scholarly journals Modeling Spatial Distribution of 2D Anisotropic Hydraulic Conductivity Tensor of Fractured Groundwater Flow Media using Neural Network Case Study Grasberg Open Pit of PTFI and Surrounding

2017 ◽  
Author(s):  
Adam Verdyansyah Putra ◽  
Tedy Agung Cahyadi ◽  
Lilik Eko Widodo ◽  
Eman Widijanto
Keyword(s):  
Neural Network ◽  
Spatial Distribution ◽  
Hydraulic Conductivity ◽  
Groundwater Flow ◽  
Geological Structure ◽  
Conductivity Tensor ◽  
Open Pit ◽  
Two Dimensional ◽  
Fracture Mapping ◽  
Anisotropic Hydraulic Conductivity

Highly fractured rocks in Grasberg open pit and surrounding of PT Freeport Indonesia (PTFI) result in fractured groundwater flow media. It is due to the complex geological structure and lithological condition. Accordingly, it leads to anisotropic distribution of hydraulic conductivity. The paper will be devoted tothe modeling of two dimensional (2D) spatial distribution of hydraulic conductivity using neural network. Surface fracture mapping database will be used to estimate 2D equivalent anisotropic hydraulic conductivity tensor based on the Oda et al (1996) approach. Modeled anisotropic hydraulic conductivity is then checked at some points where the slug tests for isotropic conductivity are observed. Co-relation, validation and training between modeled and observed hydraulic conductivity is then carried out using transformation of vector anisotropic hydraulic conductivity into the scalar isotropic hydraulic conductivity. Following training step, neural network will then generate two dimensional model of anisotropic hydraulic conductivity distribution. It is beneficial for modeling of shallow anisotropic flow of groundwater distribution

scholarly journals Modeling Spatial Distribution of 3D Isotropic Hydraulic Conductivity Based on HC-System for Fractured Groundwater Flow Media using Neural Network Case Study Grasberg Open Pit of PTFI

2017 ◽  
Author(s):  
Tedy Agung Cahyadi ◽  
Lilik Eko Widodo ◽  
Irwan Iskandar ◽  
Sukaerang ◽  
Suyono
Keyword(s):  
Neural Network ◽  
Hydraulic Conductivity ◽  
Groundwater Flow ◽  
System Approach ◽  
Groundwater Modeling ◽  
Open Pit ◽  
Open Pit Mining ◽  
Distribution Data ◽  
Slug Test ◽  
Packer Test

Hydraulic conductivity property is very important for groundwater flow modeling. It can be gathered through packer test and slug test. The high cost of the operational implementation of these tests lead to the limited availability of observational-based distribution of hydraulic conductivity data. Highly fractured rocks in Grasberg open pit mining and surrounding of PT Freeport Indonesia (PTFI) result in fractured-groundwater-flow media. It is related to the complex geological structure and lithological condition. Groundwater modeling needs 3D distribution data such hydraulic conductivity (K). On previous research, hydraulic conductivity is distributed homogenyneously at each layer model. In this paper, under limited observational hydraulic conductivity, isotropic hydraulic conductivity will be modeled based on the HC-System approach and will be three-dimensionally distributed using Artificial Neural Network (ANN). HC-System approach will be developed according to the packer test and slug test measurement using geotechnical data from drilling such as Rock Quality Designation (RQD), Lithology Permeability Index (LPI), Depth Index (DI), and Gouge Content Index. HC-System approach will be resulted in isotropic distribution of hydraulic conductivity. It is then checked at some points by the packer tests and slug tests observational data. It is further very beneficial for modeling of groundwater distribution flow with the heterogeny hydraulic conductivity.

Groundwater flow systems in the crystalline rocks of the Okanagan Highland, British Columbia

1968 ◽  
Vol 5 (4) ◽  
pp. 813-824 ◽  
Author(s):  
D. W. Lawson
Keyword(s):  
Hydraulic Conductivity ◽  
Groundwater Flow ◽  
Flow System ◽  
Crystalline Rock ◽  
Crystalline Rocks ◽  
Two Dimensional ◽  
Local Flow ◽  
Groundwater Flow Systems ◽  
Flow Systems ◽  
Two Dimensional Flow

An investigation of the groundwater flow systems associated with the most prominent topographic expression in the Okanagan Highland (a U-shaped valley) revealed that the hydraulic conductivity of the crystalline rock varies exponentially with depth, and that the local flow systems within the upper 125 to 150 ft of the crystalline rock conduct an estimated 10 to 17 Imperial gallons per day per foot thickness in a two-dimensional flow system. These local flow systems are quantitatively the most significant in the Okanagan Highland.

scholarly journals CONTRIBUTION TO HYDRAULIC CHARACTERISTICS OF PLIO-PLEISTOCENE DEPOSITS OF THRIASSION PLAIN OF ATTICA

2017 ◽  
Vol 50 (2) ◽  
pp. 967 ◽  
Author(s):  
D. Hermides ◽  
T. Mimides ◽  
G. Stamatis
Keyword(s):  
Hydraulic Conductivity ◽  
Groundwater Flow ◽  
Specific Capacity ◽  
Geological Structure ◽  
Hydraulic Characteristics ◽  
Dry Period ◽  
Tectonic Structures ◽  
Pumping Tests ◽  
Recovery Method ◽  
Hydrogeological Conditions

The geological structure of Thriassion Plain is generally complex and has been affected at different times by many tectonic activities. The last ones are the neotectonic, which caused horsts and grabens structures. Geologic and tectonic structures have influenced the hydrogeological conditions and the groundwater flow. Hydraulic characteristics of Plio-Pleistocene deposits differ throughout their extent. In this study, pumping tests in Plio-Pleistocene deposits are represented and the hydraulic characteristics transmissivity T, storativity S and hydraulic conductivity K are assigned. Pumping tests, in 8 totally wells, were conducted in the dry period. Methods as Cooper-Jacob’s, Theis’s, Papadopoulos Cooper’s and Neuman’s and last the Recovery method, are used to assign the hydraulic characteristics. These tests highlighted the Recovery method as the most reliable. Transmissivity T: 18-279.1 m2/d, storativity S: 2.5*10-3 3*10-2and hydraulic conductivity K: 0.4-25.1 m/d. Specific capacity is also determined ranging between 16-360 m3/d/m. This study contributes, essentially, in the approach of hydrogeological conditions of Thriassion Plain.

scholarly journals Groundwater Flow Modeling: A Case Study of the Lower Rusizi Alluvial Plain Aquifer, North-Western Burundi

Water ◽  
2021 ◽  
Vol 13 (23) ◽  
pp. 3376
Author(s):  
Pierre Claver Ngenzebuhoro ◽  
Alain Dassargues ◽  
Tarik Bahaj ◽  
Philippe Orban ◽  
Ilias Kacimi ◽  
...  
Keyword(s):  
Spatial Distribution ◽  
Hydraulic Conductivity ◽  
Groundwater Flow ◽  
Integrated Management ◽  
Regional Scale ◽  
Pumping Test ◽  
Groundwater Potential ◽  
Alluvial Plain ◽  
Predictive Tool ◽  
Groundwater Levels

The study area, in northwestern Burundi, is an alluvial plain consisting of fine clayey sands and coarse sands with mixed lithology. The aquifer of the lower Rusizi plain could be considered as confined under a clay layer. A 2D horizontal groundwater flow model was developed under steady-state conditions using the Modflow software. The study aims to determine the most productive areas of this confined alluvial aquifer and the main aquifer inflow and outflow values together with the recharge and river–aquifer interactions. The groundwater potential is dependent on the spatial distribution of hydraulic conductivity and aquifer thickness values providing the local transmissivity values. The calibrated model made it possible to assess the spatial distribution of the hydraulic conductivity values at the regional scale, which ranged from 6 × 10−6 (contact between alluvial plain and Precambrian basement) to 7.5 × 10−3 m/s (coastal barriers). The results also provided the computed groundwater flow directions, and an estimation of the groundwater levels in areas not yet investigated by drilling. The results of the computed groundwater flow budget allowed us to deduce that recharge and river–aquifer interaction constitute the main inflow while the downwards boundaries (where piezometric heads could be prescribed) are the main zones where outflows occur. The results of this model can be used in the planning of pumping test programs, locating areas with high groundwater potential to plan water supply for different private and public users. This predictive tool will contribute to the resolution of problems related to the use and integrated management of the groundwater resource in this part of Burundi.

scholarly journals Predictive modelling of soils’ hydraulic conductivity using artificial neural network and multiple linear regression

2021 ◽  
Vol 3 (2) ◽  
Author(s):  
Charles Gbenga Williams ◽  
Oluwapelumi O. Ojuri
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Hydraulic Conductivity ◽  
Linear Regression ◽  
Multiple Linear Regression ◽  
Coarse Grained ◽  
Soil Types ◽  
Wide Range ◽  
Artificial Neural ◽  
Input Variables

AbstractAs a result of heterogeneity nature of soils and variation in its hydraulic conductivity over several orders of magnitude for various soil types from fine-grained to coarse-grained soils, predictive methods to estimate hydraulic conductivity of soils from properties considered more easily obtainable have now been given an appropriate consideration. This study evaluates the performance of artificial neural network (ANN) being one of the popular computational intelligence techniques in predicting hydraulic conductivity of wide range of soil types and compared with the traditional multiple linear regression (MLR). ANN and MLR models were developed using six input variables. Results revealed that only three input variables were statistically significant in MLR model development. Performance evaluations of the developed models using determination coefficient and mean square error show that the prediction capability of ANN is far better than MLR. In addition, comparative study with available existing models shows that the developed ANN and MLR in this study performed relatively better.

scholarly journals Heat induction in two-dimensional graphene–Fe3O4 nanohybrids for magnetic hyperthermia applications with artificial neural network modeling

RSC Advances ◽  
2021 ◽  
Vol 11 (35) ◽  
pp. 21702-21715
Author(s):  
M. S. Dar ◽  
Khush Bakhat Akram ◽  
Ayesha Sohail ◽  
Fatima Arif ◽  
Fatemeh Zabihi ◽  
...  
Keyword(s):  
Neural Network ◽  
Magnetic Field ◽  
Artificial Neural Network ◽  
Network Modeling ◽  
Magnetic Hyperthermia ◽  
Alternating Magnetic Field ◽  
Neural Network Modeling ◽  
Two Dimensional ◽  
Artificial Neural Network Modeling ◽  
Heat Induction

Synthesis of Fe3O4–graphene (FG) nanohybrids and magnetothermal measurements of FxG100–x (x = 0, 25, 45, 65, 75, 85, 100) nanohybrids (25 mg each) at a 633 kHz alternating magnetic field of strength 9.1 mT.

scholarly journals Geological and groundwater flow model of a submarine groundwater discharge site at Hanko (Finland), northern Baltic Sea

2021 ◽  
Author(s):  
Samrit Luoma ◽  
Juha Majaniemi ◽  
Arto Pullinen ◽  
Juha Mursu ◽  
Joonas J. Virtasalo
Keyword(s):  
Hydraulic Conductivity ◽  
Groundwater Flow ◽  
Baltic Sea ◽  
Submarine Groundwater Discharge ◽  
Flow Model ◽  
Groundwater Discharge ◽  
Coarse Grained ◽  
Local Geometry ◽  
Groundwater Flow Model ◽  
Submarine Groundwater

AbstractThree-dimensional geological and groundwater flow models of a submarine groundwater discharge (SGD) site at Hanko (Finland), in the northern Baltic Sea, have been developed to provide a geological framework and a tool for the estimation of SGD rates into the coastal sea. The dataset used consists of gravimetric, ground-penetrating radar and shallow seismic surveys, drill logs, groundwater level monitoring data, field observations, and a LiDAR digital elevation model. The geological model is constrained by the local geometry of late Pleistocene and Holocene deposits, including till, glacial coarse-grained and fine-grained sediments, post-glacial mud, and coarse-grained littoral and aeolian deposits. The coarse-grained aquifer sediments form a shallow shore platform that extends approximately 100–250 m offshore, where the unit slopes steeply seawards and becomes covered by glacial and post-glacial muds. Groundwater flow preferentially takes place in channel-fill outwash coarse-grained sediments and sand and gravel interbeds that provide conduits of higher hydraulic conductivity, and have led to the formation of pockmarks on the seafloor in areas of thin or absent mud cover. The groundwater flow model estimated the average SGD rate per square meter of the seafloor at 0.22 cm day−1 in autumn 2017. The average SGD rate increased to 0.28 cm day−1 as a response to an approximately 30% increase in recharge in spring 2020. Sensitivity analysis shows that recharge has a larger influence on SGD rate compared with aquifer hydraulic conductivity and the seafloor conductance. An increase in recharge in this region will cause more SGD into the Baltic Sea.

Deep convolutional neural networks for human movement detection using wireless signals

2021 ◽  
pp. 1-10
Author(s):  
Chien-Cheng Leea ◽  
Zhongjian Gao ◽  
Xiu-Chi Huanga
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Convolutional Neural Network ◽  
Detection System ◽  
Deep Convolutional Neural Network ◽  
Human Detection ◽  
Two Dimensional ◽  
Dimensional Matrix ◽  
State Classification ◽  
Propagation Paths

This paper proposes a Wi-Fi-based indoor human detection system using a deep convolutional neural network. The system detects different human states in various situations, including different environments and propagation paths. The main improvements proposed by the system is that there is no cameras overhead and no sensors are mounted. This system captures useful amplitude information from the channel state information and converts this information into an image-like two-dimensional matrix. Next, the two-dimensional matrix is used as an input to a deep convolutional neural network (CNN) to distinguish human states. In this work, a deep residual network (ResNet) architecture is used to perform human state classification with hierarchical topological feature extraction. Several combinations of datasets for different environments and propagation paths are used in this study. ResNet’s powerful inference simplifies feature extraction and improves the accuracy of human state classification. The experimental results show that the fine-tuned ResNet-18 model has good performance in indoor human detection, including people not present, people still, and people moving. Compared with traditional machine learning using handcrafted features, this method is simple and effective.

Sign in / Sign up

Export Citation Format

Share Document