Project

Pattern Recognition on 1D Pressure Data: Bottom Hole Pressure Prediction project was part of Spot the Trend – A PetroAI hackathon that presented a challenge to recognize the pattern with time series pressure data provided. As a problem statement and its solutions, a bottom-hole pressure was to be predicted with the help of provided time series data to decide whether a well is flowing or not. An AI model was then developed and optimized with 70.1% accuracy in predicting the BHP and well-flowingness.

The project Biomass Prediction and Design of an Optimum Demand-Supply Chain was a part of the Shell.ai hackathon for sustainable and affordable energy organized in 2023 presented a challenge to predict biomass production for the future years and design an efficient demand supply chain for the same by leveraging the provided data of the Gujarat State in India. An intelligent model was trained followed by an efficient demand supply chain with an accuracy rate of 76.765%, which was successfully deployed and ranked among the Top 10 teams worldwide.

A research project focusing on the optimization of near wellbore diverters in Hydraulic Fracturing with the help of data collected through lab experiments and the development machine learning model to predict the pressure for given concentrations of Bead, Powder, and Flakes. The project was primarily focused on the end goal of web app development that lets users predict the pressure on custom observations of Beads, Powder, and Flakes in Hydraulic Fracturing.

A B.Tech degree final year major project at Pandit Deendayal Energy University (PDEU) with a prior focus on the comparative study of oil recovery performance between Regular and LoSal Waterflooding. The project involved field modeling and simulation using CMG software (IMEX Simulator) through the development of static and dynamic models to analyze the oil recovery performance under different injection & waterflooding scenarios and study the key factors influencing the oil recovery in LoSal Waterflooding scenarios.

Reservoir Simulation and Modelling is one of the best and optimum ways to analyze the field and derive valuable insights effectively. In the project, during an internship at the Institute of Reservoir Studies (IRS) ONGC, the Petrel software was used to build the field’s representative static and dynamic models, perform history matching, and analyze the 4 different variants selected from careful study and analysis of the field.

The significance of using coconut husk in drilling fluid lies in its ability to provide an effective, sustainable, and cost-efficient solution for lost circulation and related challenges. The project purely focused on the development of different variants of coconut husk-based drilling fluid (based on the concentration and sizes of the husk) and a comparative study of the same to use them as a Loss Circulation Material (LCM) in drilling operations.  Different lab experiments were conducted on the prepared mud samples and the comparative study was performed by analyzing different properties such as Fluid Loss, Shear Stress vs. Shear Rate, Gel strength, Viscosity, etc.