HONG KONG BAPTIST UNIVERSITY
FACULTY OF SCIENCE
Department of Computer Science Seminar
Machine Learning Analysis and Prediction in the Oil Well Logging Industry
Dr. Milos Stojmenovic
Department of Computer Science and Electrical Engineering
Date: April 6, 2016 (Wednesday)
Time: 5:30 - 6:30 pm
Venue: WLB211, Wing Lung Bank Building, Shaw Campus
Geologists are essential in the oil industry as they are the ones that predict where to dig, to what depth and how much oil to expect to recover. Surprisingly, they have very few software tools that enable them to perform their jobs with any degree of automation. Working with an oil well logging company, we aimed to analyze how the instrumentation readings in well probes can be used to predict and correct faulty and missing readings, which will ultimately assist geologists to locate and determine the composition of oil reservoirs. Existing 1D features, as well as novel combinations of features were used to analyze the data through the WEKA machine learning tool. We are able to reconstruct missing data with 85% accuracy in our work. In the future, we aim to employ deep learning techniques for this task.
Milos Stojmenovic is an associate professor at the Department of Computer Science and Electrical Engineering at Singidunum University, in Belgrade, Serbia. He received his PhD in Computer Science degree at the School of Information Technology and Engineering, University of Ottawa, in 2008 and was a visiting researcher at Japan's National Institute for Advanced Industrial Science and Technology. He has published more than thirty articles in the fields of computer vision, image processing, and wireless networks. More details can be found at milos.stojmenovic.com.
********* ALL INTERESTED ARE WELCOME ***********
(For enquiry, please contact Computer Science Department at 3411 2385)
Department of Computer Science, Hong Kong Baptist University