☀️ Day One: Wednesday, April 13, 2022
🎯 Opening Keynote: The Energy of the Future: Digitizing Oil and Gas Operations
- Digitization and Digital Transformation: Trends for 2022
- Digitization and value creation: In need of a shift
- Most urgent priorities for oil and gas companies to achieve true digital transformation
🎯 Panel Discussion: The Road to Net-Zero: The Role Machine Learning Will Play in Facilitating Sustainable Operations
Technology evolution is driving the shift to cleaner energy. The wealth of data generated will provide insight into supply chain visibility, help understand emissions, and abate options better.
- What is the next level for Machine Learning that could transform the industry's outlook?
- Is Machine Learning being implemented for the sake of it? How are energy companies aligning technology strategies and business strategies?
- How to merge business processes, workflows, and contextualized data.
- Collaborating with demand-side services. What is the role will providers play in ensuring targets are met? What are the subsequent significant discussions on the horizon?
🎯 Overcoming the Multivariate Data Hurdle to Reduce to Carbon Emissions
- Can predictive analysis reduce carbon emissions and help meet carbon reduction goals?
- How is Machine Learning used to detect anomalies in offshore production platforms?
- Leveraging Machine Learning and Artificial Intelligence to monitor asset behaviors and lifecycles
🎯
Why Machine Learning Needs Innovation to Work in an Organization
🎯
Technology and Purpose: The Rise of Responsible AlgorithmsAccountability around ESG data can create an opportunity for greater transparency, fewer biases, and more consistent standards. However, data fatigue and inadequate reporting systems can lead companies off course in their sustainability journey.
- How can companies adopt data-driven storytelling?
- Best approaches to quantifying ESG impact
- How can ESG reporting standards be harmonized?
- What information is most useful for engagement with stakeholders?
🎯
Organisational Agility: Developing End-to-End Machine Learning ProjectsMajor priorities with Machine Learning are preparing data, developing a model to train it, and then deploying the model, but what are the components of a successful Machine Learning implementation project?
- Determining the aspect of the value chain requires technological advancements
- Making a business case and getting leadership buy-in
- Integrating and matching vendors
- Structuring and ensuring successful pilots
🎯 Best Practices in Adopting Machine Learning - Challenges and Lessons Learned from BHP
In recent years, the Oil and Gas sector made significant investments in its data analytics and Artificial Intelligence initiatives. However, recent studies show that these initiatives are stalling and have a low return on investment due to misalignment between business needs and the Artificial Intelligence solutions developed, data availability, access, and quality, slow adoption of resolutions by business segments, failure to scale and productionize, and decision makers’ inability to fully understand the value Artificial intelligence can add to their portfolios. This session highlights the success of BHP’s Artificial Intelligence initiatives within E and P and lessons learned from their journey.
🎯 Domino unleashes data science for the world’s most advanced enterprises
From Data Center Modeling to Edge Deployments with Monitoring: Domino Enterprise MLOps for Oil & Gas ML (presented by Dell Technologies and NVIDIA)
The Oil & Gas industry presents unique challenges for developing and deploying valuable models. Heterogenous infrastructure at the edge, complex enterprise architectures, and organizational complexity mean it’s hard to drive a seamless, low-friction machine learning process. Learn how Domino’ end-to-end workflows (powered by Dell hardware) make Enterprise MLOps a reality.
🎯 Transformational and Change Efforts: Why Do They Fail?
Incredible risk and disruption is driving the need for companies to adapt and drive transformational and change efforts. However, the track record and return on these investments are horrible. Al will posit five specific reasons why these efforts fail with references to and examples from the topics being discussed at this conference (big data, machine learning, AI or analytics efforts) – with a goal for attendees to learn how to avoid these issues with the right approach.
🎯 Machine Learning for Improved Offshore Oil and Gas Megaproject Planning: Methods and Application
- Effects of complexity, principal-agent issues, and human cognitive biases on oil and gas megaproject outcomes.
- Machine learning for predictive analytics in oil and gas megaprojects.
- Quantitative cost and schedule risk forecasting and reduction in oil and gas megaprojects.
- Human cognitive biases and corrective measures using machine learning.
- The balance between professional expertise and machine learning.
🎯 Transparent Risk Mitigation
- Blending compatible technologies for better risk analysis
- Establishing shared truths around immutable records
- Applying intelligent traceability through commodity lifecycles
☀️ Day Two: Thursday, April 14, 2022
🎯 Dynamic Strategies for Machine Learning Product Development
🎯 Understanding the Subsurface through Deep Learning-Accelerated Seismic Integration
- Using deep learning to accelerate the process of seismic integration
- Understating subsurface geology
- Identifying potential plays
🎯 Building the Best AI Infrastructure Stack to Accelerate Your Data Science
- Understanding the dynamic resource requirements of Artificial Intelligence/Machine Learning based workloads.
- Helping organizations manage to compute resources such as Graphical Processing Units (GPU’s) to drive better resource allocation and increase cluster utilization.
- Applying advanced scheduling methods to dynamically set priorities and policies to orchestrate jobs better.
🎯 Innovation Talk: Digital Artificial Intelligence Safety Transformation in Oil and Gas Industry
- Why digital artificial intelligence transformation in Health, Safety & Environment should be implemented.
- Reducing time and cost using machine and deep learning.
- Business case: PyHAZOP & PyRISK – how artificial intelligence solutions saved up to 66% in costs.
🎯 Artisan – Artificial Intelligence enabled Engineering Digitalisation Platform
- Using artificial intelligence to read P&IDs and Isometrics of industrial plants to build a digital model "twin" of the plant.
- Creating master asset inventory or master tag list- valve, lines, equipment, I/O, control loops, and 3D models of plants.
- Digitalizing for management change
🎯 Panel Discussion: Leveraging Algorithms to Meet Health and Safety Standards
- How can incident report libraries be strengthened? What information shouldn’t be left out?
- What is a customized reporting system?
- How can collated data be used to develop risk prevention and mitigation strategies?
- Educating operators on the root causes of understand the root causes of hazards and equipment failure
🎯 Panel Discussion: Succeeding in the Supply Chain Evolution
- Shared examples of supply chain transformations highlighting advantages to bottom lines.
- Understanding the current supply chain challenges and risk mitigation techniques.
- Creating procurement strategies to minimize region-specific shortages and supply disruptions.
🎯 Combining Machine Learning & Domain Expertise to Optimize Oil & Gas Assets
- Challenges facing the Artificial Intelligence and Machine Learning for improving oil and gas production.
- Transitioning the existing workforce to have Artificial Intelligence full-scale process.
- Machine Learning & Deep Learning solutions for upstream, midstream, and downstream.
- How Machine Learning can boost & optimize the risk management process.
🎯 The components of Chevron’s Machine Learning Operations and the keys to Getting There
- Unpacking Chevron’s data science history- the early years and beyond the Artificial Intelligence and Machine Learning hype in 2010.
- Building sustainable Machine Learning operations.
- Operationalizing Machine Learning- the creation of roles, partnerships between DS’s and MLE’s and standardizing pipeline delivery.
- Understanding the MLOps maturity model- where is Chevron today, and where are we going?
🎯 Optimizing ESP Operations with Machine Learning to Improve Well Performance
- Applications of Artificial Intelligence and Machine Learning for improving oil and gas production.
- Laredo's business case: Changing the approach to ESP operations.
- Creating a Machine Learning solution for ESP optimization and well production improvement.
- Challenges and key lessons learned from building a Machine Learning solution for ESP optimization.
🎯 Panel Discussion: The Skillset Crisis: Making the Oil and Gas Industry More People-Centric
- How are business models affected by putting employees at the centre of technology changes?
- Transitioning the existing workforce.
- Aligning people with technology- use cases.
- How is transformation redefining the future of work?
- Ramping up efforts to close the skill gap.
