Deep Remote Sensing Group

Circling the Earth in a spaceship, I marveled at the beauty of our planet. People of the world, let us safeguard and enhance this beauty, and not destroy it!

Yuri Gagarin

Welcome to DeRS. Positioned at the intersection of artificial intelligence and remote sensing, our group focuses on advancing several imaging techniques through deep learning–based models. By integrating information from diverse spectral bands, we aim to extract meaningful patterns from the Earth’s surface even under incomplete or degraded data conditions.

Principle Investigators

Dr. Erdem Akagündüz is an associate professor with the Graduate School of Informatics (METU) and the principal investigator of the GAIA group. His research interests cover computer vision and applied deep learning.

Dr. İrem Ülkü is a faculty member at Ankara University and a affiliated principal investigator of the DERS Group. Her research interests include artificial intelligence, machine learning, and pattern recognition, with particular focus on multispectral image segmentation and remote sensing analytics.

Projects

  • “Development of a Multimodal Transformer-Based Semantic Segmentation Model Robust to Missing Wavelengths in Remote Sensing Images and Adaptable to Different Precision Agriculture Applications”
    TÜBİTAK ARDEB 3501 (Pr No: 124E725) February 2025 – May 2026
    Supervisor: Dr. İrem Ülkü
    Co-Supervisor: Dr. Erdem Akagündüz, Dr. Özgür Tanrıöver
    Research Students: Özgü Özkan, Laya Moridsedaghat

Publications

  • (2024) Ülkü İ., Tanrıöver Ö. Ö., Akagündüz E., LoRA-NIR: Low-Rank Adaptation of Vision Transformers for Remote Sensing with Near-Infrared Imagery IEEE Geoscience and Remote Sensing Letters, vol.21, 2024 (SCI-Expanded)
  • (2022) Ülkü İ., Akagündüz E., A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D Images, Applied Artificial Intelligence, vol.36, no.1, 2022 (SCI-Expanded)
  • (2022) Ülkü İ., Akagündüz E., Ghamisi P., Deep Semantic Segmentation of Trees Using Multispectral Images,IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol.15, pp.7589–7604, 2022 (SCI-Expanded)
  • (2022) Ülkü İ., Akagündüz E., Semantic Segmentation of Crop Areas in Remote Sensing Imagery using Spectral Indices and Multiple Channels, 15th International Conference on Machine Vision (ICMV), Rome, Italy, 18–20 November 2022, vol.12701.