Last modified: 25 Oct 2024 13:16
Fundamental and applied aspects of artificial intelligence (AI), machine learning and data science for petroleum engineers. Use of data from sensors, digital twins and other digital domains during seismic data acquisition, drilling, wireline and logging operations, well testing, reservoir surveillance, production and other oil field operations. Students learn how to optimise sustainable subsurface petroleum production using AI and data science tools to realize net-zero energy future.
| Study Type | Postgraduate | Level | 5 |
|---|---|---|---|
| Term | Second Term | Credit Points | 15 credits (7.5 ECTS credits) |
| Campus | Aberdeen | Sustained Study | No |
| Co-ordinators |
|
||
This course presents the fundamental and applied aspects of artificial intelligence (AI), machine learning and data science for the petroleum industry practitioners. It covers core AI concepts, including deep learning, machine learning, and neural networks. It examines application AI across multiple domains, such as natural language processing (NLP), computer vision and robotics, highlighting how these techniques drive innovation in the petroleum industry. Concepts of generative AI models, including large language models and their capabilities will be introduced. The transformative impact of AI, including generative AI, on oil and gas operations processes will be evaluated. Furthermore, the course will present how data science is used to gather, clean, organise, and analyse data with the goal of extracting helpful insights and predicting expected outcomes within the petroleum industry. It underpins how big data generated in the industry can be effectively used as part of predictive maintenance, oil and gas production management, and monetisation of petroleum exploration and exploitation processes. Use of data obtained from sensors, digital twins and other digital domains during seismic acquisition, drilling, wireline and logging operations, well testing, reservoir surveillance, production and other oil field operations will be explored. Students learn how to optimise sustainable subsurface petroleum production using AI and data science tools to realise net-zero energy future. The course also explores AI ethics, governance, regulations and prevalent concerns and issues surrounding the evolution of AI within the industry.
| Assessment Type | Summative | Weighting | 60 | |
|---|---|---|---|---|
| Assessment Weeks | Feedback Weeks | |||
| Feedback |
Word count: 7,000 Feedback will be provided via MyAberdeen and class discussion. |
|||
| Knowledge Level | Thinking Skill | Outcome |
|---|---|---|
| Conceptual | Analyse | mport and clean data sets, analyse and visualise data, and build machine learning models using data scientists’ tools, languages, and such as Python and SQL |
| Factual | Remember | Describe what AI and data science is and explain the core concepts relating to the petroleum industry |
| Reflection | Evaluate | Evaluate the ethical issues, limitations, and legal and legislative concerns surrounding AI |
| Assessment Type | Summative | Weighting | 40 | |
|---|---|---|---|---|
| Assessment Weeks | 38 | Feedback Weeks | ||
| Feedback |
Word Count: 5,000 Feedback will be provided via MyAberdeen and class discussion. |
|||
| Knowledge Level | Thinking Skill | Outcome |
|---|---|---|
| Factual | Remember | Describe what AI and data science is and explain the core concepts relating to the petroleum industry |
| Procedural | Apply | Demonstrate how AI, machine learning and data science application in the petroleum industry can transform operational processes |
There are no assessments for this course.
| Assessment Type | Summative | Weighting | ||
|---|---|---|---|---|
| Assessment Weeks | Feedback Weeks | |||
| Feedback | ||||
| Knowledge Level | Thinking Skill | Outcome |
|---|---|---|
|
|
||
| Knowledge Level | Thinking Skill | Outcome |
|---|---|---|
| Factual | Remember | Describe what AI and data science is and explain the core concepts relating to the petroleum industry |
| Procedural | Apply | Demonstrate how AI, machine learning and data science application in the petroleum industry can transform operational processes |
| Conceptual | Analyse | mport and clean data sets, analyse and visualise data, and build machine learning models using data scientists’ tools, languages, and such as Python and SQL |
| Reflection | Evaluate | Evaluate the ethical issues, limitations, and legal and legislative concerns surrounding AI |
We have detected that you are have compatibility mode enabled or are using an old version of Internet Explorer. You either need to switch off compatibility mode for this site or upgrade your browser.
