In an era where energy and digital technologies are merging, Texas A&M University plays a pivotal role in this convergence through a 2021 formal agreement between the Texas A&M Institute of Data Science (TAMIDS) and the Texas A&M Energy Institute (TAMEI).
The digitization of energy is a transformative shift that is reshaping the landscape of the energy industry. By leveraging digital technologies, we can optimize energy production, improve efficiency, enhance resilience, and significantly reduce emissions. This not only leads to cost savings but also contributes to environmental sustainability. Energy sector digitization is occurring throughout the ecosystem from supply, demand to networks. Data sciences, coupled with computing power growth and algorithm development of artificial intelligence markup language offer tremendous opportunities in the energy sector for cleaner, more reliable, and more affordable energy services.
In November 2021, TAMIDS and TAMEI signed a memorandum of understanding to collaborate on research and education opportunities that enhances capacity at Texas A&M University in data science for energy. This collaboration leverages expertise from both data sciences and energy systems perspectives. “Texas A&M Institute of Data Science and the Texas A&M Energy Institute are uniquely positioned to tackle these challenges together by leveraging expertise from both data sciences and energy systems perspectives,” said Dr. Le Xie, Professor in the Department of Electrical and Computer Engineering at Texas A&M University and TAMEI Associate Director of Energy Digitization. “We look forward to building on our collaboration in education to drive the adoption of data science and artificial intelligence in the energy arena,” explained Dr. Nick Duffield, Director of TAMIDS and the Royce E. Wisenbaker Professor in the Department of Electrical and Computer Engineering.
The institutes have jointly developed and are administering six 1.5 credit hour elective modules in energy digitization as a customized course theme for students pursuing a TAMEI Masters of Science in Energy. These modules provide both foundational introductions to data science, as well as domain-specific applications of energy, such as in power systems, oil and gas, and the process industry. Discussions are currently underway to create a joint graduate-level Certificate in Energy and Data Science. This would allow students to take data science modules related to energy and earn a professional credential.
Energy Digitization Elective Modules
- ICPE 638 Data Science Fundamentals for Energy I: Introduction of basic concepts and methods for data science in systems with focus on data and mathematical tools for understanding structure in data. Topics to be discussed include concepts of probability theory, probability distributions, statistical data modeling and inference, introduction to graphs, introduction to matrix factorization, state-space models, statistical modeling of dependent data, and graphic models.
- ICPE 689 Data Science Fundamentals for Energy II: This is an introductory course discussing machine learning methods commonly seen in data science with an emphasis to applications in energy. Topics to be discussed include supervised and unsupervised learning, clustering, classification, predictive models, performance evaluation, neural networks, and deep learning with different data types. Prerequisite: ICPE 638 – Data Science Fundamentals I.
- ICPE 639 Introduction to Machine Learning for Energy: Discussion of machine learning methods commonly seen in data science with an emphasis to applications in energy; topics include supervised and unsupervised learning, clustering, classification, predictive models, performance evaluation, neural networks, and reinforcement learning. Prerequisites: ICPE 638 and 689 – Data Science Fundamentals I & II.
- ICPE 637 Data Science for Power Systems: Basic concepts and methods of data science with an emphasis on energy-related applications; discussion of probability theory, data-based statistical modeling and inference, linear and non-linear regression and predictive models, dimensionality reduction, introduction to machine learning and statistical modeling of dependent data. Prerequisites: ICPE 638 and 689 – Data Science Fundamentals I & II.
- ICPE 689 ST: Data-Driven Workflows for Intelligent Oil Field Operations and Digital Twins: State-of-the-art digital technologies applied in the context of reservoir exploration and production, that is, instrumentation, workflows for automation in drilling, production, and reservoir. It also covers the basic working knowledge in artificial intelligence (Machine Learning and Data Analytics) for smart integration of production systems toward the goal of achieving a sustainable form of cleaner energy production. Prerequisites: ICPE 638 and 689 – Data Science Fundamentals I & II.
- ICPE 689 ST: Recent Trends in Process Modeling and Control: Benefits and limitations of modeling and computational solutions. Students learn to formulate and solve complex numerical problems and understand the limitations and sources of error in simulation and numerical computing packages. Prerequisites: ICPE 638 and 689 – Data Science Fundamentals I & II.
Moreover, coordination efforts are ongoing to launch a Consortium for Energy and Data Science (CEADS). The goal of CEADS is to establish a leading consortium that brings together academia, industry, and government to address key knowledge gaps and advance best practices in energy and data science. This consortium aims to “Harness the Data Revolution,” transforming the energy sector towards a more sustainable future. As CEADS develops, more details will be shared.
About Texas A&M Institute of Data Science: TAMIDS serves and fosters collaborations across the university and its affiliated agencies. TAMIDS is a joint undertaking of Texas A&M University with the Texas A&M Engineering Experiment Station (TEES) and Texas A&M AgriLife Research. TAMIDS is an inclusive umbrella organization for data science and will facilitate interactions between researchers in diverse application areas and those with expertise in core methodologies, promote education in data science across the university, and pursue outreach to commercial and governmental organizations in the wider data science ecosystem.