9:00 AM - 9:15 AM | |
9:15 AM - 10:00 AM | - Understanding Machine Learning capabilities across upstream, midstream, and downstream operations
- Addressing the impact of Machine Learning adoption on the new generation of engineers and scientists
- Accelerating and scaling use across value chains |
10:00 AM - 10:30 AM | - Understanding the suitability of Machine Learning across Oil & Gas operations
- Reviewing current in-house technologies to achieve the same goals
- Considering the current state of datasets |
10:30 AM - 11:00 AM | |
11:00 AM - 11:40 AM | - Exploring factors necessary to enable successful decisions
- Identifying opportunities in mature oilfields using data
- Differentiating between cost optimization and abandonment operations |
11:40 AM - 12:10 PM | - Designing intelligent wells
- Leveraging AI algorithms to achieve better production rates
- SoftServe’s approach to artificial lift optimization |
12:10 PM - 1:10 PM | |
1:10 PM - 1:30 PM | - Machine Learning, its current status, and future learnings and opportunities
- Progressing from idea to actualization
- Unlocking the power of predictive maintenance
- Reviewing Aramco’s R & D projects in the upstream Oil & Gas sector |
1:30 PM - 1:50 PM | - Highlighting the limitations of traditional seismic inversion
- Improving the accuracy and reducing cycle times through automation
- Training datasets to predict lithology, porosity, and fluid type
- Comparing results from a synthetic dataset and a Gulf of Mexico case study |
1:50 PM - 2:10 PM | - Seismic inversion as a bridge from geological knowledge to reservoir modelling
- Challenges and uncertainties in seismic inversion
- Conventional vs ML methods in quantifying uncertainty |
2:10 PM - 2:30 PM | - Operator and oilfield service company perspective on the impact of conventional methods on the economic attractiveness of wells
- Overcoming field challenges by turning them into opportunities
- Making a business case for Machine Learning as a solution compared to other technologies |
2:30 PM - 3:00 PM | |
3:00 PM - 3:15 PM | - Maximizing natural gas-fired power plant dispatch production using Machine Learning and Artificial Intelligence
- Developing tailor-made advanced tools and facilitators overcoming training hurdles
- Increasing the profitability of combined cycle power generation plants
- Optimizing Day Ahead Energy Market Offers by comparing results generated by multiple RL agents using different algorithms |
3:15 PM - 4:00 PM | - Planning for carbon-neutral operations and automated reporting
- Consolidating carbon emissions across value chains
- Understanding how Machine Learning can accelerate ESG obligations |
4:00 PM - 4:30 PM | - Evaluating Machine Learning enabled technologies currently being used in CO2 storage
- Planning for low-carbon operations
- Use case highlighting the application of Machine Learning in CO2 emission predictions |
4:30 PM - 4:45 PM | - Untapped potential in HSE & Operations using Machine learning
- What Machine Learning can/can't do in HSE & Operations
- Why Managers and Engineers synergy is crucial for successful implementation of new technology
- Real use cases and success stories with PySAFETY- PHA Solution and PyRISK - QRA solution
|
4:45 PM - 4:55 PM | |
5:00 PM - 6:00 PM | |
9:00 AM - 9:05 AM | |
9:05 AM - 9:35 AM | - Harnessing the power of upstream, midstream, and downstream data to enhance business intelligence and provide actionable insights
- Understanding how various internal teams collect and use their data
- Identifying analytical tools and technology to facilitate Machine Learning projects |
9:35 AM - 10:05 PM | - Comprehensive architectural framework for real time optimization and operation
- Hybrid modelling, which combines machine learning and first principles modelling
- Practical use cases depicting the problems, latency in monitoring in drilling wells in real time |
10:05 AM - 10:35 AM | - Understanding Chevron Phillips Chemical Company’s driver for the Rheometer implementation
- Discussing project challenges and learnings
- Building data-driven frameworks for predicting drilling fluid's behaviour
- Standardizing properties by exploring machine learning algorithms
- Use case highlighting the transition from pilot to full implementation |
10:35 AM - 11:05 AM | |
11:05 AM - 11:20 AM | - Facilitating acceptance and transition to fully digitized and automated upstream operations
- Ensuring correct system responses to gain trust from operators and production engineers
- Demonstrating integrated machine learning and analytics enables full automation of artificial lift and other components of upstream operations
|
11:20 AM - 12:05 PM | - Discussing current supply chain complexities and uncertainties
- Modernizing Supply Chains with AI & Machine Learning for Resilience and End-To-End Optimization
- Linking statistics and relationships- injecting accuracy through collaboration with subject matter experts
|
12:05 PM - 1:05 PM | |
1:05 PM - 1:35 PM | - Demonstrating the application of DRL in inventory management and shipping scheduling.
- Comparing the DRL approach with conventional reorder policy/optimization methods.
- Using DRL to make robust decisions against disruptions in demand and supply. |
1:35 PM - 2:20 PM | - Learning how Machine Learning is deployed, the challenges, and opportunities
- Discussing competitive differentiators that drive agility
- Practical use cases of deployment |
2:20 PM - 2:50 PM | |
2:50 PM - 3:20 PM | - Understanding how Dow attracts and retains talent
- Deploying Proofs of Concept within the areas of IoT, digital thread (sourcing data and data accuracy), as well as data analytics (machine learning and decision-making)
- Implementing recruitment and compensation strategies for entrepreneurs’ software engineers, and people with operations experience |
3:20 PM - 3:50 PM | |
3:50 PM - 4:35 PM | - Utilizing Digital twin and ML technologies to create solid digital cores, lower operational costs, optimize processes, and enhance real-time decision making
- Creating operational backbones across value chains
- Sharing real-life examples of the ROI of integrating these technologies |
4:35 PM - 4:40 PM | |