Our Client

Vital Energy acquires, explores, and develops oil and natural gas properties. The company is investing in digital technologies to ensure asset integrity, reduce operating costs, and increase production rates.
Oil and gas companies are always looking for ways to raise productivity, lower production costs, avoid downtime, and prevent asset failures. Artificial Lift Optimization (ALO) is critical to growing well production. Electrical Submersible Pumps (ESPs) account for the largest share of the artificial lift market, which makes them central to operational excellence.
Many operators still monitor and optimize ESPs manually. That approach is time-consuming, expensive, and prone to human error. Artificial Intelligence (AI), Machine Learning (ML), and Big Data can take the complexity out of operating ESPs. They help identify opportunities, recognize problems, and optimize production rates.
An energy industry client’s success story
Our client, Vital Energy, acquires, explores, and develops oil and natural gas properties. Operational efficiency and production optimization are among its key priorities. The company is investing in digital technologies to ensure asset integrity, reduce operating costs, and increase production rates.
ESP-operated wells play a strategic role in this digital transformation strategy. New and in-service ESP wells need constant monitoring and tuning of operating parameters to meet efficiency and production targets. Vital Energy wanted an AI-based solution for ESP optimization. The solution would automatically recommend operating parameters and visualize all the necessary data. It would also let users leave feedback and enter limitations and operating constraints.

Our approach
SoftServe helped Vital Energy build a solution on Amazon Web Services (AWS) using Deep Neural Network (DNN) algorithms and optimization techniques, with extensive visualization and interpretation for end users. The solution models the entire system by simulating telemetry and production under different scenarios. It lets Vital Energy find the best controls to meet constraints such as motor temperature, voltage, intake pressure, and gas or water volume. The algorithm adapts to various ESP systems and gives operators optimal daily controls.

Solution outcomes:
- An ML model that predicts oil, gas, and water production with high accuracy, built on several months of data from 50 ESPs
- A pipeline that retrains automatically, deployed in the AWS environment
- Interactive visualizations of simulation scenarios
- A Streamlit dashboard, built as a prototype platform for testing parameter recommendations
- A combination of ML-based and physics-based models


Value delivered
SoftServe helped Vital Energy move to data-driven ESP optimization and reach its business goals:
- Real-time dashboards with summary statistics, forecasts, and parameter recommendations for better decision-making
- A flexible solution that adapts to a variety of ESP systems
- Less downtime, better maintenance practices, and lower OPEX
- A production increase of ~400 BPD across 29 test wells in the initial pilot. Later, the client reached 800 BPD from around 50 wells
- Scale from 29 to more than 100 wells in production within months
- High prediction accuracy for oil, gas, and water production


Let's talk about how SoftServe can help you digitally transform your processes and scale your digital strategy.
The project ran in two phases. See how we optimized operating conditions to boost oil production further in the second phase here.


