Eni runs 20-year reservoir forecast in 30 minutes using Stone Ridge Technology's ECHELON 2.0 on NVIDIA GPUs
EniNVIDIA A100 40GB Tensor Core GPUs · NVIDIA V100 Tensor Core GPUs · Stone Ridge Technology ECHELON 2.0
Eni and Stone Ridge Technology (SRT) developed ECHELON 2.0, the first commercial compositional reservoir simulation software designed exclusively to run on NVIDIA GPUs, deployed on Eni's HPC5 supercomputer of 1,820 Dell EMC servers with four NVIDIA V100 Tensor Core GPUs each (7,280 V100 GPUs total). In a test, ECHELON 2.0 ran an 11.2-million-cell compositional model with nine components across a 20-year forecast in 30 minutes using eight NVIDIA A100 40GB GPUs. Eni used the software for deep-water reservoir, offshore oil field, and deep-water gas field simulations, including calibrating a strategic gas field in North Africa by running hundreds of simulations quickly.
Overview
Eni and Stone Ridge Technology (SRT) developed ECHELON 2.0, the first commercial compositional reservoir simulation software designed exclusively to run on NVIDIA GPUs, deployed on Eni's HPC5 supercomputer of 1,820 Dell EMC servers with four NVIDIA V100 Tensor Core GPUs each (7,280 V100 GPUs total). In a test, ECHELON 2.0 ran an 11.2-million-cell compositional model with nine components across a 20-year forecast in 30 minutes using eight NVIDIA A100 40GB GPUs. Eni used the software for deep-water reservoir, offshore oil field, and deep-water gas field simulations, including calibrating a strategic gas field in North Africa by running hundreds of simulations quickly.
The challenge
Multi-core CPU simulators struggle to retain the reservoir detail and complexity needed for accurate risk analysis of increasingly large geological models; reservoir engineers were spending days or weeks on large clusters simulating upscaled reservoir models.
The solution
Stone Ridge Technology (SRT) and Eni developed ECHELON 2.0, the first commercial compositional reservoir simulation software designed exclusively to run on NVIDIA GPUs, deployed on Eni's HPC5 supercomputer of 1,820 Dell EMC servers with four NVIDIA V100 Tensor Core GPUs each (7,280 V100 GPUs total). ECHELON 2.0's compositional formulation ran an 11.2-million-cell model with nine components across a 20-year forecast in 30 minutes using eight NVIDIA A100 40GB GPUs. Eni used the software for deep-water reservoir, offshore oil field, and deep-water gas field simulations, including calibrating a strategic gas field in North Africa by running hundreds of simulations in a short time.
Reported business value
ECHELON's speed, combined with the computational power of the HPC5 GPU cluster in the Eni Green Data Center, allowed Eni's team to better calibrate the reservoir model, introduce all needed geological details, and span relevant uncertainties — fast-tracking the project and tailoring the proper reservoir management strategy while weighing associated risks to reach and maintain the expected gas plateau in due time.
Sources
Open any source and check the claim yourself — that is the point of the register.
This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)
Other energy entries in the register.
Building a clean energy future with natural language analytics
Williams, a large-scale natural gas infrastructure operator, deployed Databricks AI/BI Genie to give commercial, regulatory, accounting and technical staff natural-language, self-serve access to analytics. The team flattened 27 disparate tables into SQL models that Genie Spaces reason over, encoding internal acronyms and business logic into Genie's instructions, powered by Databricks Unity Catalog. A data request that previously took an analyst five days now completes in seconds with validated accuracy, and the weekly backlog of data requests dropped from up to ten to one or two, freeing analysts for predictive modeling and enterprise projects.
WilliamsDatabricks AI/BI Genie · Databricks Unity Catalog
Plenitude builds machine learning models on Databricks to forecast energy demand and renewable production
Eni-owned energy company Plenitude, which serves 10 million households and businesses across Europe, uses statistical models and machine learning on the Databricks Data + AI Platform to forecast customer energy consumption at hourly and daily granularity, forecast wind and solar generation from its renewable asset portfolio, and run customer segmentation and propensity models across 60 implemented use cases.
PlenitudeDatabricks Data + AI Platform · Delta Lake · Unity Catalog +2Using data to power-fuel the transition to a carbon-neutral world
Helen, Helsinki's energy utility, built a centralized data and AI platform on Databricks to power forecasting and optimization models for its district heating system serving about 90% of Helsinki's population, processing real-time streaming sensor and IoT data to optimize distributed energy resources and EV charging placement as part of a plan to cut carbon emissions over 80% by decommissioning coal plants.
Helen· FinlandDatabricks Data + AI Platform · Delta Lake · Spark Declarative Pipelines +3Foresea modernizes base yard logistics with Oracle Autonomous AI Database
Foresea, a Brazilian offshore oil and gas drilling company, migrated its dock scheduling application to Oracle Autonomous AI Database 26ai with Oracle AI Database Private Agent Factory on OCI. The company replaced an unpredictable dock receiving process with a self-service booking application giving suppliers visibility into delivery status, check-in/check-out, dwell time, and document readiness, reducing wait times and overtime hours at its base yards.
Was this helpful?
Your feedback helps us improve our use case database