scholarly journals Machine Learning in Discriminating Active Volcanoes of the Hellenic Volcanic Arc

2021 ◽  
Vol 11 (18) ◽  
pp. 8318
Author(s):  
Athanasios G. Ouzounis ◽  
George A. Papakostas
Keyword(s):  
Machine Learning ◽  
Volcanic Rock ◽  
Volcanic Rocks ◽  
Major Elements ◽  
Machine Learning Algorithms ◽  
Geochemical Data ◽  
Geochemical Composition ◽  
Volcanic Arc ◽  
New Approach ◽  
Geochemical Fingerprinting

Identifying the provenance of volcanic rocks can be essential for improving geological maps in the field of geology and providing a tool for the geochemical fingerprinting of ancient artifacts like millstones and anchors in the field of geoarchaeology. This study examines a new approach to this problem by using machine learning algorithms (MLAs). In order to discriminate the four active volcanic regions of the Hellenic Volcanic Arc (HVA) in Southern Greece, MLAs were trained with geochemical data of major elements, acquired from the GEOROC database, of the volcanic rocks of the Hellenic Volcanic Arc (HVA). Ten MLAs were trained with six variations of the same dataset of volcanic rock samples originating from the HVA. The experiments revealed that the Extreme Gradient Boost model achieved the best performance, reaching 93.07% accuracy. The model developed in the framework of this research was used to implement a cloud-based application which is publicly accessible at This application can be used to predict the provenance of a volcanic rock sample, within the area of the HVA, based on its geochemical composition, easily obtained by using the X-ray fluorescence (XRF) technique.

scholarly journals Geochemical features and formation conditions of Early-Devonian cherty-argillaceous shales and the underlying basalts in the Ishkildino section (eastern slope of the Southern Urals)

LITOSFERA ◽  
2019 ◽  
pp. 30-47
Author(s):  
A. M. Fazliakhmetov
Keyword(s):  
Volcanic Rocks ◽  
Southern Urals ◽  
Geochemical Data ◽  
Upper Ordovician ◽  
The Southern Urals ◽  
Geochemical Composition ◽  
Early Devonian ◽  
Ocean Ridges ◽  
Clay Shales ◽  
Conodont Zone

Research subject.The West Magnitogorsk zone of the Southern Urals in the vicinity of the Ishkildino village features a subaerially exposed basaltic sequence superposed by cherts and siliceous-clay shales. The basalts and the overlying shales are assumed to have formed during the Ordovician and Silurian (?)–Early Devonian (up to the conodont zone excavates inclusive) periods, respectively. The aim of this research was to reconstruct, using geochemical data, the conditions under which the rocks present in this geological location were formed.Materials and methods. Five samples of the basalts (XRD and ICP-MS methods), 27 samples of the siliceous-clay shales and 10 samples of the cherts (XRD and ICP-AES methods) were analyzed.Results.According to the ratio of SiO2, Na2O and K2O, the volcanic rocks from the lower part of the section are represented by basalts and trachybasalts. Their geochemical composition corresponds to the N-MORB and is established to be similar to that of the basalts in the Polyakovskaya formation (the Middle–Upper Ordovician). In terms of main elements, the shales under study consist of quartz and illite with a slight admixture of organic matter, goethite, quartzfeldspar fragments, etc. The degree of the sedimentary material weathering according to the CIA, CIW and ICV index values is shown to be moderate. The values of Strakhov’s and Boström’s moduli correspond to sediments without the admixture of underwater hydrothermal vent products. The values of Cr/Al, V/Al and Zr/Al correspond to those characteristic of deposits in deep-water zones remote from the coasts of passive and active continental margins, basalt islands and areas adjacent to mid-ocean ridges. For most samples, the values of Ni/Co, V/Cr, Mo/Mn are typical of deposits formed under oxidative conditions. However, several samples from the upper part of the section, which is comparable to the kitabicus and excavatus conodont zones, demonstrate the Ni/Co, V/Cr, and Mo/Mn values corresponding to deposits formed under reducing atmospheres. An assumption is made that the existence of these deposits can be associated with the Bazal Zlichov event.Conclusion.The investigated pre-Emsian shales have shown no signs of volcanic activity in the adjacent areas. The studied deposits are established to correspond to the central part of the Ural Paleoocean.

Developing a new approach for design support of subsurface constructed wetland using machine learning algorithms

2022 ◽  
Vol 301 ◽  
pp. 113868
Author(s):  
Xuan Cuong Nguyen ◽  
Thi Thanh Huyen Nguyen ◽  
Quyet V. Le ◽  
Phuoc Cuong Le ◽  
Arun Lal Srivastav ◽  
...  
Keyword(s):  
Machine Learning ◽  
Constructed Wetland ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Design Support ◽  
New Approach

Using machine learning as an aid to seismic geomorphology, which attributes are the best input?

2019 ◽  
Vol 7 (3) ◽  
pp. SE1-SE18 ◽  
Author(s):  
Lennon Infante-Paez ◽  
Kurt J. Marfurt
Keyword(s):  
Machine Learning ◽  
Volcanic Rocks ◽  
High Amplitude ◽  
Machine Learning Algorithms ◽  
Pyroclastic Flows ◽  
Seismic Survey ◽  
Self Organizing Maps ◽  
Target Pattern ◽  
Seismic Geomorphology ◽  
Amplitude Data

Volcanic rocks with intermediate magma composition indicate distinctive patterns in seismic amplitude data. Depending on the processes by which they were extruded to the surface, these patterns may be chaotic, moderate-amplitude reflectors (indicative of pyroclastic flows) or continuous high-amplitude reflectors (indicative of lava flows). We have identified appropriate seismic attributes that highlight the characteristics of such patterns and use them as input to self-organizing maps to isolate these volcanic facies from their clastic counterpart. Our analysis indicates that such clustering is possible when the patterns are approximately self-similar, such that the appearance of objects does not change at different scales of observation. We adopt a workflow that can help interpreters to decide what methods and what attributes to use as an input for machine learning algorithms, depending on the nature of the target pattern of interest, and we apply it to the Kora 3D seismic survey acquired offshore in the Taranaki Basin, New Zealand. The resulting clusters are then interpreted using the limited well control and principles of seismic geomorphology.

Andesite Geochemistry Features of Late Triassic Tumugou Formation, in Zhongdian, Yunnan Province

2012 ◽  
Vol 524-527 ◽  
pp. 16-23
Author(s):  
Jian Guo Huang ◽  
Run Sheng Han ◽  
Ren Tao ◽  
Zhi Qiang Li
Keyword(s):  
Trace Element ◽  
Volcanic Rock ◽  
Continental Margin ◽  
Active Continental Margin ◽  
Volcanic Rocks ◽  
Distribution Patterns ◽  
Island Arc ◽  
Late Triassic ◽  
Magma Source ◽  
Volcanic Arc

The Late Triassic Tumugou Formation volcanic rocks which belongs to typical island arc volcanic rocks in southern end of Yidun island arc belt is located at the eastern of the Zhongdian ,NW Yunnan, SW China. The volcanic rocks can be divided into three categories:andesitic basalt, andesite, quartz andesite, etc. Through geochemical analysis the major elements, rare earth ele and trace element in volcanic rocks, SiO255.18-57.59×10-2,TiO21.16-1.45×10-2,Na2O+K2O5.11-8.05×10-2.consider it is calc-alkaline- alkaline Series of high-K andesite, volcanic may be controlled by the crystal fractionation of magma.Rb31.50-101×10-6,Ba1310-12300×10-6,Nb/Ta11.4-15.5,REE166.07-240.78×10-6,δEu0.74-1.00,REE distribution patterns show oblique to the HREE side and enrichment in LREE .Eu anomaly is not obvious. It is can see from the relevant figure about trace element, it is very similar in magmatic distribution patterns between volcanic rock and Volcanic-arc rock, indicating that the volcanic in this area may be formed in volcanic-arc environment. From east to west, Magma source depth have regular change with the really thickness of mainland shell. Explain that Tumugou Formation volcanic rock is subduction by Ganzi- Litang Ocean basin from east to west. Hongshan-Ousaila region of eastern edge of Zhongdian is the volcanic island arc system during the passive continental margin into an active continental margin.

scholarly journals Evaluation on NTM based Predictive Analytics on Rainfall and Flood Disaster Management

2020 ◽  
Vol 6 (10) ◽  
pp. 89-95
Author(s):  
Satwik P M and Dr. Meenatchi Sundram
Keyword(s):  
Machine Learning ◽  
Predictive Analytics ◽  
Learning Algorithm ◽  
Research Work ◽  
Evaluation Process ◽  
Machine Learning Algorithms ◽  
New Approach ◽  
Research Article ◽  
The Neural Networks ◽  
Evaluation Parameters

In this Research article, we presented a new approach for predicting the flood through the advanced Machine learning Algorithm which is one among the Neural networks class that outperforms itself in best data operations and predictive analytics. This Research article discusses in detail about the prediction of flood occurrences evaluation process. We interpreted the Research with many algorithms that is existing, and the Research work have been dealing with different research works inculcated and compared with different Research approaches. On Comparing to the Previous Researches its observed that the Neural Turing networks have been performing the prediction of the rainfall and flood-based disasters for the consecutive year counts of 10,15 and 20 with 93.8% accuracy. Here the Research is analyzed with various parameters and Comparing it with the other researches which is implemented with other machine learning algorithms. Comparing with the previous researches the Idea of the research have been described and evaluated with the different evaluation parameters including the number of iterations or Epochs.

scholarly journals Chau Thoi and Nui Gio volcanic rocks: A remnant of the Loei Phetchabun volcanic belt in Viet Nam

2021 ◽  
Vol 24 (1) ◽  
pp. 1879-1888
Author(s):  
Tuan Anh Nguyen ◽  
Doan Thi Thuy ◽  
Ngo Tran Thien Quy ◽  
Lan Ching Yin
Keyword(s):  
Earth Science ◽  
Volcanic Rocks ◽  
Volcanic Belt ◽  
Major Elements ◽  
Island Arc ◽  
Geochemical Data ◽  
Viet Nam ◽  
Volcanic Island ◽  
Current Time ◽  
Continental Plate

Introduction: Extrusive volcanic rocks, such as dacite, andesite, basalto-andesite, basalt… of Chau Thoi and Nui Gio hills in Bien Hoa and Binh Phuoc provinces, southern Viet Nam, characterize volcanic island arc rocks. These rock suites formed as the convergent tectonic between the Indochina and Sibumasu geological blocks. Methods: Geochemical data of rock samples collected on the field were examined and analyzed by the Academia Sinica I E S (Institute of Earth Science, Taiwan and processed with a GCD kit (Geochemical Data Toolkit) to ascertain their characteristics and geotectonic setting. Result: Geochemical data both in major elements and trace elements of the Chau Thoi – Nui Gioshow a specific characteristic of a volcanic island arc environment. Discussion: Chau Thoi and Nui Gio rocks are suitable to correlate to the Permian Thailand Loei Phetchabun volcanic belt. However, at the current time, Chau Thoi and Nui Gio rocks have been classified as Deo Bao Loc formation - late Jurassic to early Cretaceous in ages - belong Truong Son magmatic belt. This magmatic belt resulted from the Yanshanian orogeny by the subduction of the Paleo-Pacific oceanic plate beneath the Eurasia (Indochina) continental plate. More studies needed to be performed, specially geochronological data to support the study. Conclusion: Chau Thoi and Nui Gio rock suites characterize volcanic island arc rocks, products of a convergence tectonic between Indochina and Sibumasu blocks. They are remnants of the Thailand Loei Phetchabun volcanic belt, the first time reported in Vietnam.

Evolution of a Middle Jurassic volcanic arc: stratigraphic, isotopic, and geochemical characteristics of the Harrison Lake Formation, southwestern British Columbia

1995 ◽  
Vol 32 (10) ◽  
pp. 1759-1776 ◽  
Author(s):  
J. Brian Mahoney ◽  
Richard M. Friedman ◽  
Sean D. McKinley
Keyword(s):  
British Columbia ◽  
Middle Jurassic ◽  
Volcanic Rocks ◽  
Explosive Volcanism ◽  
Eastern Coast ◽  
Geochemical Data ◽  
Isotopic Data ◽  
Volcanic Arc ◽  
Fine Grained ◽  
Lake Formation

The Harrison Lake Formation is an Early to Middle Jurassic volcanic-arc assemblage unconformably overlying Triassic oceanic basement in the eastern Coast Belt of southwestern British Columbia. The formation is subdivided into four members including, in ascending order, the Celia Cove Member (conglomerate), the Francis Lake Member (fine-grained strata), the Weaver Lake Member (flows and breccias), and the Echo Island Member (pyroclastic and epiclastic strata). New biostratigraphic constraints pinpoint the initiation of volcanism to late early Toarcian. U–Pb geochronology demonstrates the arc was active until at least late Bajocian–early Bathonian time (166.0 ± 0.4 Ma), and that the timing of arc volcanism strongly overlaps emplacement of both hypabyssal intrusions (Hemlock Valley stock) and deep-seated plutons (Mount Jasper pluton) within and adjacent to the arc. Geochemical data indicate the arc is of medium- to high-K calc-alkaline affinity, and is strongly light rare earth element enriched (LaN/YbN = 1.5 – 2.5). Nd and Sr isotopic data from primary volcanic rocks demonstrate the juvenile nature of the magmatic system, but isotopic data from associated fine-grained sedimentary rocks suggest temporally controlled variations in isotopic composition interpreted to represent two-component mixing between juvenile volcanic detritus and a more evolved detrital component. The succession of facies in the Harrison Lake Formation records initial basin subsidence in the Early Jurassic, initiation of explosive volcanism in the late early Toarcian, a change to effusive volcanism in the early Aalenian, and late-stage explosive volcanism in the late Bajocian. The Harrison Lake Formation contains mesoscopic folds and overturned bedding that are absent in the overlying Callovian Mysterious Creek Formation, strongly suggesting the existence of a regional Bathonian deformational event in the southern Coast Belt.

scholarly journals In-process detection of grinding burn using machine learning

2021 ◽  
Author(s):  
Emil Sauter ◽  
Erkut Sarikaya ◽  
Marius Winter ◽  
Konrad Wegener
Keyword(s):  
Machine Learning ◽  
Machine Learning Algorithms ◽  
Limiting Factors ◽  
Process Time ◽  
New Approach ◽  
Time Frequency ◽  
Grinding Burn ◽  
Process Measurement ◽  
Feature Selector ◽  
Process Detection

AbstractThe improvement of industrial grinding processes is driven by the objective to reduce process time and costs while maintaining required workpiece quality characteristics. One of several limiting factors is grinding burn. Usually applied techniques for workpiece burn are conducted often only for selected parts and can be time consuming. This study presents a new approach for grinding burn detection realized for each ground part under near-production conditions. Based on the in-process measurement of acoustic emission, spindle electric current, and power signals, time-frequency transforms are conducted to derive almost 900 statistical features as an input for machine learning algorithms. Using genetic programming, an optimized combination between feature selector and classifier is determined to detect grinding burn. The application of the approach results in a high classification accuracy of about 99% for the binary problem and more than 98% for the multi-classdetection case, respectively.

Sign in / Sign up

Export Citation Format

Share Document