Machine Learning for Sustainability in Oil & Gas

Introduction to Machine Learning and Sustainability

• Introduction to the history of ML and its importance for sustainability in the oil and gas sector, emphasizing the role of ML in energy transition.
• Study of oil markets with Gapminder tools to understand sustainability challenges and opportunities.
• Clarifying the distinctions and connections between Machine Learning (ML), Artificial Intelligence (AI), and Deep Learning (DL), and discussing how intelligent digital workplaces can contribute to energy transition.
• Initial Python setup, laying the groundwork for hands-on programming throughout the course.

Data Handling and Carbon Emission Analysis

• Introduction to Python basics, including data structures like lists and tuples.
• Use of NumPy for analyzing carbon emission factors, a critical factor in measuring environmental impact.
• Pandas library for handling climate datasets, demonstrating its utility in managing and analyzing environmental data.
• Discussion on location intelligence and greener practices for oil and gas facilities using Python and its libraries.

Visualization and AI Workflows

• Visualization techniques using matplotlib/seaborn on a dataset from a multisensor device in an Italian city, for practical insights into pollution measurement.
• Exploration of AI workflows, comparing supervised and unsupervised learning approaches.
• Applying principal component analysis to a methane emissions dataset to identify key factors contributing to emissions.
• Optional additional practice

Regression Analysis and Classification in AI

• Understanding regression using climate models to predict future trends and patterns.
• Application of clustering on datasets from carbon capture and sequestration sites, an important technique for reducing carbon footprint.
• A demonstration of classification using a chatbot to recognize carbon scope and category, providing a real-world application of NLP.
• Optional extra learning activities

Deep Learning and Professional Responsibilities

• Application of deep learning in NLP, time series, and computer vision, focusing on sustainability.
• Exploration of advancements in deep learning architectures, enhancing the ability to process complex sustainability-related data.
• Case study discussion on Schlumberger Limited's (SLB) energy transition initiatives, providing context for ML's role in industry projects.
• Closing discussions on responsible and explainable AI, intellectual property, legal considerations, and addressing any lingering doubts or questions.