I received my bachelor and masters degree in geophysics from the Aristotle University of Thessaloniki in 2009 and 2011 respectively, where my research focused in near surface geophysics including electrical resistivity tomography (ERT), potential methods, seismics and ground penetrating radar (GPR).
In 2015 I received my PhD from The University of Edinburgh under a project co-funded by the Defence Science and Technology Laboratory (DSTL) and the Engineering and Physical Sciences Research Council (EPSRC). My research focused on numerical modelling of GPR for landmine detection and has been awarded with the best paper awart at the 15th International Conference of GPR. During my PhD, as a member of COST (European Cooperation in Science and Technology) Action TU1208, I was a visiting researcher at Roma Tre University working on applications of GPR to civil engineering. Subsequently, I was employed as postdoctoral researcher at Delft University of Technology (TUDelft) in the Microwave Sensing, Signals and Systems (MS3) group. There, I worked for D-Box, an industry oriented project aimed to deliver end-user tools for efficient demining. After finishing my national service in the Greek army I was employed by the University of Edinburgh under a project funded by Google fiber. Subsequently, I was employed by University of West London as a research fellow where I focused on applications of near surface geophysics and non-destructive testing for forestry and arboriculture applications. Lastly, I am a frequnet reviewer in journals associated with geophysics and I am part of the team behind gprMax, an open-source FDTD solver tuned for GPR.
My research focus and direction is on using innovative artificial intelligence concepts, signal processing and inversion to solve problems in applied geophysics and non-destructive testing. It is a novel combination of my background in geology/geophysics,and the experience I have developed in successfully employing machine learning and signal processing for non-destructive testing,and geophysical investigation. Consequently, my research extends across a wide range of disciplines and has focused on topics with high societal value such as landmine detection, marine geophysics and forestry applications. I have a robust theoretical and practical understanding of computational geophysics, inversion, signal processing, data science and neural networks and have collaborated with international researchers to apply these tools in electrodynamics, geophysics and non-destructive testing.
Data-driven interpretation and machine learning in exploration geophysics
Landmine detection using ground penetrating radar
Non-destructive testing for civil engineering and urban geophysics
Applications of near surface geophysics for forestry and arboriculture applications
Page 1 of 5 Results 1 to 10 of 50
Evidence of shallow basaltic lava layers in Von Kármán crater from Yutu-2 lunar Penetrating RadarIcarus (New York, N.Y. 1962), vol. 408, 115837Contributions to Journals: Articles
A flexible deep learning crater detection scheme using Segment Anything Model (SAM)Icarus, vol. 408, 115797Contributions to Journals: Articles
GPR Full-Waveform Inversion With Deep-Learning Forward Modeling: A Case Study From Non-Destructive TestingIEEE Transactions on Geoscience and Remote Sensing, vol. 61, 2003910Contributions to Journals: Articles
Layered Structures in the Upper Several Hundred Meters of the Moon Along the Chang'E-4 Rover's First 1,000-m TraverseJournal of Geophysical Research: Planets, vol. 128, no. 8, e2022JE007714Contributions to Journals: Articles
Stochastic hyperbola fitting, probabilistic inversion, reverse-time migration and clustering: A novel interpretation toolbox for in-situ planetary radarIcarus (New York, N.Y. 1962), vol. 400, 115555Contributions to Journals: Articles
Background Removal, Velocity Estimation, and Reverse-Time Migration: A Complete GPR Processing Pipeline Based on Machine LearningIEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1-11Contributions to Journals: Articles
A deep learning framework based on improved self-supervised learning for ground-penetrating radar tunnel lining inspectionComputer-Aided Civil and Infrastructure EngineeringContributions to Journals: Articles
Extracting mud invasion information using borehole radar - A numerical studyGeophysics, vol. 88, no. 2, pp. D69-D83Contributions to Journals: Articles
Unveiling the Subsurface of Late Amazonian Lava Flows at Echus Chasma, on MarsRemote Sensing, vol. 15, no. 5, 1357Contributions to Journals: Articles
Deep learning–based nondestructive evaluation of reinforcement bars using ground-penetrating radar and electromagnetic induction dataComputer-Aided Civil and Infrastructure Engineering, vol. 37, no. 14, pp. 1834-1853Contributions to Journals: Articles