Digital twins are nothing new but have reached the point of wider industry adoption. There are early examples of digital twins applied to manufacturing plants, warehouse operations and even entire city centers to aid operations managers in finding ways to increase efficiency and even reduce costs.
Some of the projects are far more massive in scope, however.
In one new example, Lockheed Martin and Nvidia on Thursday announced a collaboration to `build an artificial intelligence-driven Earth Observations Digital Twin for use by the National Ocean and Atmospheric Administration for monitoring global environmental conditions and extreme weather.
The twin is designed to provide NOAA with high resolution, accurate and timely depictions of conditions around the globe relying on current satellite and ground-based operations. Today, NOAA receives data about land, atmosphere, space weather, ocean and cryosphere and researchers collect the data to observe environmental conditions and changes.
Lockheed Martin’s Open Rosetta3D platform will use AI and machine learning to ingest, format and fuse climate observations into a grid, then detect anomalies. Nvidia’s Omniverse Nucleus will convert this data into the Universal Scene Description approach to enable data sharing between researchers. Also, Lockheed Martin’s visualization platform called Agatha will ingest the data from Omniverse Nucleus to allow users to interact with it.
Lockheed Martin already uses digital twins and AI for government customers to provide actionable intelligence for various missions. The two companies are already collaborating on ways to help fight wildfires by using Lockheed Martin’s AI/ML platforms and command and control with Omniverse.
RELATED: Lockheed helps crews fight wildfires with simulation
“Digital twins will help us solve the world’s hardest scientific and environmental challenges,” said Nvidia’s Dion Harris, lead project manager for accelerated computing.
Google recently described how it is using AI to forecast floods and track wildfires. The company is relying on AI transfer learning processes to take data from drainage basins not specific to where the model is predicting an imminent flood.
RELATED: How Google uses AI to forecast floods and track wildfires