Case Study

Conventional Energy

PETAI Services provide SOTA to drive your decisions based on AI. Our Research and development team builds SOTA architectures for enterprise data.


Attribute Selection: 

Seismic attributes contain information (energy) in a given seismic volume. In PETAI we use state of the art deep learning algorithms in selecting the right attributes for seismic interpretation. At PETAI we provide solutions to classification of multiple seismic attributes and enable seismic interpretation of geologic features and their geometries. 

Deep Learning (DL) Fault Detection

Uses state-of-the-art AI technology for Deep Learning (DL) Fault Detection application. This enables the application of a wide range of seismic data without the need for user-provided fault examples for training. Using Graphics Processing Unit (GPU) technology, the tool dramatically reduces the time to identify faults in a volume, accelerating the seismic interpretation workflow. Seismic interpreters use the Fault Detection application to compare aggressive and conservative results quickly, providing more time to focus on refining the results.

Deep Learning (DL) Seismic Facies Classification

The new DL Seismic Facies classification tool enables the identification of structural and stratigraphic facies patterns based on supervised, deep learning (CNN) technology. Seismic facies and other patterns present in seismic data, such as potential Direct Hydrocarbon Indicators, multiples, etc., can be identified in a seismic volume through training of the engine (model) on the desired facies. The 3D extent of these features can provide significant and valuable insights into the seismic interpretation process.

Deep Learning Well log 

The Rock Facies Classification tool enables rock typing using clustering methods. Deep learning models to understand data-driven Geomechanical Characterization. Use of Artificial intelligence algorithms to ingest asset operational data, pressures, mud properties, temperature, and more to understand exactly what is happening downhole at a specific well. These algorithms then use this data to predict bit wear, pore pressure, stuck pipe events, formation washouts, uncontrolled release of hydrocarbons to the atmosphere, and many other drilling dysfunctions. PETAI provides solutions on how  AI can identify all drilling dysfunction and propose a path forward to address drilling optimization.

Deep Learning in drilling Rigs 

Machine Learning provides a means to predict ROP during drilling with high accuracy with minimal data. This machine learning predictor can be used for simulation optimization so that ROP is maximized by adjusting surface parameters. This machine learning predictor can be used for simulation optimization so that ROP is maximized by adjusting surface parameters.

Predictive Modelling Analysis:

  • Through a multiuser, cross-domain environment, PETAI promotes collaboration between team members. PETAI provides interpretation support in predictive maintenance, asset defect recognition, and equipment maintenance. This enables you to leverage data and lessons learned from offset wells to improve drilling efficiency and identify potential hazards.
  • At PETAI we integrate end-to-end data with SOTA data analysis that can provide solutions to real-time data analytics and all relevant wellbore data in a common workspace. This allows you to fully understand your wellbore conditions and downhole dynamics and take preventative actions to mitigate risk and improve drilling performance.
  • PETAI workflow allows you to analyze events to determine the performance of the upstream and downstream activities and calculate cost-saving decisions.  

Data Pipeline:

  • PETAI Services provides both a custom Machine Learning pipeline and analytics-as-a-service offerings to help you gain control of your data environment and start driving actionable solutions. This includes the development of a strategy, the flexibility to select winning models from tests and easily deploy them. Blueprints and roadmaps, along with the engineering and operational requirements to help you maximize your data investment. Our end-to-end services, delivered with industry-specific expertise and processes, help make your data simpler to understand and empower data-driven intelligent workflows.
  • We build efficient pipelines to manage huge data influx. We outsource the MLOps platform to support the integration and deployment of custom-made algorithms into existing enterprise architecture.
  • Easy to use UI/UX for analyzing and visualizing data, training models, and reporting. The UI/UX can be customizable too.