Event Summary
Pipeline integrity and risk professionals are under increasing pressure to do more with existing asset and inspection data—while also meeting regulatory expectations and improving decision quality. However, many lack a clear understanding of how machine learning fits into current processes or how to confidently apply and validate these models.
Without the ability to effectively leverage advanced analytics, organizations rely on static or incomplete risk models, leading to missed risk indicators, inefficient inspection prioritization, and challenges defending results during audits or reviews. This can increase operational risk, reduce ROI on data, and limit confidence in decision-making.
This webinar provides a practical, real-world introduction to how machine learning can be applied to pipeline integrity and risk. Through live demonstrations using actual gas transmission use cases, participants will see how models are built, validated, explained, and integrated alongside existing risk frameworks—removing the mystery and making the technology actionable.
Participants will be able to better evaluate how machine learning can enhance their current integrity and risk processes, improve inspection prioritization, and support defensible, data-driven decisions. They will leave with a clear understanding of how to apply these concepts within their own systems and whether to advance into more hands-on implementation.
What You Will Gain
- A clear understanding of how machine learning applies to pipeline integrity and risk management
- Insight into real-world use cases (e.g., third-party damage prediction, corrosion growth, QRA)
- Knowledge of how models are built, validated, and explained in practical terms
- Awareness of how to integrate ML with existing risk and compliance frameworks
- Confidence in evaluating and defending data-driven decisions
- A preview of hands-on applications available in the full 1.5-day course
What the 1.5-Day Course Adds (Hands-On)
- Day 1: the full process end-to-end — data quality, sampling, partitioning, cross-validation, model tuning, and deterministic validation, on your pc
- Day 2: attendee-selected use cases — TPD, EC corrosion, coating prediction, SCC (supervised and unsupervised), CP time series, dig-cost prediction, PHMSA consequence modeling, and ML-based QRA — run against example or your own data
Who Should Attend
- Integrity engineers and risk analysts
- Corrosion and cathodic protection specialists
- GIS and data analysts supporting integrity programs
- Integrity and risk program managers responsible for oversight and decision-making
- Anyone responsible for building, running, or defending pipeline integrity or risk models
Attendees will receive 1 Professional Development Hour (PDH) upon completion.
Meet the Instructor
Mike Gloven
Managing Partner, Pipeline-Risk (PLR)
Mike Gloven is Managing Partner of Pipeline-Risk, a provider of machine learning based integrity management and risk solutions for the oil, gas and water industries. He’s a risk and asset management practitioner with more than 30 years of experience working as an asset and integrity manager, technical consultant, software developer, business owner and energy company executive. Mike is a frequent speaker on machine learning based risk & integrity management and has led the development of numerous technology-based solutions currently in use in the energy industry. Mike is professional engineer and holds bachelor’s degree in mechanical engineering from Louisianna State University.
About Pipeline-Risk (PLR)
Pipeline-Risk (PLR) is an engineering and technology company serving the oil, gas, and water pipeline industries. The company has completed risk projects across hundreds of thousands of miles of pipeline in North and South America using its ML.ai machine learning platform. The objective of ML.ai is to improve the identification, prediction and mitigation of risks for the purposes of improved safety, reliability and cost effectiveness of critical infrastructure.
