University of Twente Student Theses

Login

Using Unsupervised Learning to predict the success rate of geothermal drilling operations

Lange, R. de (2022) Using Unsupervised Learning to predict the success rate of geothermal drilling operations.

Full text not available from this repository.

Full Text Status:Access to this publication is restricted
Abstract:Geothermal Drilling has become an increasingly popular subject when looking for long-term sustainable sources of energy, as to combat the climate crisis currently affecting our world. In collaboration with Radial Drilling Europe, this report seeks to analyze data gathered from geothermal drilling operations by means of Clustering algorithms using Unsupervised Learning. The work done in this report builds upon previous work reported in [7] where the so-called Mean Shift (MS) algorithm was adopted. Here, we aim to explore alternative methods, as well as provide a detailed documentation of the subject matter. Particular attention was given to Expectation Maximization (EM) which appears a promising algorithm for drilling applications. The performance of EM was compared to that of MS on well-known benchmarks and found to be promising.
Item Type:Essay (Bachelor)
Clients:
Radial Drilling Europe B.V., Gouda, The Netherlands
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Programme:Applied Mathematics BSc (56965)
Link to this item:https://purl.utwente.nl/essays/89417
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page