Publications

Showing 13 of 13 publications

2026

1. GRSL

   Hybrid Machine Learning Model for Forest Height Estimation From TanDEM-X and Landsat Data

   Islam Mansour, Ronny Hänsch, Irena Hajnsek, and 1 more author

   IEEE Geoscience and Remote Sensing Letters, 2026 · Extends the multimodal hybrid AI-physical modeling approach developed during the PhD.

   AbsDOIBibHTMLDetails

   

   A hybrid machine learning model combining TanDEM-X InSAR and Landsat optical data for forest height estimation.

   @article{mansour2026hybridgrsl,
     title = {Hybrid Machine Learning Model for Forest Height Estimation From TanDEM-X and Landsat Data},
     author = {Mansour, Islam and Hänsch, Ronny and Hajnsek, Irena and Papathanassiou, Kostas},
     journal = {IEEE Geoscience and Remote Sensing Letters},
     volume = {23},
     pages = {4008705--4008705},
     year = {2026},
     doi = {10.1109/LGRS.2026.3693644}
   }

2025

1. PhD Thesis

   Hybrid AI–Physical Modeling in Interferometric SAR: Bridging Data-Driven and Physics-Based Approaches for Enhanced Parameter Retrieval

   Islam Mansour

   2025 · Chair of Earth Observation and Remote Sensing. Supervised by Prof. Dr. Irena Hajnsek, co-advised by Dr. Kostas Papathanassiou (PolInSAR / tomographic SAR), Dr. Ronny Hänsch (Machine Learning), and Dr. Georg Fischer (Cryosphere application).

   AbsDOIBibHTMLDetails

   Doctoral thesis on combining data-driven machine learning with physics-based scattering models to improve parameter retrieval from interferometric SAR. Covers forest height retrieval from TanDEM-X and penetration bias correction in X-band InSAR DEMs.

   @phdthesis{mansour2025thesis,
     title = {Hybrid AI--Physical Modeling in Interferometric SAR: Bridging Data-Driven and Physics-Based Approaches for Enhanced Parameter Retrieval},
     author = {Mansour, Islam},
     school = {ETH Zurich},
     year = {2025},
     doi = {10.3929/ETHZ-C-000783509},
     pages = {186}
   }

2. TGRS

   Hybrid Machine Learning Forest Height Estimation From TanDEM-X InSAR

   Islam Mansour, Kostas Papathanassiou, Ronny Hänsch, and 1 more author

   IEEE Transactions on Geoscience and Remote Sensing, 2025 · Noted as relevant to ESA's Biomass mission.

   AbsDOIBibHTMLDetails

   

   A hybrid model-based and machine learning approach to forest height estimation from TanDEM-X InSAR, validated over tropical biomes including Gabon and the Amazon.

   @article{mansour2025hybridtgrs,
     title = {Hybrid Machine Learning Forest Height Estimation From TanDEM-X InSAR},
     author = {Mansour, Islam and Papathanassiou, Kostas and Hänsch, Ronny and Hajnsek, Irena},
     journal = {IEEE Transactions on Geoscience and Remote Sensing},
     volume = {63},
     pages = {1--11},
     year = {2025},
     doi = {10.1109/TGRS.2024.3520387}
   }

3. CVPRW

   Hybrid AI-physical Modeling for Penetration Bias Correction in X-band InSAR DEMs: A Greenland Case Study

   Islam Mansour, Georg Fischer, Ronny Hänsch, and 1 more author

   2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2025 · Extended journal-quality version of the IGARSS 2024 conference paper on the same topic.

   AbsDOIBibHTMLCodeDetails

   

   A hybrid AI-physical method to correct penetration bias in X-band InSAR DEMs over the Greenland Ice Sheet, parameterising the vertical structure function via machine learning.

   @inproceedings{mansour2025hybridcvprw,
     title = {Hybrid AI-physical Modeling for Penetration Bias Correction in X-band InSAR DEMs: A Greenland Case Study},
     author = {Mansour, Islam and Fischer, Georg and Hänsch, Ronny and Hajnsek, Irena},
     booktitle = {2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
     address = {Nashville, TN, USA},
     pages = {2175--2184},
     year = {2025},
     doi = {10.1109/CVPRW67362.2025.00205}
   }

2024

1. IGARSS

   Correction of The Penetration Bias for InSAR DEM Via Synergetic AI-Physical Modeling: A Greenland Case Study

   Islam Mansour, Georg Fischer, Ronny Hänsch, and 2 more authors

   IGARSS 2024 – 2024 IEEE International Geoscience and Remote Sensing Symposium, 2024 · Conference precursor to the extended CVPRW 2025 paper on the same topic.

   AbsDOIBibHTMLCodeDetails

   Rapid changes in the Greenland Ice Sheet require precise elevation monitoring to understand ice dynamics and predict sea level rise. X-band Interferometric Synthetic Aperture Radar (InSAR) has the potential for this purpose but is limited by microwave signal penetration biases, which can be a few meters. We present a novel hybrid modeling approach that integrates machine learning (ML) with physical models to enhance the estimation of the elevation bias in InSAR data at X-band.

   @inproceedings{mansour2024correction,
     title = {Correction of The Penetration Bias for InSAR DEM Via Synergetic AI-Physical Modeling: A Greenland Case Study},
     author = {Mansour, Islam and Fischer, Georg and Hänsch, Ronny and Hajnsek, Irena and Papathanassiou, Kostas},
     booktitle = {IGARSS 2024 -- 2024 IEEE International Geoscience and Remote Sensing Symposium},
     pages = {138--142},
     year = {2024},
     doi = {10.1109/IGARSS53475.2024.10642748}
   }

2. IGARSS

   Characterization of Forest Structure Changes Exploiting TanDEM-X and GEDI Synergies

   L. M. Albrecht, N. Basargin, Islam Mansour, and 4 more authors

   International Geoscience and Remote Sensing Symposium (IGARSS), 2024 · Co-authored (Islam is a contributing author, not lead).

   AbsBibHTMLDetails

   The objective of this paper is to discuss experimentally potentials and perspectives of the synergetic combination of spatially continuous TanDEM-X interferometric measurements at X-band and sampled GEDI lidar waveforms to map forest height and structure changes at high resolution and large scale.

   @inproceedings{albrecht2024characterization,
     title = {Characterization of Forest Structure Changes Exploiting TanDEM-X and GEDI Synergies},
     author = {Albrecht, L. M. and Basargin, N. and Mansour, Islam and Guliaev, R. and Romero Puig, N. and Pardini, M. and Papathanassiou, Kostas},
     booktitle = {International Geoscience and Remote Sensing Symposium (IGARSS)},
     pages = {1--4},
     year = {2024}
   }

2023

1. TSX/TDX STM

   Synergizing AI and Physical Models for TanDEM-X InSAR Forest Height Estimation: A Hybrid Approach over the Gabon

   Islam Mansour, Kostas Papathanassiou, Ronny Hänsch, and 1 more author

   TerraSAR-X / TanDEM-X Science Team Meeting, 2023

   AbsBibHTMLDetails

   Presents the hybrid AI-physical forest height estimation approach applied over Gabon, at the TerraSAR-X/TanDEM-X Science Team Meeting.

   @inproceedings{mansour2023synergizing,
     title = {Synergizing AI and Physical Models for TanDEM-X InSAR Forest Height Estimation: A Hybrid Approach over the Gabon},
     author = {Mansour, Islam and Papathanassiou, Kostas and Hänsch, Ronny and Hajnsek, Irena},
     booktitle = {TerraSAR-X / TanDEM-X Science Team Meeting},
     year = {2023}
   }

2. BioGeoSAR

   Combining AI Techniques with Physical Models: Forest Height Inversion from TanDEM-X InSAR Data Using a Hybrid Modeling Approach

   Islam Mansour, Kostas Papathanassiou, Ronny Hänsch, and 1 more author

   BioGeoSAR Book of Abstracts, 2023

   AbsBibHTMLDetails

   In this study, we propose a novel hybrid modeling approach that combines machine learning techniques and physical models to invert forest height from TanDEM-X InSAR data. Accurate estimation of forest height is crucial for understanding forest structure and biomass, which in turn plays a pivotal role in climate change mitigation and ecosystem management. This approach might be relevant for the Biomass mission.

   @inproceedings{mansour2023combining,
     title = {Combining AI Techniques with Physical Models: Forest Height Inversion from TanDEM-X InSAR Data Using a Hybrid Modeling Approach},
     author = {Mansour, Islam and Papathanassiou, Kostas and Hänsch, Ronny and Hajnsek, Irena},
     booktitle = {BioGeoSAR Book of Abstracts},
     year = {2023}
   }

3. IGARSS

   Combining TanDEM-X and GEDI Data For Mapping Forest Structure Parameter Dynamics

   Islam Mansour, L. M. Albrecht, B. Hartweg, and 5 more authors

   International Geoscience and Remote Sensing Symposium (IGARSS), 2023

   AbsBibHTMLDetails

   The synergy of TanDEM-X interferometric data with GEDI lidar full waveform measurements for large-scale forest mapping, including a forest height map derived from the combination of TanDEM-X and GEDI data over the whole Brazilian Amazon (12,000+ TanDEM-X scenes, 250 million GEDI lidar measurements).

   @inproceedings{mansour2023combining1,
     title = {Combining TanDEM-X and GEDI Data For Mapping Forest Structure Parameter Dynamics},
     author = {Mansour, Islam and Albrecht, L. M. and Hartweg, B. and Guliaev, R. and Romero Puig, N. and Kim, J. and Pardini, M. and Papathanassiou, Kostas},
     booktitle = {International Geoscience and Remote Sensing Symposium (IGARSS)},
     year = {2023}
   }

4. POLinSAR

   Machine Learning in Model-Based Forest Height Inversion

   Islam Mansour, Kostas Papathanassiou, Ronny Hänsch, and 1 more author

   POLinSAR Online Abstracts, 2023 · Presented at the ESA POLinSAR Workshop (2023).

   AbsBibHTMLDetails

   Model-based (PM) forest height inversion from Polarimetric Interferometric Synthetic Aperture Radar (Pol-InSAR) measurements is today an established application demonstrated and validated at large scales for a wide variety of boreal and tropical forest sites at different frequencies. However, as with any model-based inversion approach, there are inherent limitations that can restrict expected performance depending on the individual case.

   @inproceedings{mansour2023machine,
     title = {Machine Learning in Model-Based Forest Height Inversion},
     author = {Mansour, Islam and Papathanassiou, Kostas and Hänsch, Ronny and Hajnsek, Irena},
     booktitle = {POLinSAR Online Abstracts},
     year = {2023}
   }

2022

1. EUSAR

   Towards a Symbiosis of Model-Based and Machine Learning Forest Height Estimation Based on TanDEM-X InSAR

   Islam Mansour, Kostas Papathanassiou, Ronny Hänsch, and 1 more author

   EUSAR 2022; 14th European Conference on Synthetic Aperture Radar, 2022

   AbsBibHTMLDetails

   

   This paper contributes to the generalization of forest height inversion by comparing the performance of two Machine Learning (ML) approaches for estimating forest height from single baseline single-polarimetric TanDEM-X (single-pass) interferometric coherence measurements against state-of-art physical-model estimates.

   @inproceedings{mansour2022towards,
     title = {Towards a Symbiosis of Model-Based and Machine Learning Forest Height Estimation Based on TanDEM-X InSAR},
     author = {Mansour, Islam and Papathanassiou, Kostas and Hänsch, Ronny and Hajnsek, Irena},
     booktitle = {EUSAR 2022; 14th European Conference on Synthetic Aperture Radar},
     pages = {1--4},
     year = {2022}
   }

2021

1. MSc Thesis

   Analysis of Multi-Frequency Polarimetric SAR Data over Permafrost Regions

   Islam Mansour

   2021

   AbsBibHTMLDetails

   Multi-frequency polarimetric SAR analysis of the 2018-2019 PermASAR airborne campaign over the permafrost region of Herschel Island, northwest Canada. Completed as part of the ESPACE program at TUM, with DLR's Microwaves and Radar Institute.

   @mastersthesis{mansour2021analysis,
     title = {Analysis of Multi-Frequency Polarimetric SAR Data over Permafrost Regions},
     author = {Mansour, Islam},
     school = {Technical University of Munich (TUM)},
     year = {2021}
   }

2019

1. Report

   3D Matching of TerraSAR-X Derived Ground Control Points to Mobile Mapping Data

   L. Loesch, Islam Mansour, M. Reich, and 1 more author

   2019

   AbsBibDetails

   Machine learning algorithms for 3D matching of TerraSAR-X-derived ground control points with mobile LiDAR mapping data, for georeferencing of pole-like structures. Technical report developed with Airbus Defence and Space.

   @techreport{loesch2019matching,
     title = {3D Matching of TerraSAR-X Derived Ground Control Points to Mobile Mapping Data},
     author = {Loesch, L. and Mansour, Islam and Reich, M. and Xie, X.},
     institution = {TUM Data Innovation Lab},
     year = {2019}
   }