Clustering Considerations in the Machine Learning Workflow – Examples with Exploration Data - скачать в хорошем качестве

Clustering Considerations in the Machine Learning Workflow – Examples with Exploration Data -

Philip Lesslar, Data solutions consultant with Precision DM, presenting in Digital Energy Journal KL forum in October 2019, on Clustering Considerations in the Machine Learning Workflow – Examples with Exploration Data. There is currently a very high interest in machine learning and its potential applications for oil and gas. However, the usefulness of any tool is dependent on its correct application and this is no different with Machine Learning (ML). AI has been making its way into so many aspects of our lives that it is almost taken for granted that its implementation will guarantee success. This is far from the truth and if AI and ML are not used appropriately, it could lead not just to non-success but in the worst case, wrong and costly decisions. This paper focuses on cluster analysis which is a key classification tool, but still just one of many tools and techniques in the ML toolkit, with the aim to highlight the need that aspiring data scientists in the oil and gas domains arm themselves with the necessary knowledge and skills to carry out effective ML projects. Example exploration data are used and should help the audience not only to relate to the points made but also to trigger ideas about how they can approach their own data sets.