R&D Associate in Spatial AI Modeling for Population Dynamics (Hybrid Eligible)

Requisition Id 13300 

Overview:  

As a U.S. Department of Energy (DOE) Office of Science national laboratory, Oak Ridge National Laboratory (ORNL) has an extraordinary 80-year history of solving the nation’s biggest problems. We have a dedicated and creative staff of over 6,000 people! Our vision for diversity, equity, inclusion, and accessibility (DEIA) is to cultivate an environment and practices that foster diversity in ideas and in the people across the organization, as well as to ensure ORNL is recognized as a workplace of choice. These elements are critical for enabling the execution of ORNL’s broader mission to accelerate scientific discoveries and their translation into energy, environment, and security solutions for the nation.

We are seeking a qualified applicant for an R&D Associate position in Spatial AI Modeling for Population Dynamics for the Human Geography (HG) Group within the Human Dynamics Section (HDS) found in the Geospatial Science and Human Security (GSHS) Division, National Security Sciences Directorate, at ORNL.

 

The position affords the unique opportunity to work with a dedicated interdisciplinary team of R&D professionals across research groups to build new research directions in development of the next generation of population models. The successful candidate will work on advancing machine learning (ML) and deep learning (DL) methods toward the understanding of global gridded population modeling, human settlement patterns, urbanization, population forecasting and change detection. Specifically, as it is difficult to estimate accurate population at high resolution (3 arc-second) for all the countries across the globe, the HG Group is interested in the generalizability of ML models. Your work will be focused on experimenting with DL models such as variants of CNN, LSTM, and transformers using remote sensing data to estimate the population at the grid cell level on a global scale using a GPU cluster.

 

Within the HG Group, you will be part of a research team that is developing novel methods for applied ML in large scale space-time analytics and multi-modal data fusion. Using the world’s most robust high-performance computing platforms, we aim for big geospatial science opportunities to support critical national security missions.

 

Major Duties/Responsibilities: 

• Contribute to and lead the design, development, and implementation of new models, methods, and algorithms that improve our understanding of gridded population modeling on a global scale.
• Evaluate and improve existing population modeling methodology, workflows, and codebases where appropriate.
• Provide coding support to implement novel uncertainty estimation algorithms as proof of concept or prototype to test effectiveness and robustness of applied machine learning algorithms.
• Support the design of statistical sampling strategies and accelerating the implementation of such tools.
• Contribute to journal publications; participate in conferences; and engage with other scientists, technicians, and analysts in the private sector, academia, and US Government communities.
• Deliver strong science and technology artifacts demonstrating research innovation for our sponsors.
• All team members deliver ORNL’s mission by aligning behaviors, priorities, and interactions with our core values of Impact, Integrity, Teamwork, Safety, and Service. Promote diversity, equity, inclusion, and accessibility by fostering a respectful workplace – in how we treat one another, work together, and measure success.

 

Basic Qualifications:

• PhD in computer science, computational data sciences, geography, statistics, computer engineering, remote sensing or equivalent field with 0-2 years of relevant experience. An equivalent combination of education and experience may be considered.
• Experience with parallel processing on CPU and/or GPU.
• Experience with Pandas, Numpy, Pytorch, and other similar tools for ML and DL.
• Experience with Python, R, and/or other similar languages for statistical analysis.
• Experience with remote sensing data or other imagery.
• Experience in manipulating large scale physical geospatial data inc