Real-time Analytics
Duke Energy needed to go beyond current US EPA regulations and replace slow physical inspection-based leak surveys with a rigorous end-to-end way to detect, monitor, and remediate methane emissions across its natural gas distribution assets.
Reported impact
The platform is already giving Duke Energy more accurate, holistic decision support and near real-time leak detection, helping crews find leaks in minutes instead of days, repair them faster, and improve resilience in gas operations while supporting methane-reduction goals.
Accenture, Avanade, and Microsoft helped Duke Energy build a first-of-its-kind, end-to-end Azure-based cloud platform for its natural gas distribution business. The implementation ingests satellite monitoring data and operating signals tied to pipelines, gas meters, and other assets, then uses analytics and artificial intelligence to quantify baseline methane emissions, prioritize likely leaks, and attach precise geolocation context for field response. The platform packages the resulting insights into graphic dashboards so leadership and operations teams can review findings at different levels of detail and coordinate remediation. Instead of relying only on physical inspections, Duke Energy now has a near real-time monitoring workflow that detects issues faster, improves repair prioritization, and provides a shared cloud foundation for wider asset and jurisdiction coverage as the program scales.
Satellite monitoring data and emissions signals from natural gas distribution assets flow into the Azure-based cloud platform, where analytics and AI quantify baseline emissions, prioritize findings, and attach geolocation context. The resulting insights are delivered through graphic dashboards to leadership and operations teams so they can locate leaks quickly and coordinate remediation across pipelines, meters, and other assets.
"The platform is already delivering results with more accurate, holistic insights for leadership decision-making."
"The result is a first-of-its-kind, end-to-end Azure-based cloud platform that monitors baseline methane emissions from natural gas distribution assets (e.g., pipelines, gas meters), using satellite monitoring, analytics and artificial intelligence."
"The solution quantifies and prioritizes findings in graphic dashboards, making data easily consumable at multiple levels of the organization."
"With pinpoint-accurate geolocation data, workers are finding leaks in minutes compared to physical inspection of pipelines and other assets -- and repairing them more quickly."
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
NVIDIA Sample Sep 30, 2026 EPRI EPRI needed to run advanced AI for sensitive utility documents and weather-planning workflows locally, because energy-sector research data could not leave controlled environments and shared compute delays limited how… 150 tokens/sec aggregate across 10 concurrent Power Chat users DGX Spark · Dell Pro Max with GB10 · NVIDIA CBottle 
Accenture Sample Aug 14, 2026 Novartis Novartis needed to unify fragmented data across R&D, manufacturing, commercial, and corporate functions so teams could analyze growing biomedical and operational data sets faster and apply AI to drug development and… 10 days to three days Amazon Web Services (AWS) · Microsoft Azure · analytics tools supported by AI and ML Accenture Sample Aug 13, 2026 Lendlease Group Lendlease needed a scalable way to turn building, occupancy, and workplace data into practical operating decisions as hybrid work, sustainability pressure, and real-estate cost demands reshaped customer expectations. predict the number of attendees in the coming week Podium Property Insights for Workplace (PPI) · building data · cloud-based software-as-a-service (SaaS) 