Work Experience
Postdoctoral Research Associate (PDRA), The University of Edinburgh / UK National Centre for Earth Observation (NCEO) 2024 - present
AI, Physics-aware Deep Learning, Earth Observation, Environmental monitoring Python
Postdoctoral researcher at the University of Edinburgh, funded by the UK National Centre for Earth Observation (NCEO) and UKRI SECO project, work on physics-aware and interpretable AI models for biomass estimation from EO data and understanding the relation between radar backscatter-vegetation structure using interpretable AI models.
Developing Process-Guided Concept Bottleneck Models (PG-CBMs).
Teaching AI models to think like an ecologist and try to understand the underlying casual mechanism rather than purely statistical mapping.
Developing interpretable and physics-aware AI models for less biased biomass estimation from EO data.
Postdoctoral Research Assistant, Stanford University / Stockholm School of Economics, (Remote) 2023 - 2024
Remote Sensing, High-Resolution Data, Google Earth Engine (GEE)
Postdoctoral researcher at the Stanford University, Center for Food Security and the Environment (FSE), work on the Market Activity Index (MAI) project to create a remote sensing approach to detect local markets in low-income countries through high-resolution EO data.
Developing change detection and object detection remote sensing approaches.
Processing high-resolution EO data.
Assistant Researcher, Research Center for Spatial Information (CEOSpace Tech) 2020 - 2023
AI, Deep Learning, Computer Vision, Earth Observation, SAR, Python
Assistant Researcher and PhD student at the University POLITEHNICA of Bucharest (UPB), Research Center for Spatial Information (CEOSpaceTech), Bucharest, Romania, in the frame of the MENELAOS-NT European Training Network (ETN) H2020-MSCA-ITN project. The MENELAOS-NT project applies novel technologies to realize multimodal – multi-sensor data fusion to optimally combine the information, delivered by different sensors (in-situ/remote, optical/non-optical) on different scales, with different resolutions, and with different reliability. My main focus in this project was development of various deep learning-based solutions for Synthetic Aperture Radar (SAR) data applications.
Study the fundamentals of SAR imaging systems and image formation.
Elaboration of deep learning-based solutions for various applications of SAR data, such as data compression, land cover classification, and semantic data mining.
Development of the complex-valued deep architectures for complex-valued SAR data.
Development of the complex-valued SAR dataset for training deep architectures, S1SLC-CVDL dataset.
AI Researcher, Research Center for Spatial Information (CEOSpace Tech) - ARTISTE Project 2022 - 2023
AI, Complex-valued Deep Learning, Neural Data Compression, Earth Observation, SAR, Python
Key personnel and AI researcher at the Artificial Intelligence for SAR Data Compression (ARTISTE) project. The project is funded by European Space Agency (ESA) and aims to provide AI-based solutions for SAR raw data compression for future ESA missions in collaboration with DLR and Airbus teams.
Contribution to writing the project proposal.
Development of complex-valued neural data compression methods for SAR data compression.
Visiting Researcher, Zentrum für Sensorsysteme (ZESS) 2021 - 2022
AI, Complex-valued Deep Learning, Computer Vision, Earth Observation, SAR, Python
Research secondment at the University of Siegen, Zentrum für Sensorsysteme (ZESS), Germany, in the frame of the MENELAOS-NT European Training Network (ETN) H2020-MSCA-ITN project. The main focus of the secondment was on the development of complex-valued deep architectures for SAR data classification and comparison between complex- and real-valued architectures.
Development of complex-valued deep architectures.
Comparative study between complex- and real-valued deep architectures for SAR data classification.
Presentation of the results in various conferences and forums, including IGARSS 2022, EuSAR 2022, and MENELAOS Forum 2022.
Researcher, Remote Sensing Lab, K.N. Toosi University of Technology 2016 - 2018
Earth Observation, SAR, Computer Vision, Python
Researcher at the Remote Sensing lab of the faculty of Geodesy & Geomatics Engineering, K.N. Toosi University of Technology. My research focused on developing machine learning algorithms for SAR data classification.
Development of Segment-based Bag of Visual Words (BOVW) method for enhanced SAR data classification.
Master’s research thesis
Source code
