Machine Learning

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.

The Shell.ai Hackathon organized in 2023 with a theme of sustainable and affordable energy 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.