David Moffatمشاهده پروفایل
پژوهشگر
David Moffat serves as AI and Machine Learning Data Scientist at Plymouth Marine Laboratory, leading organization-wide AI initiatives to advance environmental and marine research through cutting-edge data science methodologies. His work bridges computer science expertise with critical ecological challenges, leveraging both traditional and modern AI techniques to extract insights from complex environmental datasets. His academic credentials include: BSc in Artificial Intelligence and Computer Science (University of Edinburgh) MSc in Signal Processing (Queen Mary University of London) PhD in Computer Science (Queen Mary University of London) Moffat's research centers on applied artificial intelligence with specialization in signal processing and time series analysis for environmental applications. He develops AI solutions for air-sea interaction studies, phytoplankton dynamics monitoring, invasive species mapping using drone technology, and audio processing systems. His methodological approach combines deep learning with domain-specific knowledge to create robust models for understanding complex natural systems under changing environmental conditions. Dr. Moffat actively secures research funding through major projects including NEODAAS, SCOPE DEAL, Marine Geospatial Foundation Models, and DEFRA-ASIP. These initiatives support collaborative research across environmental science domains and have enabled him to deliver specialized AI training to over 300 professionals. His leadership drives institutional capacity building in data science while maintaining strong connections to academic research through publications and conference contributions. At Plymouth Marine Laboratory, Moffat heads the AI research team that develops and implements machine learning frameworks across environmental monitoring programs. The team focuses on creating transferable AI models for marine applications, integrating satellite data with in-situ measurements, and developing practical tools for ecosystem management that balance scientific rigor with real-world usability.








