Description

• Minimum Specifications: Participants are required to have access to modern laptops or PCs with at least 16 GB RAM, a discrete GPU or an integrated GPU within Apple Silicon M1 Pro, and 40 GB of free disk space
• Recommended Specifications: For optimal performance, it is recommended that participants use a computer with 16 GB+ of RAM, a modern discrete Nvidia GPU or an integrated GPU Apple Silicon M1 Pro or newer, and 40 GB of free disk space

Designed for you, if you are...

• A reservoir engineer, geologist, petrophysicist, production engineer, drilling engineer, pipeline engineer, process engineer, or another technical professional from the Upstream, Midstream, or Downstream sectors of the Oil & Gas industry.
  This course is ideal if you're seeking to build a solid foundation in neural networks, deep learning, and machine learning operations (MLOps), while also learning how to define high-impact AI business cases that deliver real value to your company.

• Participants should have strong domain knowledge with a minimum of 5 years of oil and gas experience
• Prior programming experience is a strong advantage
• Prior experience in data science and machine learning is an advantage. If a participant does not have basic knowledge of data science and machine learning, it is recommended to attend the following course upfront:
  Applied Machine Learning and Data Science for Upstream Professionals.

How we build your confidence

• Complex AI business case frameworks are clearly explained and presented step-by-step, demonstrating how top consulting firms approach strategy, planning, execution, and impact measurement, enabling you to confidently apply these proven methods in your own AI projects
• Core deep learning algorithms and architectures are comprehensively covered and supported by practical, reusable code examples based on real-world Oil & Gas datasets, effectively bridging theory with hands-on learning
• Comprehensive MLOps practices are explored in detail, equipping you to build, deploy, and maintain end-to-end machine learning solutions, from development data pipelines to model performance monitoring and user interface design

The benefits from attending

• Identify and scope high-impact deep learning opportunities and develop compelling AI business cases across Upstream, Midstream, and Downstream Oil & Gas domains
• Design and implement advanced neural network architectures using TensorFlow and Keras, tailored to Oil & Gas challenges
• Apply cutting-edge deep learning techniques, including Generative AI, Intelligent Agents, Large Language Models, and Reinforcement Learning, to solve complex industry problems
• Build and operationalise robust end-to-end MLOps pipelines that support scalable and maintainable AI solutions

Topics

• Deep Learning fundamentals and the TensorFlow ecosystem
• Deep Feed Forward neural networks
• Bayesian neural networks and Probabilistic Forecasting
• Anomaly detection
• MLOps: data pipelines, hyperparameter tuning, and tracking modelling experiments

• Setting up Machine Learning projects
• Forecasting reservoir fluid saturation pressure
• Lithofacies classification from well log data
• Production forecasting for unconventional reservoirs
• Detecting non-stationary production regimes in production and injection wells

• Set up a machine learning project to ensure the reproducibility and model accuracy
• Develop regression and classification models using the Tensorflow framework
• Build probabilistic deep learning models to quantify forecast uncertainty and support risk-aware decision-making
• Implement anomaly detection techniques using deep learning models
• Interpret deep learning model outputs and communicate predictions to a non-technical audience
• Use Docker and code templates to streamline experimentation and operational deployment

• A top-tier consultancy framework for structuring AI projects
• Developing an AI business case tailored to Oil & Gas operations
• Predictive maintenance solutions for critical Oil & Gas equipment
• AI business case impact assessment

• Developing a practical framework for mapping AI opportunity areas to an operational financial model
• Business case walkthrough: quantifying value creation and ROI for a predictive maintenance AI-based initiative
• Designing and implementing a predictive maintenance solution for Electrical Submersible Pumps (ESP)
• Impact assessment and risk appetite definition

• Apply a consulting mindset to structure AI initiatives that align with business strategy and drive measurable value
• Design and implement predictive maintenance models that minimise downtime and extend equipment life through deep learning
• Quantify AI project impact, build persuasive business cases, and navigate organisational risk appetite
• Embed AI solutions into operational workflows to achieve lasting business transformation
• Ensure model reliability and reproducibility through robust MLOps pipelines and best practices

• Deep Convolutional Neural Networks (CNN)
• Object detection architectures and their applications
• Semantic and instance segmentation techniques
• MLOps for Computer Vision: model serving, monitoring, and cross-platform deployment

• Diagnosing sucker-rod pump performance using dynamometer card images.
• Predicting rock permeability from petrographic thin-section images
• Detecting and monitoring Oil & Gas infrastructure with satellite imagery
• Identifying oil spills using drone footage and georeferenced aerial images
• Deploying real-time computer vision models to edge devices such as smart cameras and IoT sensors

• Develop CNN-based classification and regression models for tasks such as seismic interpretation, digital core analysis, borehole image interpretation, pipeline leakage detection, and safety surveillance in hazardous areas
• Build object detection solutions to locate equipment, infrastructure, or anomalies in visual Oil & Gas data
• Create segmentation models to delineate complex geological and engineering structures
• Operationalise computer vision solutions by deploying models to edge environments, ensuring performance under real-world constraints
• Integrate computer vision models into broader AI systems for automated monitoring and decision support

• Text classification
• Named Entity Recognition (NER)
• Prompt Engineering
• Retrieval-augmented generation (RAG)
• Fine-Tuning open-source Large Language Models
• MLOps: building the interface for a deep learning model and dashboarding

• Classifying Oil & Gas text documents by topics or relevance
• Training a custom Named Entity Recognition (NER) model to extract Oil & Gas domain-specific entities
• Building a Natural Language Interface to query production and geological databases
• Applying Advanced Prompting techniques to analyse structured and unstructured Oil & Gas data
• Developing RAG solution to enhance the accuracy and reliability of LLMs
• Fine-tuning the Large Language Models (LLMs) using proprietary datasets

• Automatically classify technical documents, such as reports, logs, and notes, by topic to enable alerting, streamline workflows, and systematise information
• Extract targeted Oil & Gas–specific information from unstructured text using advanced NLP techniques
• Leverage pre-trained Large Language Models (LLMs) to extract insights from large volumes of Oil & Gas data stored in internal databases
• Design and deploy a Retrieval-Augmented Generation (RAG) system that enables natural language interaction with reports, drilling summaries, and incident records
• Fine-tune open-source LLMs efficiently on proprietary datasets to improve relevance, accuracy, and domain alignment

• Reinforcement learning
• Generative AI with multimodal models (text, image, audio)
• Intelligent LLM Agents and tool-use capabilities
• Multi-agent AI Teams and collaborative agent systems

• Optimise geosteering and well placement using reinforcement learning techniques
• Detecting water production mechanisms in production wells
• Develop an autonomous AI agent for geological and reservoir simulation models analysis
• Build a team of specialised agents (Upstream, Midstream, Downstream) to optimise the operational costs in a vertically integrated company

• Apply reinforcement learning to optimise drilling parameters and well placement strategy.
• Build a multimodal generative AI model capable of interpreting complex multi-source data.
• Develop intelligent agents that autonomously use tools, retrieve information, and complete domain-specific tasks across the Oil & Gas value chain.
• Design and implement collaborative agent teams to support cross-functional optimisation and reduce total operational costs in vertically integrated operations