scholarly journals Combining ground-based and airborne EM through Artificial Neural Networks for modelling hydrogeological units under saline groundwater conditions

2012 ◽  
Vol 9 (3) ◽  
pp. 3269-3309 ◽  
Author(s):  
J. L. Gunnink ◽  
J. H. A. Bosch ◽  
B. Siemon ◽  
B. Roth ◽  
E. Auken
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Clay Content ◽  
Cost Effective ◽  
Glacial Till ◽  
Saline Groundwater ◽  
Artificial Neural ◽  
Electro Magnetic ◽  
Groundwater Quantity ◽  
Airborne Em

Abstract. Airborne Electro Magnetic (EM) methods supply data over large areas in a cost-effective way. We used Artificial Neural Networks (ANN) to classify the geophysical signal into a meaningful geological parameter. By using examples of known relations between ground-based geophysical data (in this case electrical conductivity, EC, from Electrical Cone Penetration Tests) and geological parameters (presence of glacial till), we extracted learning rules that could be applied to map the presence of a glacial till using the EC profiles from the airborne EM data. The saline groundwater in the area was obscuring the EC signal from the till but by using ANN we were able to extract subtle and often non-linear, relations in EC that were representative for the presence of the till. The ANN results were interpreted as the probability of having till and showed a good agreement with drilling data. The glacial till is acting as a layer that inhibits groundwater flow, due to its high clay-content, and is therefore an important layer in hydrogeological modelling and for predicting the effects of climate change on groundwater quantity and quality.

scholarly journals Combining ground-based and airborne EM through Artificial Neural Networks for modelling glacial till under saline groundwater conditions

2012 ◽  
Vol 16 (8) ◽  
pp. 3061-3074 ◽  
Author(s):  
J. L. Gunnink ◽  
J. H. A. Bosch ◽  
B. Siemon ◽  
B. Roth ◽  
E. Auken
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Clay Content ◽  
Cost Effective ◽  
Glacial Till ◽  
Saline Groundwater ◽  
Cone Penetration Tests ◽  
Artificial Neural ◽  
Groundwater Quantity ◽  
Airborne Em

Abstract. Airborne electromagnetic (AEM) methods supply data over large areas in a cost-effective way. We used Artificial Neural Networks (ANN) to classify the geophysical signal into a meaningful geological parameter. By using examples of known relations between ground-based geophysical data (in this case electrical conductivity, EC, from electrical cone penetration tests) and geological parameters (presence of glacial till), we extracted learning rules that could be applied to map the presence of a glacial till using the EC profiles from the airborne EM data. The saline groundwater in the area was obscuring the EC signal from the till but by using ANN we were able to extract subtle and often non-linear, relations in EC that were representative of the presence of the till. The ANN results were interpreted as the probability of having till and showed a good agreement with drilling data. The glacial till is acting as a layer that inhibits groundwater flow, due to its high clay-content, and is therefore an important layer in hydrogeological modelling and for predicting the effects of climate change on groundwater quantity and quality.

scholarly journals Prediction of Geotechnical Properties of Soil using Artificial Intelligence Framework

2021 ◽  
Vol 10 (4) ◽  
pp. 218-227
Author(s):  
Jitendra Khatti ◽  
◽  
Dr. Kamaldeep Singh Grover ◽  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Gaussian Process ◽  
Gaussian Process Regression ◽  
Clay Content ◽  
Geotechnical Properties ◽  
Support Vector ◽  
Analysis Tool ◽  
Artificial Neural ◽  
Properties Of Soil

The present research work is carried out to predict the geotechnical properties (consistency limits, OMC, and MDD) of soil using AI technologies, namely regression analysis (RA), support vector machine (SVM), Gaussian process regression (GPR), artificial neural networks (ANNs), and relevance vector machine (RVM). The models of machine learning (SVM, GPR), hybrid learning (RVM), and deep learning (ANNs) are constructed in MATLAB R2020a with different configurations. The models of RA are built using the Data Analysis Tool of Microsoft Excel 2019. The input parameters of AI models are gravel, sand, silt, and clay content. The correlation coefficient is calculated for pair of soil datasets. The correlation shows that sand, silt, and clay content play a vital role in predicting soil's liquid limit and plasticity index. The performance of constructed AI models is compared to determine the optimum performance models. The limited datasets of soil are used in this study. Therefore, artificial neural networks and relevance vector machines could not perform well. Based on the performance of AI models, the Gaussian process regression outperformed the RA, SVM, ANNs, and RVM AI technologies. Hence, the GPR AI approach can predict the geotechnical properties of soil by gravel, sand, silt, and clay content. The Monte-Carlo global sensitivity analysis is also performed, and it is observed that the prediction of geotechnical properties of soil is affected by sand and clay content

Indirect aircraft structural monitoring using artificial neural networks

2008 ◽  
Vol 112 (1131) ◽  
pp. 251-265 ◽  
Author(s):  
S. C. Reed
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Monitoring System ◽  
Cost Effective ◽  
Military Aircraft ◽  
Royal Air Force ◽  
Parametric Data ◽  
Flight Parameters ◽  
Artificial Neural

Abstract From necessity, military aircraft often operate in a highly fatigue damaging environment and history has shown in lost lives and aircraft the consequences of failure to appreciate fully the usage environment. The need for robust and cost effective structural usage monitoring of military aircraft to ensure operations are conducted within acceptable levels of risk is paramount. Furthermore, increased economic pressures require ever-inventive methods to be employed to maximise the lives of military fleets; structural usage monitoring will be a key asset in this drive. A highly cost effective indirect structural health and usage neural network (SHAUNN) monitoring system is proposed. A SHAUNN uses regression relationships determined by artificial neural networks to predict stresses, strains, loads, or fatigue damage from flight parameters. Within this paper the development of a SHAUNN monitoring system is described. Flight parametric data, captured during Operational Loads Measurement of the Royal Air Force Dominie TMk1 aircraft have been used to predict stresses at the key structural location in the wing, using mapping relationships determined by artificial neural networks. A framework for the development of the SHAUNN monitoring system is discussed and the basic architecture of the multilayer perceptron artificial neural network is described. It is concluded that this technology could provide the basis for an accurate, cost-effective structural usage monitoring system and further work to investigate the prediction of ground – based stresses in the wing is recommended.

scholarly journals Artificial neural networks in the prediction of soil chemical attributes using apparent electrical conductivity

2021 ◽  
Vol 19 (3) ◽  
pp. e0208-e0208
Author(s):  
Samuel A. Silva ◽  
Keyword(s):  
Neural Networks ◽  
Electrical Conductivity ◽  
Artificial Neural Networks ◽  
Clay Content ◽  
Soil Samples ◽  
Resistivity Method ◽  
Artificial Neural ◽  
Chemical Attributes ◽  
Input Variables ◽  
Data Collections

Aim of study: To use artificial neural networks (ANN) to predict the values and spatial distribution of soil chemical attributes from apparent soil electrical conductivity (ECa) and soil clay contents. Area of study: The study was carried out in an area of 1.2-ha cultivated with cocoa, located in the state of Bahia, Brazil. Material and methods: Data collections were performed on a sampling grid containing 120 points. Soil samples were collected to determine the attributes: clay, silt, sand, P, K+, Ca2+, Mg2+, S, pH, H+Al, SB, CTC, V, OM and P-rem. ECa was measured using the electrical resistivity method in three different periods related to soil sampling: 60 days before (60ECa), 30 days before (30ECa) and when collecting soil samples (0ECa). For the prediction of chemical and physical-chemical attributes of the soil, models based on ANN were used. As input variables, the ECa and the clay contents were used. The quality of ANN predictions was determined using different statistical indicators. Thematic maps were constructed for the attributes determined in the laboratory and those predicted by the ANNs and the values were grouped using the fuzzy k-means algorithm. The agreement between classes was performed using the kappa coefficient. Main results: Only P and K+ attributes correlated with all ANN input variables. ECa and clay contents in the soil proved to be good variables for predicting soil attributes. Research highlights: The best results in the prediction process of the P and K+ attributes were obtained with the combination of ECa and the clay content.

scholarly journals Identification of efficient COVID-19 diagnostic test through artificial neural networks approach − substantiated by modeling and simulation

2021 ◽  
Vol 30 (1) ◽  
pp. 836-854
Author(s):  
Mustafa Kamal Pasha ◽  
Syed Fasih Ali Gardazi ◽  
Fariha Imtiaz ◽  
Asma Talib Qureshi ◽  
Rabia Afrasiab
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Cost Effective ◽  
Limiting Factor ◽  
Probabilistic Algorithms ◽  
Global Pandemic ◽  
Sample Pooling ◽  
Test Specificity ◽  
Artificial Neural ◽  
The Masses

Abstract Soon after the first COVID-19 positive case was detected in Wuhan, China, the virus spread around the globe, and in no time, it was declared as a global pandemic by the WHO. Testing, which is the first step in identifying and diagnosing COVID-19, became the first need of the masses. Therefore, testing kits for COVID-19 were manufactured for efficiently detecting COVID-19. However, due to limited resources in the densely populated countries, testing capacity even after a year is still a limiting factor for COVID-19 diagnosis on a larger scale and contributes to a lag in disease tracking and containment. Due to this reason, we started this study to provide a better cost-effective solution for enhancing the testing capacity so that the maximum number of people could get tested for COVID-19. For this purpose, we utilized the approach of artificial neural networks (ANN) to acquire the relevant data on COVID-19 and its testing. The data were analyzed by using Machine Learning, and probabilistic algorithms were applied to obtain a statistically proven solution for COVID-19 testing. The results obtained through ANN indicated that sample pooling is not only an effective way but also regarded as a “Gold standard” for testing samples when the prevalence of the disease is low in the population and the chances of getting a positive result are less. We further demonstrated through algorithms that pooling samples from 16 individuals is better than pooling samples of 8 individuals when there is a high likelihood of getting negative test results. These findings provide ground to the fact that if sample pooling will be employed on a larger scale, testing capacity will be considerably increased within limited available resources without compromising the test specificity. It will provide healthcare units and enterprises with solutions through scientifically proven algorithms, thus, saving a considerable amount of time and finances. This will eventually help in containing the spread of the pandemic in densely populated areas including vulnerably confined groups, such as nursing homes, hospitals, cruise ships, and military ships.

Development of a parametric-based indirect aircraft structural usage monitoring system using artificial neural networks

2007 ◽  
Vol 111 (1118) ◽  
pp. 209-230 ◽  
Author(s):  
S. C. Reed
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Artificial Neural Networks ◽  
Monitoring System ◽  
Cost Effective ◽  
Monitoring Systems ◽  
Military Aircraft ◽  
Parametric Data ◽  
Artificial Neural

The development of a parametric-based indirect aircraft structural usage monitoring system using artificial neural networks is described. Flight parametric data, captured during Operational Loads Measurement have been used to predict strains or stresses at key structural locations for several military aircraft types, using mapping relationships determined by artificial neural networks. A framework for the development of a neural network-based structural usage monitor is discussed and the basic architecture of the multilayer perceptron artificial neural network is described. Additionally, results from case studies are presented. It is concluded that this technology could provide the basis for accurate, cost-effective structural usage monitoring systems across the range of military aircraft types and roles.

scholarly journals Enhanced Short-Term Load Forecasting Using Artificial Neural Networks

Energies ◽  
2021 ◽  
Vol 14 (22) ◽  
pp. 7788
Author(s):  
Athanasios Ioannis Arvanitidis ◽  
Dimitrios Bargiotas ◽  
Aspassia Daskalopulu ◽  
Vasileios M. Laitsos ◽  
Lefteri H. Tsoukalas
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Power Systems ◽  
Power System ◽  
Research And Development ◽  
Load Forecasting ◽  
Cost Effective ◽  
Training Data ◽  
Renewable Energy Resources ◽  
Artificial Neural

The modernization and optimization of current power systems are the objectives of research and development in the energy sector, which is motivated by the ever-increasing electricity demands. The goal of such research and development is to render power electronic equipment more controllable, to ensure maximal use of current circuits, system flexibility and efficiency, as well as the relatively easy integration of renewable energy resources at all voltage levels. The current revolution in communication technologies and the Internet of Things (IoT) offers us an opportunity to supervise and regulate the power grid, in order to achieve more reliable, efficient, and cost-effective services. One of the most critical aspects of efficient power system operation is the ability to predict energy load requirements, i.e., load forecasting. Load forecasting is essential for balancing demand and supply and for determining electricity prices. Typically, load forecasting has been supported through the use of Artificial Neural Networks (ANNs), which, once trained on a set of data, can predict future loads. The accuracy of the ANNs’ prediction depends on the quality and availability of the training data. In this paper, we propose novel data pre-processing strategies, which we apply to the data used to train an ANN, and subsequently evaluate the quality of the predictions it produces, to demonstrate the benefits gained. The proposed strategies and the obtained results are illustrated using consumption data from the Greek interconnected power system.

Fabrication and Wear Behavior Investigation of the Carbon/Epoxy Composites Based on Wood Using Artificial Neural Networks

2011 ◽  
Vol 413 ◽  
pp. 95-102 ◽  
Author(s):  
Hossein Vafaeenezhad ◽  
Seyed Mojtaba Zebarjad ◽  
Jalil Vahdati Khaki
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Wear Behavior ◽  
Raw Materials ◽  
Normal Load ◽  
Carbon Matrix ◽  
Cost Effective ◽  
Quercus Suber ◽  
Wear Properties ◽  
Artificial Neural

Since wood is the main component of the applied raw materials, it can be used as matrix in carbon composites, also it can be taken into consideration as a cost effective advanced application and have this potential to suppress many expensive fabrication and finishing procedures. Wood samples from Oak tree (Quercus suber) were heated at different temperatures to produce porous carbon templates. Subsequently, the Carbonized wood was infiltrated with an epoxy in order to fabricate the final carbon/epoxy composite. Scanning electron microscopy was used to elucidate parameters affecting on microstructure and wear properties of products. In this context, artificial neural networks (ANN) and design of experiments method (DOE) was implemented to analyze the wear performance of a new class of cellulose based composites. This work indicates that epoxy shows good reinforcement characteristics as it improves the sliding wear resistance of the carbon matrix and that factors like carbonization temperature, sliding distance and normal load are the important factors affecting the wear behaviors.

Sign in / Sign up

Export Citation Format

Share Document