Cognite to release industrial AI with NVIDIA

The first, high-impact use case to be delivered for this initiative focuses on real-time anomaly detection in time series data. This joint effort with Celanese, a global specialty materials and chemical company, aims to enhance the speed, scale, and accuracy of identifying critical anomalies in vast streams of industrial time series data, enabling proactive intervention to help prevent operational disruptions.

Industrial operations generate an immense, continuous flow of sensor readings and equipment performance metrics. These readings are often noisy, complex, and lack context (essential background information and relationships), making it challenging to separate the predictable signal from random noise.

Cognite provides this context with Cognite Atlas AI, a low-code industrial AI workbench that delivers agents that can leverage real-time, AI-ready operational technology (OT), information technology (IT), and engineering data from Cognite Data Fusion via a unified AI and data platform. This makes it faster and easier for industrial organisations to build and extend agents into their existing maintenance workflows, while ensuring that these agents deliver accurate, traceable, and trustworthy results.

These capabilities are further strengthened with NV-Tesseract – a foundation model family developed by NVIDIA for time-series analysis, purpose-built to rapidly process and extract insights from complex industrial data streams. As a modular, transformer-based foundation model, NV-Tesseract delivers high accuracy in anomaly detection, forecasting, and classification, even in noisy or fast-shifting environments. By capturing long-range temporal patterns and adapting to changing scenarios, it enables scalable, trustworthy analytics across demanding industrial applications.

Across all use cases, Cognite and NVIDIA will deliver:

• Proactive problem solving with real-time insights at scale: with Cognite Atlas AI agents built on NVIDIA accelerated computing, customers will be able to forecast future operational states and predict potential failures in near real-time across thousands of sensors, even in high-velocity data streams. This allows industrial companies to move from reactive maintenance to proactive intervention, preventing failures before they occur.
• Rapid AI model development: building accurate predictive models is an iterative process of training, testing, and refining. NVIDIA's accelerated computing and software will allow for more training simulations and iterations in a shorter timeframe, enabling faster model retraining and significantly increased accuracy of Cognite Atlas AI agents while reducing false positives.
• More value from driving down costs and increasing efficiency: achieving anomaly detection results with less overall compute power translates directly into substantial operational cost reductions for customers. This acceleration also frees up valuable engineering and data science resources, allowing them to focus on higher-value tasks, like root cause analysis and strategic optimisation, rather than spending time on manual data analysis or lengthy model training cycles.

“For years, our partnership with Cognite has been the cornerstone of our digital transformation, allowing us to scale valuable use cases across more than 50 global sites and build streamlined agentic AI workflows that enhance productivity and efficiency across our organisation,” said Sameer Purao, SVP and CIO at Celanese. “By bringing NVIDIA's compute power to our AI solutions, we are now taking our capabilities, such as anomaly detection, to the next level."

Read the article online at: https://www.hydrocarbonengineering.com/refining/17102025/cognite-to-release-industrial-ai-with-nvidia/