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.     

The first peak ground motion attenuation relationships for North of Vietnam

The first attenuation relationships of peak ground acceleration (PGA) and peak ground velocity (PGV) for northern Vietnam are obtained in this study. Ground motion data are collected by a portable broadband seismic network in northern Vietnam as a part of cooperation between the Institute of Geophysics, Vietnamese Academy of Science and Technology, Vietnam and Institute of Earth Sciences, Academia Sinica, Taiwan. The database comprises a total of 330 amplitude records by 14 broadband stations from 53 shallow earthquakes, which were occurred in and around northern Vietnam in the period between 01/2006 and 12/2009. These earthquakes are of local magnitudes between 1.6 and 4.6, focal depths less than 30 km, and epicentral distances less than 500 km. The new attenuation relationships for PGA and PGV are:

log₁₀(PGA)=-0.987+0.7521M_L-log₁₀(R)-0.00475R,     

Geophysical techniques to aquifer locating and monitoring for industrial zones in North Hanoi, Vietnam

Geophysical methods were applied for hydrogeological targets in many countries including Vietnam. This paper presents results of using complex geophysical techniques as well as 2D electrical resistivity imaging (ERI), vertical electrical sounding (VES), very low frequency (VLF), and seismic refraction for geological structure investigation for locating the aquifers and assessing the hydrogeological conditions for groundwater potential in industrial zones of North Hanoi, Vietnam. The locations of two aquifers are determined by their depth and thickness on the basis of resistivity and seismic velocity values which were proved by stratifications of three boreholes to 40–60 m of depth on the study area. There are connections from surface water to shallow aquifer by hydraulic windows, as follows from VLF data. The deeper aquifer can be considered as a potential groundwater supply, but the water level is descending in time, as shown by hydrological monitoring. However, with careful use and by reducing sources of pollution, groundwater can continue to be an important natural resource for future.     

EM and GPR investigations of contaminant spread around the Hoc Mon waste site,Vietnam

This paper is presenting the results from near-surface geophysical surveys near the waste site of Hoc Mon in southern Vietnam where leachate contamination has been recognized at the surface. Using EM and GPR surveys, we were able to determine the lateral extent of a contaminated area of high electrical conductivity and have identified channels that concentrate the contaminant flow. The simple relationship between the electrical resistivity and the leachate concentration is suggested and estimated the in situ leachate concentration from the inversion of the EM data; values are as high as 40%. Thanks to a permeability barrier leachate flow is confined to the shallow subsurface, making it easier to apply possible site remediation projects.     

Stress state in the Cuu Long and Nam Con Son basins, offshore Vietnam

The results presented in this paper are the first published estimates of the complete stress tensor in the Cuu Long and Nam Con Son basins, offshore Vietnam. We analysed in situ stress and pore pressure fields in the sedimentary formations using data from petroleum exploration and production wells to evaluate the stress state in these basins. The data were obtained from the seafloor to 4300 m burial depth and include both hydrostatic and overpressured sections. Minimum horizontal stresses were obtained from extended leak-off tests and mini-fracture tests. Maximum horizontal stresses were estimated from drilling-induced fracture parameters and borehole breakout widths in twelve wells using rock properties measured in the laboratory or estimated empirically from wireline logs. Seven data points are located in sediments, and seventeen data points in igneous basement rocks at depths greater than 3000 m.The estimated magnitudes of σ_H are 70-110% of the σ_v magnitudes. Considering the errors in the stress magnitude estimates, their relative magnitudes suggest that a borderline normal/strike-slip stress regime presently exists in normally pressured sequences of the Nam Con Son and Cuu Long basins. Of the twenty-four data points, twenty have effective stress ratios at a critical stress state for faulting on the assumption that there are faults present that are optimally oriented for failure with friction coefficients of ∼0.5. The results suggest that the stress state in these basins is generally critical.     

FEM × DEM modelling of cohesive granular materials: Numerical homogenisation and multi-scale simulations

The article presents a multi-scale modelling approach of cohesive granular materials, its numerical implementation and its results. At microscopic level, Discrete Element Method (DEM) is used to model dense grains packing. At the macroscopic level, the numerical solution is obtained by a Finite Element Method (FEM). In order to bridge the micro- and macro-scales, the concept of Representative Elementary Volume (REV) is applied, in which the average REV stress and the consistent tangent operators are obtained in each macroscopic integration point as the results of DEM’s simulation. In this way, the numerical constitutive law is determined through the detailed modelling of the microstructure, taking into account the nature of granular materials. We first elaborate the principle of the computation homogenisation (FEM × DEM), then demonstrate the features of our multiscale computation in terms of a biaxial compression test. Macroscopic strain location is observed and discussed.     

Statistical data fusion of multi-sensor AOD over the Continental United States

This article illustrates two techniques for merging daily aerosol optical depth (AOD) measurements from satellite and ground-based data sources to achieve optimal data quality and spatial coverage. The first technique is a traditional Universal Kriging (UK) approach employed to predict AOD from multi-sensor aerosol products that are aggregated on a reference grid with AERONET as ground truth. The second technique is spatial statistical data fusion (SSDF); a method designed for massive satellite data interpolation. Traditional kriging has computational complexity O(N³), making it impractical for large datasets. Our version of UK accommodates massive data inputs by performing kriging locally, while SSDF accommodates massive data inputs by modelling their covariance structure with a low-rank linear model. In this study, we use aerosol data products from two satellite instruments: the moderate resolution imaging spectrometer and the geostationary operational environmental satellite, covering the Continental United States.     

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.