# Fuel Innovation in Energy Deliver a reliable supply of lower-cost fuels and power, while optimizing energy efficiency. ## Powering the Future of Energy With AI and High-Performance Computing To meet global demands, energy companies are turning to a software-defined approach to explore, produce, transport, and deliver lower-cost energy while pursuing net-zero emission goals. They’re leveraging AI and high-performance computing (HPC) to reduce environmental impact from subsurface operations, automate manually intensive surface operations, and bring real-time intelligence to the grid edge. #### Shell Uses AI and HPC to Improve Efficiency, Safety, and Sustainability in Energy Learn how Shell used [NVIDIA DGX™ systems](https://www.nvidia.com/en-us/data-center/dgx-platform.md) to determine salt boundaries in reservoir modeling, enable 4K iterative image reconstruction, test new designs for industrial plants, and drive advancements in sustainable new materials. [Read Case Study](https://resources.nvidia.com/en-us-upstream-energy/energy-success-story?lx=d-5uUJ) #### Siemens Gamesa Maximizes Wind Energy Using Wake Optimization Siemens Gamesa is optimizing their offshore wind farms for maximum power output at minimal cost using [NVIDIA Omniverse™](https://www.nvidia.com/en-us/omniverse.md) and [NVIDIA PhysicsNeMo](https://developer.nvidia.com/physicsnemo). Find out how neural super-resolution accelerates simulation times from 40 days to 15 minutes. [Watch Demo](https://resources.nvidia.com/en-us-energy-utilities/siemens-gamesa-wind) ## Use Cases ## Discover How the Energy Industry Is Using AI and HPC #### Oil and Gas Operations Accelerate reservoir simulation and seismic processing for fuel production. Learn how AI is accelerating reservoir simulation and seismic processing, enhancing pipeline monitoring, and protecting worker health and safety, while reducing emissions and environmental impact. [Explore Oil and Gas Operations](https://www.nvidia.com/en-us/industries/energy/oil-gas-operations.md) #### Surface Operations Build industrial and scientific digital twins for sustainability and safety. Find out how AI is being used to develop physically accurate industrial [digital twins](https://www.nvidia.com/en-us/omniverse/solutions/digital-twins.md), scale renewable energy generation, simulate climate and weather, speed up computational fluid dynamics (CFD) workloads, and optimize industrial site efficiency. [Explore Surface Solutions](https://www.nvidia.com/en-us/industries/energy/surface-operations.md) #### Power and Utilities Enhance power generation, transmission, and distribution for grid resiliency. Explore the future of software-defined smart grids, including predictive maintenance of grid infrastructure, management of distributed energy resources, synthetic data generation of grid assets, outage scheduling, truck roll optimization, and utility contact center virtual assistants. [Explore Power and Utilities Solutions](https://www.nvidia.com/en-us/industries/energy/power-utilities.md) ## Success Stories ## See the Real-World Impact of AI in Energy Learn from industry leaders using AI to optimize processes, reduce risk, and trim costs. Image courtesy of Deloitte, Exelon. ### Exelon® Leads Utility Innovation With Deloitte in Autonomous Drones for Grid Asset Inspection Exelon, one of the largest U.S. energy companies, partnered with Deloitte and NVIDIA to develop OptoAI, an autonomous drone solution built on NVIDIA Jetson and Omniverse. [Read Case Study](https://www.nvidia.com/en-us/customer-stories/exelon.md) Image courtesy of Deloitte, Exelon. ### Parabole AI Achieves 1,000x Speedup for Industrial Process Optimization With Gurobi Parabole AI leverages causal AI on NVIDIA's accelerated computing platform to solve complex industrial optimization challenges. This collaboration enhances real-time AI decision-making with speed, context, and confidence by combining domain-specific causal modeling with advanced compute infrastructure. [Read Case Study](https://www.nvidia.com/en-us/customer-stories/parabole-ai.md) ### Stone Ridge Technology Boosts ECHELON by 3.8x on NVIDIA GPUs Stone Ridge Technology benchmarked their ECHELON reservoir simulation software on the [NVIDIA Hopper GPU](https://www.nvidia.com/en-us/data-center/technologies/hopper-architecture.md) architecture, including the [NVIDIA Grace Hopper Superchip](https://www.nvidia.com/en-us/data-center/grace-hopper-superchip.md), H100-NVL, and H100-PCIe. Learn how the company achieved up to 3.8x faster simulations with up to 25-million cell models. [Read Stone Ridge Technology Blog](https://stoneridgetechnology.com/company/blog/leap-ahead-with-hopper-2/) ### Developing Power Plant Digital Twins to Save Billions Annually Learn how global energy companies such as Siemens Energy are building industrial digital twins to support predictive maintenance at power plants and how that could save the energy industry an estimated $1.7 billion a year. [Read Blog](https://resources.nvidia.com/en-us-energy-utilities/siemens-energy-nvidia) Image courtesy of Noteworthy AI. ### Edge Computing Monitors Millions of Utility Poles for Needed Repairs Take a look at FirstEnergy’s onboard smart camera system—developed by Noteworthy AI and powered by the [NVIDIA® Jetson™ edge AI platform](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems.md)—which automatically monitors millions of utility poles and tens of millions of grid devices for maintenance. [Read Blog](https://resources.nvidia.com/en-us-energy-utilities/power-utility-ai-edge) Image courtesy of Noteworthy AI. Previous Next 1. Slide 4 2. Slide 4 3. Slide 4 4. Slide 4 5. Slide 4 > Shell has ongoing work with NVIDIA: more realistic 3D reservoir models (e.g., dipping reservoir) for CO2 storage, layered geology with horizontal and vertical heterogeneity, computationally efficient Fourier neural operator (FNO)-based networks dealing with larger input datasets and providing acceptable predictions over longer time windows (hundreds of years), and the capability to build next-generation digital twin models of deep earth for climate change scenario (CCS) applications in real time with uncertainty assessment. — Pandu Devarakota, Principal Science Expert, Shell > We can examine the contribution of AI to the energy sector from three dimensions: energy forecasting, carbon capture, and predictive maintenance... AI algorithms are being used for energy forecasting, to predict energy demand, and to optimize economic value... AI can be used to reduce carbon emissions by analyzing data from multiple sources regarding weather, soil, and crop yield... to optimize our supply chain logistics and reduce our carbon footprint... AI can also help energy companies monitor the performance of their assets and equipment. — Nayef Otaibi, Vice President and Chief Digital Officer, Saudi Aramco > We will continue to collect data, not just on how our wind turbines operate, but also for weather forecasting, site planning, and other areas to optimize wind turbine sites. We're exploring augmented reality and extended reality as wind turbines are complicated machines with many types of failure modes. It's imperative to make sure the wind turbines operate safely and service technicians know how to do service repairs in the right way. — Lasse Lundberg Nowack, Vice President, Engineering Development Power Solutions, Vestas > By using synthetic data generation in NVIDIA Omniverse, our goal was to automatically create thousands of labeled photorealistic examples of various defects in grid assets. We are in the process of using real images and these synthetic images to train inspection models. — Ankush Agarwal, Director of Advanced Analytics, Exelon > In Oregon, we are experiencing the impacts of climate change firsthand and recognize the urgent need for innovation at the grid edge as we transition to a clean energy future. Investing in new technologies for the grid is a key strategy for PGE to achieve its climate goals and provide customers with clean, affordable, and resilient energy. — Ananth Sundaram, Senior Manager of Integrated Grid, Portland General Electric (PGE) Previous Next 1. Quote 1 2. Quote 2 3. Quote 3 4. Quote 4 5. Quote 5 ## News and Events ### NVIDIA Announces Omniverse Real-Time Physics Digital Twins With Industry Software Leaders A new blueprint for interactive virtual wind tunnels enables unprecedented computer-aided engineering exploration for Altair, Ansys, Cadence, Siemens, and more. [Read Announcement](https://nvidianews.nvidia.com/news/nvidia-announces-omniverse-real-time-physics-digital-twins-with-industry-software-leaders) ### Accelerating SLB INTERSECT up to 11X With NVIDIA GPUs Systems powered by [NVIDIA A100 80GB Tensor Core GPUs](https://www.nvidia.com/en-us/data-center/a100.md) demonstrate superb performance uplifts compared to CPU performance running SLB’s INTERSECT high-resolution reservoir simulator. [Read Tech Brief](https://resources.nvidia.com/en-us-upstream-energy/tech-brief-slb-intersect) ### Shearwater Accelerates Seismic Processing With NVIDIA Grace Hopper Superchip Shearwater is expanding its collaboration with NVIDIA to innovate subsurface processing and imaging with higher performance-per-watt, energy efficiency, and fewer emissions with the NVIDIA Grace Hopper™ Superchip. [Read Shearwater's Article](https://www.shearwatergeo.com/news/accelerating-seismic-processing-with-the-nvidia-grace-hopper-superchip) ### Utilidata Partners With Aclara to Bring Distributed AI to the Grid Edge Aclara will be the first company to embed Utilidata’s distributed AI platform, Karman, in a smart meter to enable a connected grid that delivers clean and reliable energy. Built on a custom NVIDIA module that leverages AI, Karman captures robust, high-quality data to improve grid operations and manage distributed energy resources. [Read Utilidata's Announcement](https://utilidata.com/press-release/utilidata-partners-with-aclara-to-bring-distributed-ai-to-the-grid-edge) Previous Next 1. Slide 1 2. Slide 2 3. Slide 3 4. Slide 4 ## NVIDIA DGX Spark DGX Spark brings the power of NVIDIA Grace Blackwell™ to developer desktops. The GB10 Superchip, combined with 128 GB of unified system memory, lets AI researchers, data scientists, and students work with AI models locally with up to 200 billion parameters. [Learn More](https://www.nvidia.com/en-us/products/workstations/dgx-spark.md) #### Technology ## Energy Solutions—From Data Center to Edge to Cloud Learn about the AI and HPC hardware, software, and networking solutions for energy companies. ### NVIDIA Grace Hopper Superchip The NVIDIA Grace Hopper™ Superchip is a breakthrough accelerated CPU designed from the ground up for giant-scale AI and HPC applications. The superchip will deliver up to 10X higher performance for applications running terabytes of data, enabling scientists and researchers to reach unprecedented solutions for the world’s most complex problems. [Explore Superchip](https://www.nvidia.com/en-us/data-center/grace-hopper-superchip.md) ### NVIDIA DGX H100 The latest iteration of [NVIDIA DGX™ systems](https://www.nvidia.com/en-us/data-center/dgx-platform.md) and the foundation of [NVIDIA DGX SuperPOD™](https://www.nvidia.com/en-us/data-center/dgx-superpod.md), DGX H100 is the AI powerhouse that’s accelerated by the groundbreaking performance of the [NVIDIA H100 Tensor Core GPU](https://www.nvidia.com/en-us/data-center/h100.md). [Explore DGX H100](https://www.nvidia.com/en-us/data-center/dgx-h100.md) ### NVIDIA DGX Cloud NVIDIA DGX Cloud is a multi-node AI-training-as-a-service solution optimized for the unique demands of enterprise AI. It’s a combined software and infrastructure solution for AI training that includes a full-stack developer suite, leadership-class infrastructure, and concierge support, allowing businesses to get started immediately with predictable, all-in-one pricing. [Explore DGX Cloud](https://www.nvidia.com/en-us/data-center/dgx-cloud.md) ### NVIDIA AI Enterprise With NVIDIA AI Enterprise, energy companies can speed up development of use case applications, such as reservoir simulation, seismic processing, and predictive maintenance. Learn how to get free, short-term access to NVIDIA AI Enterprise in curated labs through NVIDIA LaunchPad. [Get Started](https://www.nvidia.com/en-us/data-center/products/ai-enterprise-suite.md) ### NVIDIA HPC SDK The NVIDIA HPC SDK includes the proven compilers, libraries and software tools essential to maximizing developer productivity and the performance and portability of HPC modeling and simulation applications. [Explore the HPC SDK](https://developer.nvidia.com/hpc-sdk) ### NVIDIA PhysicsNeMo NVIDIA PhysicsNeMo is an open-source framework for building, training, and fine-tuning physics-informed machine learning (physics-ML) models with a simple Python interface. With PhysicsNeMo, you can build models for enterprise-scale digital twin applications across multiple physics domains, from CFD to structural analysis to electromagnetics to climate science. [Explore PhysicsNeMo](https://developer.nvidia.com/physicsnemo) ### NVIDIA Omniverse Enterprise NVIDIA Omniverse is an extensible, open platform built for 3D virtual collaboration and real-time physically accurate simulation. Omniverse combined with NVIDIA PhysicsNeMo, a framework for developing physics machine learning neural network models, enables digital twins for wind farms, power plants, electric grids, and someday Earth itself. [Explore Omniverse](https://www.nvidia.com/en-us/omniverse/enterprise.md) ### NVIDIA Jetson Edge AI Platform NVIDIA Jetson brings accelerated AI performance to the edge in a power-efficient and compact form factor. Together with the [NVIDIA JetPack™ SDK](https://developer.nvidia.com/embedded/jetpack) and [NVIDIA Isaac™](https://www.nvidia.com/en-us/deep-learning-ai/industries/robotics.md) software for Robotics Operating System, these Jetson modules, including [NVIDIA Jetson Orin Nano™](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-orin.md), support a full range of edge AI and robotics applications. [Explore Jetson](https://developer.nvidia.com/embedded-computing) ### NVIDIA Nemo Framework NVIDIA NeMo™, part of the [NVIDIA AI platform](https://www.nvidia.com/en-us/ai-data-science.md), is an end-to-end, cloud-native enterprise framework for building, customizing, and deploying generative AI models with billions of parameters. The NeMo framework provides an accelerated workflow for training with 3D parallelism techniques, several customization techniques, and optimized at-scale inference of large-scale models for language and image applications. [Explore Nemo](https://www.nvidia.com/en-us/ai-data-science/generative-ai/nemo-framework.md) ## Resources ## Take a Deeper Dive Into AI in Energy 1. Videos 2. Training 3. Blogs 4. Publications 5. Community **Featured** ### Powering the Future of Clean Energy | I Am AI To manage renewable energy at scale, NVIDIA and its ecosystem of partners are using AI to optimize solar and wind farms, simulate climate and weather, maintain power grids, advance carbon capture, and power fusion breakthroughs. [Watch Now](https://youtu.be/zrcxLZmOyNA) Videos [See All](https://resources.nvidia.com/l/en-us-upstream-energy) Webinars [See All](https://resources.nvidia.com/l/en-us-upstream-energy) ### Intro to Physics-Informed ML With PhysicsNeMo Gain an understanding of the various building blocks of [NVIDIA PhysicsNeMo](https://developer.nvidia.com/physicsnemo), the basics of physics-informed deep learning, and how the framework integrates with the overall [Omniverse platform](https://www.nvidia.com/en-us/omniverse.md). [Learn How to Build Physics-Informed Neural Networks With PhysicsNeMo](https://courses.nvidia.com/courses/course-v1:DLI+S-OV-04+V1/) ### Build an AI Center of Excellence Learn how to use NVIDIA Base Command™ Platform to accelerate your containerized AI training workloads, discover the tools necessary to build an AI center of excellence, and get the basics of working with, modifying, and running Docker containers from [NVIDIA NGC™](https://www.nvidia.com/en-us/gpu-cloud.md). [Learn How to Use Base Command Platform](https://www.nvidia.com/en-us/data-center/base-command-platform.md) ### Getting Started With AI on Jetson Nano Learn how to use Jupyter iPython notebooks on a [Jetson Nano Developer Kit](https://developer.nvidia.com/embedded/jetson-nano-developer-kit) to build a deep learning classification project with computer vision models. This easy-to-use, powerful computer runs multiple neural networks in parallel. [Get Trained](https://courses.nvidia.com/courses/course-v1:DLI+S-RX-02+V2/?ncid=em-news-168929-vt31#cid=_em-news_en-us) ### NVIDIA Inception Program Meet NVIDIA Inception, the free program designed to help startups evolve faster through access to cutting-edge technology and NVIDIA experts, connections with venture capitalists, and co-marketing support to raise visibility. [Explore Inception](https://www.nvidia.com/en-us/startups.md) ### NVIDIA Connect NVIDIA Connect is a free program that helps software development companies and service providers shorten time to market through tailored development resources, technical training, and preferred pricing on NVIDIA technologies. [Apply for the NVIDIA Connect Program](https://www.nvidia.com/en-us/programs/isv.md) ### NVIDIA Developer Program Connect with millions of like-minded developers in the NVIDIA Developer Program to do your life’s work. Gain access to free containers, pretrained models, SDKs, technical documentation, and peer and domain expert help. [Join the Developer Program](https://developer.nvidia.com/developer-program) Partners ### NVIDIA Partners for Energy Our solutions for the energy industry go beyond products. Our partners are here to assist your organization at every level to build and execute transformative AI strategies, products, and services. [Explore Our Partners](https://www.nvidia.com/en-us/industries/energy/partners.md) ## Get Started ## Take the Next Steps ### Stay Up to Date on NVIDIA News for Energy [Subscribe](#subscribe-modal) ### Request a Meeting Chat with NVIDIA energy experts to help solve your business challenges. [Let's Talk](mailto:energy@nvidia.com) ## Get The Latest Energy News Welcome back. Not you? Log Out Welcome back. Not you? Clear form