COURSE UNIT TITLE

: GEOPHYSICAL APPLICATIONS OF ARTIFICIAL NEURAL NETWORK

Description of Individual Course Units

Course Unit Code Course Unit Title Type Of Course D U L ECTS
GPE 5036 GEOPHYSICAL APPLICATIONS OF ARTIFICIAL NEURAL NETWORK ELECTIVE 2 2 0 7

Offered By

Graduate School of Natural and Applied Sciences

Level of Course Unit

Second Cycle Programmes (Master's Degree)

Course Coordinator

PROFESSOR DOCTOR MÜJGAN ŞALK

Offered to

Geophysical Engineering

Course Objective

In recent years, science and engineering in the field of Artificial Neural Networks are widely used in the method, examples of incidents related to caring for them to make generalizations about the event, when faced with examples of information gathering, and later learned he had never seen examples of using the information about it can be decided.Method is applied to the solution of many problems in recent years, science has led to the formation of the different viewpoints.
Especially predict-front estimation, modeling, and the success and applicability of the method has been tested in areas such as data processing.
In this lesson, Artificial Neural Networks in Geophysics preliminary estimation, modeling and data processing Using the displayed order.

Learning Outcomes of the Course Unit

1   To understand the mathematical basis of artificial neural network
2   Define the structure of artificial neural networks
3   Explain how to use geophysical data of the artificial neural networks
4   To Establish the structure of Artificial Neural Network according to the characteristics of the geophysics problem
5   Apply of geophysical problems in artificial neural networks and interpret the results

Mode of Delivery

Face -to- Face

Prerequisites and Co-requisites

None

Recomended Optional Programme Components

None

Course Contents

Week Subject Description
1 Introduction of artificial Neural Network
2 Structure of Artificial Neural Networks
3 Learning Processes,homework
4 Multilayer Perceptrons (MLP)
5 Radyal-Basis Function Networks (RBF),homework
6 Alternative Network Structures and Learning Rules,Homework
7 Application of Artificial Neural Networks in Gravity Propection Method
8 Application of Artificial Neural Networks in Gravity Propection Method,Homework
9 Application of Artificial Neural Networks in Magnetic Propection Method, Homework
10 Application of Artificial Neural Networks in Magnetic Propection Method
11 Midterm Exam
12 Application of Artificial Neural Networks in Seismic Propection Method
13 Student presentation
14 Application of Artificial Neural Networks in Time Series

Recomended or Required Reading

M.M.POULTON, Computational Neural Networks for Geophysical Data Handbook of Geophysical Exploration, Volume 30, Pergamon Press, 2001.
William SANDHAM and Miles LEGGETT., Geophysical Applications of Artificial Neural Networks and Fuzzy logic, Kluwer Academic Publishers,2003

Planned Learning Activities and Teaching Methods

Lecturer, Assignment and Presentation, Exam

Assessment Methods

SORTING NUMBER SHORT CODE LONG CODE FORMULA
1 ASG ASSIGNMENT
2 PAR PARTICIPATION
3 FIN FINAL EXAM
4 FCG FINAL COURSE GRADE ASG * 0.40 +PAR * 0.10 +FIN * 0.50
5 RST RESIT
6 FCGR FINAL COURSE GRADE (RESIT) ASG * 0.40 +PAR * 0.10 + RST * 0.50


*** Resit Exam is Not Administered in Institutions Where Resit is not Applicable.

Further Notes About Assessment Methods

None

Assessment Criteria

ÖÇ1, ÖÇ2, ÖÇ3 midterm Exam
ÖÇ4 ve ÖÇ5 homework , presentation

ÖÇ1,ÖÇ2,ÖÇ3,ÖÇ4, ÖÇ5 Final Exam

Language of Instruction

English

Course Policies and Rules

To be announced.

Contact Details for the Lecturer(s)

Dokuz Eylül Üniversitesi Mühendislik Fakültesi Jeofizik Mühendisliği Bölümü Tınaztepe
Kampüsü 35160 Buca-IZMIR
mujgan.salk@deu.edu.tr

Office Hours

Monday 10-12, Thursday 13-15 hours

Work Placement(s)

None

Workload Calculation

Activities Number Time (hours) Total Work Load (hours)
Lectures 13 2 26
Tutorials 13 2 26
Preparation for final exam 1 10 10
Preparations before/after weekly lectures 13 4 52
Preparation for midterm exam 1 5 5
Preparing presentations 1 10 10
Preparing assignments 5 7 35
Final 1 4 4
Midterm 1 5 5
TOTAL WORKLOAD (hours) 173

Contribution of Learning Outcomes to Programme Outcomes

PO/LOPO.1PO.2PO.3PO.4PO.5PO.6PO.7PO.8PO.9PO.10PO.11PO.12PO.13
LO.15
LO.24
LO.353
LO.45443
LO.55443