Session has ended. Available on-demand.
Session has ended. Available on-demand.
Session has ended. Available on-demand.
Session has ended. Available on-demand.
Managing asset performance and risk effectively often requires an analysis of multiple spatiotemporal data sets including IoT, telematics, multispectral, lidar, and weather. In the case of Utilities, millions of assets of varying ages and types throughout their service territories must be closely monitored not only to improve operational efficiency and customer service but also to avoid catastrophic risk. The moment assets are installed in the field, the risk of failure varies based not only on intrinsic characteristics but also on maintenance and environmental exposure. These risk management processes are constrained by the limited spatial and temporal computational ability of CPU based systems used to inform a complex cadence of visual inspection and examination patrols. These paper-based processes have proven to be ineffective. The result is that risks continue to increase and costs grow. To progress further, utilities must use rigorous analytical methods to assess vegetation risks, identify mitigation activities and measure performance. In this session we will show how OmniSci overcomes these challenges and has opened an easy path to the digital transformation of asset risk and performance decision management. We will demonstrate the risk-informed and performance-based future of vegetation management enabled by OmniSci GPU acceleration and insitu rendering that delivers: Continuous Monitoring and Analysis-on-Demand Services ● Analytical access to full LIDAR data capable of scaling across entire service area ● Continuous multispectral satellite monitoring (for tree health) ● Real-time and Forecast Data Integration (for wind, etc.) ● Streaming multiple data sets at scale ● Real-time, interactive visual monitoring and analytics ○ Process/visualize disaggregate data (cm to meters, not hectares to square km) ○ Proven capability to scale (to 120m trees, 4.2 polys) ○ Robust round-trip connections to Data Science pipelines
.svg)
