Leibniz Universität Hannover Faculty Faculty of Civil Engineering and Geodetic Science
Deutsch Contact Deutsch
Geodetic Institute
 
Geodetic Institute Hanover Institute Team Kourosh Shahryarinia
Research projects

Research projects of Kourosh Shahryarinia, M. Sc.

  • OpenData4InfMon: Monitoring with GNSS sensors and open data
    The ageing infrastructure on land, rail and water requires significant resources to ensure operational safety. The monitoring of deformations, especially on bridge structures and other important infrastructure, caused by ageing, material fatigue and slow (also climate-related) ground movements, is currently very cost-intensive. It is therefore necessary to develop and evaluate mass-applicable and cost-efficient analysis methods based on open data sources combined with local GNSS sensors, which do not yet exist. The project will investigate the possibilities of strict fusion of free GNSS and radar data as well as 3D city models and traffic route plans for the purpose of better assessment of deformations on structures in combination with locally installed sensor technology, in particular on infrastructures such as railroad lines, power lines and (bridge) structures. The added value of the data is generated in particular by AI analyses and spatiotemporal parameter estimation in combination with local GNSS data.
    Led by: Prof. Dr.-Ing. Ingo Neumann, Dr.-Ing. Mohammad Omidalizarandi
    Team: Kourosh Shahryarinia, M. Sc.
    Year: 2023
    Funding: Bundesministerium für Digitales und Verkehr (BMDV)
    Duration: 03/2023 – 08/2024
  • Large-Scale InSAR Deformation Monitoring Using Realistic Simulation-Based Training of a Deep Learning Model
    Large-scale land surface deformation monitoring using Interferometric Synthetic Aperture Radar (InSAR) requires robust detection of changes in long-term deformation trends. However, accurate change point (CP) detection remains challenging due to the complex characteristics of InSAR time series, including seasonal and quasi-periodic components, as well as noise. Classical statistical methods and many existing deep learning approaches rely on restrictive assumptions or training data that do not fully represent real-world InSAR time series, resulting in limited generalization capability and scalability for large-scale operational applications. This study focuses on the use of deep learning models to address these challenges.
    Led by: Prof. Dr.-Ing. Ingo Neumann, Dr.-Ing. Mohammad Omidalizarandi
    Team: Kourosh Shahryarinia, M. Sc.
    Year: 2024
    Funding: DAAD Research Grant
    Duration: 10/2024 - 09/2027
    © GIH

Last Change: 27.03.26 Print

Contact us
Contact