David Sterling serves as a Principal R&D Scientist at Maxar Technologies, where he leverages his extensive expertise in quantitative predictive modeling to address complex challenges in scientific and engineering domains. With a robust background in applied mathematics, David specializes in developing advanced statistical models and...
David Sterling serves as a Principal R&D Scientist at Maxar Technologies, where he leverages his extensive expertise in quantitative predictive modeling to address complex challenges in scientific and engineering domains. With a robust background in applied mathematics, David specializes in developing advanced statistical models and deep learning algorithms tailored for computer vision applications. His current research focuses on statistical modeling and deep metric embeddings, particularly in the context of multi-spectral geo-spatial data, where he employs Gaussian Process models for spatial-spectral segmentation. This innovative approach enhances the accuracy and efficiency of data interpretation in remote sensing applications.
In addition to his work on segmentation, David is pioneering research in imperceptible digital watermarking techniques, which are crucial for securing geospatial data integrity. His contributions to the field are underscored by the design and implementation of two proprietary systems, recognized as trade secrets, that showcase his ability to translate theoretical concepts into practical, impactful solutions.
David's proficiency in large-scale data analysis and visualization, combined with his command of tools such as Pandas, NumPy, and TensorFlow, enables him to extract meaningful insights from vast datasets. His work not only advances the state of the art in predictive analytics but also fosters collaboration within interdisciplinary teams, driving innovation at Maxar Technologies. As a thought leader in the integration of machine learning and statistical analysis, David Sterling continues to shape the future of geospatial intelligence and computer vision.
