Data science applications in engineering systems, environmental modeling, spatial statistics, reinforcement/meta/few-shot learning, environmental remote sensing, geospatial modeling
PhD, University of Tennessee
Energy Science and Engineering
Concentration: Remote Sensing, Machine Learning, Spatial Statistics
MSc, Pennsylvania State University
Concentration: Remote Sensing and Data Mining
BSc, University of Alabama in Huntsville
Earth System Science (Focus: GIS, Remote Sensing, Hydrology)
Minor in Mathematics
A list is also available online
Robust Signal Classification Using Siamese Networks. In Proceedings of the ACM Workshop on Wireless Security and Machine Learning (WiseML), 1-5. New York, NY, USA: Association for Computing Machinery. 2019.
Zachary L. Langford, Logan Eisenbeiser, and Matthew Vondal.
Arctic Vegetation Mapping Using Unsupervised Training Datasets and Convolutional Neural Networks. Remote Sensing, 11(1):69, 2019.
Zachary L. Langford, Jitendra Kumar, Forrest M. Hoffman, Amy L. Breen, and Colleen M. Iversen.
- Robert J. Klein, John H. Aughey, and Zachary L. Langford. Apparatus, System, and Method for Generating an Image, 2017. US20190158805A1.
R&D Staff, Oak Ridge National Laboratory
- Working in the Cyber Resilience and Intelligence Division at ORNL.
- Developing data analytics techniques (e.g. anomaly detection, visualizations, machine learning, etc.) for national security projects.
- Machine learning algorithms for rapid development of digital twins of industrial control systems.
- Contributing to technology for over-the-air machine learning applications for secure communications.
Research Scientist, Virginia Tech
- Developed new approaches for signal classification using deep learning methods.
- Developed a Generative Adversarial Network modeling framework of latent space for extracting wanted features of synthetic images.
- Contributed to Bayesian networks for understanding the likelihoods of known causes and contributing factors.
Advanced Technologist, Boeing Research & Technology
- Contributed to object detection approaches on aerial platforms.
- Developed anomaly detection approach for identifying manufacturing defects.
- Hyperspectral remote sensing UAV sensor modeling for methane detection.
Graduate Research Assistant, University of Tennessee/ORNL
- Provided geospatial datasets of Arctic ecosystems for parameterizing land surface models for climate change research.
- Developed multi-sensor fusion frameworks of satellite imagery and ground measurements for retrieving surface parameters.
- Developed automated algorithms for identifying and understanding disturbance threats (e.g., wildfires) using spatiotemporal datasets in Google Earth Engine.