and dissolved organic carbon (POC, DOC), net community production (NCP), as well as selected variables from the literature were used to evaluate the fate of size-fractionated GPP in the ecosystem. The structure and functioning of the planktonic food web was elucidated through inverse analysis using the mean GPP and the 95% confidence limits of every other field measurement as lower and upper constraints. The model computed a net primary production of 49.2 g C m⁻², which was directly channeled toward dominant calanoid copepods (i.e. Calanus hyperboreus 20%, Calanus glacialis 10%, and Metridia longa 10%), other mesozooplankton (12%), microzooplankton (14%), detrital POC (18%), and DOC (16%). Bacteria required 29.9 g C m⁻², a demand met entirely by the DOC derived from local biological activities. The ultimate C outflow comprised respiration fluxes (82% of the initial GPP), a small sedimentation (3%), and a modest residual C flow (15%) resulting from NCP, dilution and accumulation. The sinking C flux at the model limit depth (395 m) supplied 60% of the estimated benthic C demand (2.8 g C m⁻²), suggesting that the benthos relied partly on other C sources within the bottom boundary layer to fuel its activity. In summary, our results illustrate that the ongoing decline in Arctic sea ice promotes the growth of pelagic communities in the Amundsen Gulf, which benefited from a ∼80% increase in GPP in spring-summer 2008 when compared to 2004 – a year of average ice conditions and relatively low GPP. However, 53% of the secondary production was generated within the microbial food web, the net ecological efficiency of zooplankton populations was not particularly high (13.4%), and the quantity of biogenic C available for trophic export remained low (6.6 g C m⁻²). Hence it is unlikely that the increase in lower food web productivity, such as the one observed in our study, could support new harvestable fishery resources in the offshore Beaufort Sea domain.     

Detection of mines in acoustic images using higher order spectral features

A new pattern-recognition algorithm detects approximately 90% of the mines hidden in the Coastal Systems Station Sonar0, 1, and 3 databases of cluttered acoustic images, with about 10% false alarms. Similar to other approaches, the algorithm presented here includes processing the images with an adaptive Wiener filter (the degree of smoothing depends on the signal strength in a local neighborhood) to remove noise without destroying the structural information in the mine shapes, followed by a two-dimensional FIR filter designed to suppress noise and clutter, while enhancing the target signature. A double peak pattern is produced as the FIR filter passes over mine highlight and shadow regions. Although the location, size, and orientation of this pattern within a region of the image can vary, features derived from higher order spectra (HOS) are invariant to translation, rotation, and scaling, while capturing the spatial correlations of mine-like objects. Classification accuracy is improved by combining features based on geometrical properties of the filter output with features based on HOS. The highest accuracy is obtained by fusing classification based on bispectral features with classification based on trispectral features.     

Direct parameter identification of fractured porous medium

A direct method of parameter identification for a fracture porous medium can be formulated. The coefficient of piezo-conductivity and the virtual fracture transmissivity can be determined using a combination of graphical methods and approximate formulae. Field calculation provides a practical demonstration of the proposed approach.