Total organic carbon from well logging - statistical approach, Polish shale gas formation case study
by Jadwiga A. Jarzyna; Paulina I. Krakowska; Edyta Puskarczyk; Kamila Wawrzyniak-Guz; Marcin Zych
International Journal of Oil, Gas and Coal Technology (IJOGCT), Vol. 22, No. 2, 2019

Abstract: Advanced statistical methods - artificial neural networks (ANN) and support vector machines (SVM) were used to calculate total organic carbon (TOC) on the basis of well logging. Data from three wells from the Silurian and Ordovician formations in the Baltic Basin from the north Poland were used. In learning procedures TOC data as Rock-Eval pyrolysis results were applied. Research was undertaken in four steps aiming to determine the best ANN in aspect of number and type of input variables. Regarding increase of cases number used in learning process data from two wells were combined and next, determined ANN and SVR were used to predict TOC. There were also made tests of number of input variables (results of standard and sophisticated well logs and laboratory data). Results obtained using standard logs when number of available cases for learning was big enough did not gave way to results based on very many input variables. [Received: October 29, 2016; Accepted: October 21, 2017]

Online publication date: Mon, 07-Oct-2019

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Oil, Gas and Coal Technology (IJOGCT):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com