Development of a computer program for machine learning based analysis of well log data | |
| Author | Ratnayake, Dhyan Ruwantha |
| Call Number | AIT Thesis no.GE-19-12 |
| Subject(s) | Artificial intelligence--Computer programs Machine learning--Computer programs Petroleum engineering |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Geotechnical and Earth Resources Engineering with area of specialization in Geosystem Exploration and Petroleum Geoengineering |
| Publisher | Asian Institute of Technology |
| Abstract | Artificial intelligence (AI) and machine learning (ML) have the potential to reshape the oil and gas exploration and production landscape. Once viewed as a promising novelty, AI and ML are not far away from becoming mainstream for all exploration and production companies. Earlier many researchers have worked on using intelligent analyses such as Artificial Neural Network (ANN), Deep Learning (DL), Fuzzy, Genetic Algorithm (GA) in well log interpretation, which are supposed to be effective for large data sets. Random Forest (RF) algorithm has not ever been tried and applied in well log analysis. In this research, a code in Python language was developed, which has four modules for full interpretation of well log data, ANN, RF and RPT analysis. The created modules were applied and tested using a published data set of a clastic reservoir (Darling, 2005) and two real data sets from Nam Con Son (NCS) basin and Cuu Long (CL) basin, Vietnam. The full interpretation module was able to perform well log interpretation to calculate porosity, water saturation and permeability using different methods. Same well log answers of the reservoir zone were predicted by the RF analysis, compared with those obtained by the ANN analysis and validated with the available core measurements. It was found that there is a significant improvement in running time and accuracy for the RF analysis compared to those results by ANN analysis. The RPT module was able to successfully construct two RPTs based on Odegaard & Avseth (2003) method and using modified Gassmann equation (Giao et al., 2019). |
| Year | 2020 |
| Type | Thesis |
| School | School of Engineering and Technology (SET) |
| Department | Department of Civil and Infrastucture Engineering (DCIE) |
| Academic Program/FoS | Geotechnical Engineering (GE) |
| Chairperson(s) | Pham Huy Giao; |
| Examination Committee(s) | Chao, Kuo-Chieh;Avirut Putiwongrak; |
| Scholarship Donor(s) | Asian Institute of Technology Fellowship; |
| Degree | Thesis (M. Eng.) - Asian Institute of Technology, 2020 |