Kyle Bradbury

Bio

Kyle Bradbury is the Managing Director of the Energy Data Analytics Lab at the Duke University Energy Initiative. He brings experience in machine learning and statistical modeling to energy problems. He completed his Ph.D. at Duke University, with research focused on modeling the reliability and cost trade-offs of energy storage systems for integrating wind and solar power into the grid. Kyle holds a M.S. in Electrical Engineering from Duke University where he specialized in statistical signal processing and machine learning, and a B.S. in Electrical Engineering from Tufts University. He has worked for ISO New England, MIT Lincoln Laboratories, and Dominion.

Education

• Ph.D. Duke University, 2013

Positions

• Assistant Research Professor in the Department of Electrical and Computer Engineering
• Managing Director, Energy Data Analytics Lab, Nicholas Institute for Energy, Environment & Sustainability

Awards, Honors, and Distinctions

• Bass Connections Award for Outstanding Leadership. Duke University. 2022

Courses Taught

• IDS 794: Independent Study
• IDS 705: Principles of Machine Learning
• HOUSECS 59: House Course
• ENERGY 796T: Bass Connections Energy & Environment Research Team
• ENERGY 795T: Bass Connections Energy & Environment Research Team
• ENERGY 795: Connections in Energy: Interdisciplinary Team Projects
• ENERGY 396T: Bass Connections Energy & Environment Research Team
• ENERGY 395T: Bass Connections Energy & Environment Research Team
• EGR 393: Research Projects in Engineering
• ECE 494: Projects in Electrical and Computer Engineering
• ECE 392: Projects in Electrical and Computer Engineering

Publications

• Ren S, Luzi F, Lahrichi S, Kassaw K, Collins LM, Bradbury K, et al. Segment anything, from space? In: Proceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024. 2024. p. 8340–50.
• Robinson C, Bradbury K, Borsuk ME. Remotely sensed above-ground storage tank dataset for object detection and infrastructure assessment. Scientific data. 2024 Jan;11(1):67.
• Yaras C, Kassaw K, Huang B, Bradbury K, Malof JM. Randomized Histogram Matching: A Simple Augmentation for Unsupervised Domain Adaptation in Overhead Imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2024 Jan 1;17:1988–98.
• Hakizimana M, Mavis E, Chiu Y, Malof J, Bradbury K. Enhanced Remote Sensing Model Performance Through Self-Supervised Learning with Multi-Spectral Data. In: International Geoscience and Remote Sensing Symposium (IGARSS). 2024. p. 2833–6.
• Luzi F, Gupta A, Collins L, Bradbury K, Malof J. Transformers For Recognition In Overhead Imagery: A Reality Check. In: Proceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023. 2023. p. 3767–76.
• Kornfein C, Willard F, Tang C, Long Y, Jain S, Malof J, et al. Closing the domain gap: blended synthetic imagery for climate object detection. Environmental Data Science. 2023;2.
• Hu W, Bradbury K, Malof JM, Li B, Huang B, Streltsov A, et al. What you get is not always what you see—pitfalls in solar array assessment using overhead imagery. Applied Energy. 2022 Dec 1;327.
• Ren S, Hu W, Bradbury K, Harrison-Atlas D, Malaguzzi Valeri L, Murray B, et al. Automated Extraction of Energy Systems Information from Remotely Sensed Data: A Review and Analysis. Applied Energy. 2022 Nov 15;326.
• Calhoun ZD, Lahrichi S, Ren S, Malof JM, Bradbury K. Self-Supervised Encoders Are Better Transfer Learners in Remote Sensing Applications. Remote Sensing. 2022 Nov 1;14(21).
• Ren S, Malof J, Fetter R, Beach R, Rineer J, Bradbury K. Utilizing Geospatial Data for Assessing Energy Security: Mapping Small Solar Home Systems Using Unmanned Aerial Vehicles and Deep Learning. ISPRS International Journal of Geo-Information. 2022 Apr 1;11(4).
• Xu Y, Huang B, Luo X, Bradbury K, Malof JM. SIMPL: Generating Synthetic Overhead Imagery to Address Custom Zero-Shot and Few-Shot Detection Problems. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2022 Jan 1;15:4386–96.
• Huang B, Yang J, Streltsov A, Bradbury K, Collins LM, Malof JM. GridTracer: Automatic Mapping of Power Grids Using Deep Learning and Overhead Imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2022 Jan 1;15:4956–70.
• Hu W, Feldman T, Ou YJ, Tarn N, Ye B, Xu Y, et al. Wind Turbine Detection with Synthetic Overhead Imagery. In: International Geoscience and Remote Sensing Symposium (IGARSS). 2021. p. 4908–11.
• Streltsov A, Malof JM, Huang B, Bradbury K. Estimating residential building energy consumption using overhead imagery. Applied Energy. 2020 Dec 15;280.
• Nair V, Rhee P, Yang J, Huang B, Bradbury K, Malof JM. Designing Synthetic Overhead Imagery to Match a Target Geographic Region: Preliminary Results Training Deep Learning Models. In: International Geoscience and Remote Sensing Symposium (IGARSS). 2020. p. 948–51.
• Hu W, Alexander B, Cathcart W, Hu A, Nair V, Zuo L, et al. Mapping Electric Transmission Line Infrastructure from Aerial Imagery with Deep Learning. In: International Geoscience and Remote Sensing Symposium (IGARSS). 2020. p. 2229–32.
• Huang B, Bradbury K, Collins LM, Malof JM. Do Deep Learning Models Generalize to Overhead Imagery from Novel Geographic Domains? the xGD Benchmark Problem. In: International Geoscience and Remote Sensing Symposium (IGARSS). 2020. p. 1476–9.
• Kong F, Huang B, Bradbury K, Malof JM. The synthinel-1 dataset: A collection of high resolution synthetic overhead imagery for building segmentation. In: Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020. 2020. p. 1803–12.
• Lin K, Huang B, Collins LM, Bradbury K, Malof JM. A simple rotational equivariance loss for generic convolutional segmentation networks: Preliminary results. In: International Geoscience and Remote Sensing Symposium (IGARSS). 2019. p. 3876–9.
• Kong F, Chen C, Huang B, Collins LM, Bradbury K, Malof JM. Training a single multi-class convolutional segmentation network using multiple datasets with heterogeneous labels: Preliminary results. In: International Geoscience and Remote Sensing Symposium (IGARSS). 2019. p. 3903–6.
• Huang B, Reichman D, Collins LM, Bradbury K, Malof JM. On the extraction of training imagery from very large remote sensing datasets for deep convolutional segmenatation networks. In: International Geoscience and Remote Sensing Symposium (IGARSS). 2018. p. 6895–8.
• Streltsov A, Bradbury K, Malof J. Automated building energy consumption estimation from aerial imagery. In: International Geoscience and Remote Sensing Symposium (IGARSS). 2018. p. 1676–9.
• Wang R, Collins LM, Bradbury K, Malof JM. Semisupervised adversarial discriminative domain adaptation, with application to remote sensing data. In: International Geoscience and Remote Sensing Symposium (IGARSS). 2018. p. 3611–4.
• Huang B, Lu K, Audebert N, Khalel A, Tarabalka Y, Malof J, et al. Large-scale semantic classification: Outcome of the first year of inria aerial image labeling benchmark. In: International Geoscience and Remote Sensing Symposium (IGARSS). 2018. p. 6947–50.
• Huang B, Collins LM, Bradbury K, Malof JM. Deep convolutional segmentation of remote sensing imagery: A simple and efficient alternative to stitching output labels. In: International Geoscience and Remote Sensing Symposium (IGARSS). 2018. p. 6899–902.
• Huang B, Knox M, Bradbury K, Collins LM, Newell RG. Non-intrusive load monitoring system performance over a range of low frequency sampling rates. In: 2017 6th International Conference on Renewable Energy Research and Applications, ICRERA 2017. 2017. p. 505–9.
• Qian S, Chelikani S, Wang P, Collins LM, Bradbury K, Malof JM. Trading spatial resolution for improved accuracy when using detection algorithms on remote sensing imagery. In: International Geoscience and Remote Sensing Symposium (IGARSS). 2017. p. 3716–9.
• So B, Nezin C, Kaimal V, Keene S, Collins L, Bradbury K, et al. Estimating the electricity generation capacity of solar photovoltaic arrays using only color aerial imagery. In: International Geoscience and Remote Sensing Symposium (IGARSS). 2017. p. 1603–6.
• Malof JM, Collins LM, Bradbury K. A deep convolutional neural network, with pre-training, for solar photovoltaic array detection in aerial imagery. In: International Geoscience and Remote Sensing Symposium (IGARSS). 2017. p. 874–7.
• Wang R, Camilo J, Collins LM, Bradbury K, Malof JM. The poor generalization of deep convolutional networks to aerial imagery from new geographic locations: An empirical study with solar array detection. In: Proceedings - Applied Imagery Pattern Recognition Workshop. 2017.
• Wang R, Camilo J, Collins LM, Bradbury K, Malof JM. The poor generalization of deep convolutional networks to aerial imagery from new geographic locations: An empirical study with solar array detection. In: Proceedings - Applied Imagery Pattern Recognition Workshop. 2017.
• Malof JM, Chelikani S, Collins LM, Bradbury K. Trading spatial resolution for improved accuracy in remote sensing imagery: An empirical study using synthetic data. In: Proceedings - Applied Imagery Pattern Recognition Workshop. 2017.
• Bradbury K, Saboo R, L Johnson T, Malof JM, Devarajan A, Zhang W, et al. Distributed solar photovoltaic array location and extent dataset for remote sensing object identification. Scientific data. 2016 Dec;3:160106.
• Malof JM, Bradbury K, Collins LM, Newell RG. Automatic detection of solar photovoltaic arrays in high resolution aerial imagery. Applied Energy. 2016 Dec 1;183:229–40.
• Czarnek N, Morton K, Collins L, Newell R, Bradbury K. Performance comparison framework for energy disaggregation systems. In: 2015 IEEE International Conference on Smart Grid Communications, SmartGridComm 2015. 2016. p. 446–52.
• Malof JM, Bradbury K, Collins LM, Newell RG, Serrano A, Wu H, et al. Image features for pixel-wise detection of solar photovoltaic arrays in aerial imagery using a random forest classifier. In: 2016 IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2016. 2016. p. 799–803.
• Malof JM, Collins LM, Bradbury K, Newell RG. A deep convolutional neural network and a random forest classifier for solar photovoltaic array detection in aerial imagery. In: 2016 IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2016. 2016. p. 650–4.
• Malof JM, Hou R, Collins LM, Bradbury K, Newell R. Automatic solar photovoltaic panel detection in satellite imagery. In: 2015 International Conference on Renewable Energy Research and Applications, ICRERA 2015. 2015. p. 1428–31.
• Bradbury K, Pratson L, Patiño-Echeverri D. Economic viability of energy storage systems based on price arbitrage potential in real-time U.S. electricity markets. Applied Energy. 2014 Jan 1;114:512–9.
• Bradbury K, Torrione PA, Collins L. Realtime gaussian markov random field based ground tracking for ground penetrating radar data. In: Proceedings of SPIE - The International Society for Optical Engineering. 2009.
• Bradbury KJ, Noonan JP. Covert binary communications through the application of chaos theory: Three novel approaches. In: CITSA 2007 - Int Conference on Cybernetics and Information Technologies, Systems and Applications and CCCT 2007 - Int Conference on Computing, Communications and Control Technologies, Proceedings. 2007. p. 60–5.
• Bradbury K, Brigman B, Collins L, Johnson T, Lin S, Newell R, et al. Norfolk, Virginia - Aerial imagery object identification dataset for building and road detection, and building height estimation.
• Bradbury K, Brigman B, Collins L, Johnson T, Lin S, Newell R, et al. New York City, New York - Aerial imagery object identification dataset for building and road detection, and building height estimation.
• Bradbury K, Saboo R, Malof J, Johnson T, Devarajan A, Zhang W, et al. Distributed Solar Photovoltaic Array Location and Extent Data Set for Remote Sensing Object Identification.
• Bradbury K, Brigman B, Collins L, Johnson T, Lin S, Newell R, et al. Metadata - Aerial imagery object identification dataset for building and road detection, and building height estimation.
• Bradbury K, Li B, Brigman B, Chandrasekar G, Hossain S, Nagenalli T, et al. Indian Village Satellite Imagery and Energy Access Dataset.
• Bradbury K, Brigman B, Collins L, Johnson T, Lin S, Newell R, et al. San Francisco, California - Aerial imagery object identification dataset for building and road detection, and building height estimation.
• Bradbury K, Saboo R, Johnson T, Malof J, Devarajan A, Zhang W, et al. Oxnard Aerial USGS Imagery from the Distributed Solar Photovoltaic Array Location and Extent Data Set.
• Bradbury K, Brigman B, Collins L, Johnson T, Lin S, Newell R, et al. New Haven, Connecticut - Aerial imagery object identification dataset for building and road detection, and building height estimation.
• Bradbury K, Brigman B, Collins L, Johnson T, Lin S, Newell R, et al. Austin, Texas - Aerial imagery object identification dataset for building and road detection, and building height estimation.
• Bradbury K, Brigman B, Collins L, Johnson T, Lin S, Newell R, et al. Atlanta, Georgia - Aerial imagery object identification dataset for building and road detection, and building height estimation.
• Bradbury K, Brigman B, Chandrasekar G, Collins L, Hossain S, Jeuland M, et al. Power Plant Satellite Imagery Dataset.
• Bradbury K, Brigman B, Collins L, Johnson T, Lin S, Newell R, et al. Seekonk, Massachusetts - Aerial imagery object identification dataset for building and road detection, and building height estimation.
• Bradbury K, Brigman B, Collins L, Johnson T, Lin S, Newell R, et al. Arlington, Massachusetts - Aerial imagery object identification dataset for building and road detection, and building height estimation.
• Bradbury K, Saboo R, Johnson T, Malof J, Devarajan A, Zhang W, et al. Fresno Aerial USGS Imagery from the Distributed Solar Photovoltaic Array Location and Extent Data Set.
• Hu W, Huang B, Bradbury K, Malof J, Nair V, Pathirathna T, et al. Electric Transmission Infrastructure Satellite Imagery Dataset for Computer Vision.
• Bradbury K, Saboo R, Johnson T, Malof J, Devarajan A, Zhang W, et al. Modesto Aerial USGS Imagery from the Distributed Solar Photovoltaic Array Location and Extent Data Set.
• Bradbury K, Saboo R, Johnson T, Malof J, Devarajan A, Zhang W, et al. Stockton Aerial USGS Imagery from the Distributed Solar Photovoltaic Array Location and Extent Data Set.
• Bradbury K, Brigman B, Collins L, Johnson T, Lin S, Newell R, et al. Washington, DC - Aerial imagery object identification dataset for building and road detection, and building height estimation.
• Bradbury K, Han Q, Nair V, Pathirathna T, You X. Electric Transmission and Distribution Infrastructure Imagery Dataset.