Houston, TX, United States of America

Harsh Biren Vora



Average Co-Inventor Count = 8.5

ph-index = 1


Company Filing History:


Years Active: 2024

Loading Chart...
Loading Chart...
2 patents (USPTO):Explore Patents

Title: Harsh Biren Vora: Innovator in Petroleum Reservoir Modeling

Introduction

Harsh Biren Vora is a notable inventor based in Houston, TX, specializing in advanced methodologies for petroleum reservoir modeling. With a focus on utilizing deep learning techniques, he has made significant contributions to the field of reservoir behavior prediction.

Latest Patents

Harsh holds two patents that showcase his innovative approach. The first patent, titled "Petroleum reservoir behavior prediction using a proxy flow model," involves training a deep neural network (DNN) to model a proxy flow simulation of a reservoir. This method employs an ensemble Kalman filter (EnKF) to assimilate new data, allowing for accurate history matching and prediction of reservoir behavior. The second patent, "Optimized methodology for automatic history matching of a petroleum reservoir model with Ensemble Kalman Filter (EnKF)," outlines a method for generating an ensemble of reservoir models based on geological data. This technique transforms production data into normal distributions, enabling effective updates and predictions of future reservoir behavior.

Career Highlights

Harsh is currently employed at Landmark Graphics Corporation, where he applies his expertise in petroleum engineering and data science. His work focuses on enhancing the accuracy of reservoir simulations, which is crucial for optimizing fluid production.

Collaborations

Throughout his career, Harsh has collaborated with talented professionals, including Yevgeniy Zagayevskiy and Hanzi Mao. These collaborations have further enriched his research and development efforts in the field.

Conclusion

Harsh Biren Vora's innovative patents and contributions to petroleum reservoir modeling highlight his significant role in advancing the industry. His work continues to influence the methodologies used in reservoir behavior prediction and optimization.

This text is generated by artificial intelligence and may not be accurate.
Please report any incorrect information to support@idiyas.com
Loading…