The Data Analytics for Petroleum Industry (DAPI) Certificate is an interdisciplinary certificate program coordinated by TAMIDS and housed in Texas A&M’s Department of Petroleum Engineering. This certificate provides students with the opportunity to work on technical problems with global consequences in the energy industry.
Why Data Analytics?
A growing trend towards the use of data analytics and machine learning is emerging due to the large-scale deployment of sensors in exploration, drilling, production, asset management, supply chain, and various commercial operations. Data analytics has numerous applications in the energy industry including analyzing seismic and distributed sensing data, improving reservoir characterization and simulation, reducing drilling time and increasing drilling safety, optimizing the performance of production pumps, improving petrochemical asset management, improving shipping and transportation, and improving occupational safety.
Supporting Future Aggie Engineers
In the Spring 2024 semester, Dr. Sid Misra, an associate professor in the Department of Petroleum Engineering, mentored twelve undergraduate students in the DAPI program who were interested in applied machine learning research. Dr. Misra said his goal in mentoring undergrad research is not only to introduce them to new tools but to help them understand the challenges of developing practical solutions.
“There’s a magic to guiding undergrads on their first research journeys. It’s like witnessing a treasure hunt.”
– Dr. Sid Misra

Despite the short amount of time they had with Dr. Misra, this group of twelve students authored three journal papers, two of which are currently being peer-reviewed for publication. The first paper, “Machine Learning for Gas Leak Detection and Forecasting,” was written by Jacob Enerio, Minhyuk Kim, and Catherine Duong. In their paper, they discuss the applications of gas sensors with an emphasis on their capability to detect extremely low concentrations of target gases.
The second paper, authored by Wahayb Alotaibi, Jessica Torres, Yousif Alsekait, William Gretzinger, Omar Al Blushi, Jana Alsabyani, Madhawi Alharbi, and Dinghan Wang, is entitled “A Comparative Study of Transfer Learning, Convolutional Neural Network, and Random Forest for Satellite-Image-Based Land Use Classification.” This paper presents possible classification models in response to the increasing accessibility of satellite imagery. Dr. Misra says, “I’m immensely proud of the dedication and hard work demonstrated by each member of the team…During undergrad research, I need to be patient, explaining things in simple ways and cheering them on when they struggle.”
A defining goal of TAMIDS’s efforts is to give Aggies the skills and training needed to enter the workforce prepared to solve real-world problems. Opportunities like the DAPI Certificate Program introduce undergraduate students to research and the latest advancements in data analysis. To read more about the DAPI Certificate Program, click here.