Subsurface Machine Learning Scientist

Key Skills

Java Programming, Python Programming, SQL, NumPy, Pandas, PyTorch, SciPy, ArcGIS, Scikit-learn, GIS, matplotlib, GemPy - Geological modeling, Rasterio, Welly, Lasio library, Striplog, Geopandas, QGIS - GIS application

Job Description

Looking for an opportunity to make an impact?

We are seeking?a Geologic Machine Learning Scientist?to join our research team in providing actionable, scientific, and data-driven results to inform carbon storage assessments and evaluate risks associated with oil and gas infrastructure, supporting the energy transition to a carbon neutral future.

The position will be a hybrid of on site and remote research and development support for NETL at one of its three research sites: Albany, Oregon; Morgantown, West Virginia, and Pittsburgh, Pennsylvania. This work will involve participation alongside data scientists, engineers, geologists, and computer scientists as part of a multi-disciplinary, scientific, and technically-oriented national laboratory team that produces technological solutions for America’s energy challenges. From developing creative innovations for efficient and resilient energy systems to environmental stewardship of energy resources, NETL research is providing breakthroughs and discoveries that support the transition to a carbon-neutral energy future, stimulate a growing economy, and improve the health, safety, and security of all Americans. Highly skilled people at NETL’s three research sites – Albany, Oregon; Morgantown, West Virginia, and Pittsburgh, Pennsylvania – conduct a broad range of research activities that support DOE’s mission to advance the national, economic, and energy security of the United States.

Aspiring candidates should demonstrate:

• Expert ability to apply and explain existing and build novel Artificial Intelligence and Machine Learning (AI/ML) applications to investigate complex environmental or geologic problems.
• Expert domain knowledge of geologic and environmental systems, especially sedimentary geology and subsurface interpretation.
• Collaborative mindset to work with a team towards actionable, scientific, and data-driven results that inform carbon storage risk assessment and support safe energy strategies.
• Experience publishing in peer-reviewed journals and presenting scientific findings at conferences or workshops.

Come join the Leidos Research Support Team supporting the National Energy Technology Laboratory (NETL), where you’ll be able to work side by side conducting research with world-class scientists and engineers using state of the art equipment to contribute to new areas of basic and applied research; discover, integrate, and mature technology solutions to enhance the nation’s energy foundation and protect the environment for future generations. You will contribute to the development of patents, written reports, journal articles, and contribute to presentations on findings, highlights, and innovative solutions in DOE-sanctioned meetings, scientific conferences, and national committees. Explore the Research Support Services (RSS) contract for the U.S. Department of Energy’s (DOE) National Energy Technology Laboratory (NETL) here - https://netl.doe.gov/.

Primary Responsibilities:

• Use subsurface domain knowledge to evaluate and establish decision-making frameworks for subsurface energy applications and energy infrastructure risk assessments.
• Source, organize, and curate data from available sources and develop the appropriate analytical plan to assess and inform subsurface energy applications and energy infrastructure development.
• Build novel and adapt existing AI/ML applications and methods to transform, analyze, and make reliable, accurate predictions using complex spatio-temporal data sets.
• Interrogate and explain model and tool results and provide research products that inform subsurface energy applications and safe energy infrastructure development.
• Work with software development team to integrate tools and create working user interfaces within established platforms (e.g. Energy Data eXchange® and similar platforms).
• Publish associated research in scientific journals and present results at workshops and conferences.
• Collaborate with a dynamic team across diverse domain backgrounds to drive projects towards data-driven conclusions.

Basic Qualifications:

• Master’s degree in Data Science, Statistics, Mathematics, Reservoir Engineering or related field with a focus on AI/ML
• 4+ years of experience working on a scientific research team to provide actionable, scientific, and data-driven solutions.
• Experience applying existing and building novel AI/ML models to evaluate and forecast trends in data.
• Subsurface expertise obtained through education or professional experience with sedimentology and subsurface interpretation of data logs (e.g., seismic, wireline).
• Experience with subsurface energy applications and energy infrastructure system components with a demonstrated ability to evaluate and apply that knowledge in a decision-making framework.
• Expertise curating, organizing, and producing metadata from all available sources to analyze and evaluate subsurface energy applications and energy infrastructure.
• Expertise in Python, especially libraries such as: Numpy, Gdal, GemPy, Rasterio, Scikit-Learn, Pandas, Matplotlib, PyTorch, SciPy, Welly, Lasio, Striplog, Geopandas.
• Experience collaborating with a team to use geospatial data analytics to inform decision-making strategies.
• Experience managing and analyzing multiple sources and types of spatio-temporal and subsurface data.
• Demonstrated experience publishing and presenting scientific findings in journal manuscripts and at workshops and conferences.

Preferred Qualifications:

• Ph.D. in Data Science, Statistics, Mathematics, Reservoir Engineering or related field.
• Bachelor’s degree in a physical science (e.g. Geology, Physics, Chemistry).
• Demonstrated experience with or domain knowledge of carbon storage infrastructure components.
• Expertise with Geographic Information Systems (GIS) software/applications (e.g., ArcGIS, QGIS)