Ilyas Yalcin

Remote sensing has become a core technology for environmental and climate monitoring, supported by expanding sensor constellations, advanced processing capabilities, and coordination frameworks established by the European Space Agency (ESA), Global Earth Observation System of Systems (GEOSS), and Committee on Earth Observation Satellites (CEOS). Ensuring consistency across missions requires robust geometric and radiometric calibration and validation. However, traditional reliance on ground control points (GCPs) is limited by sparse global coverage, temporal instability, and dependence on surveyed accuracy. While alternative geospatial datasets, including satellite and aerial imagery, Light Detection and Ranging (LiDAR) point clouds, and vector databases, can serve as references, challenges remain in data access, automation, and cross-sensor applicability. This study proposes a generative adversarial network (GAN)-based approach to generate geometrically consistent image chips from vector maps. Two models were trained at 50 cm and 10 m resolution within the ESA-supported Generative Ground Control Point (GenCP) study, using Sentinel-2 and very-high-resolution RGB imagery. The generated GenCP image chips are evaluated using image similarity (radiometric consistency), as well as geometric and model-performance metrics. The results demonstrate their suitability for automated Cal/Val workflows and their potential as scalable, fit-for-purpose reference datasets.

Remote sensing has become a core technology for environmental and climate monitoring, supported by expanding sensor constellations, advanced processing capabilities, and coordination frameworks established by the European Space Agency (ESA), Global Earth Observation System of Systems (GEOSS), and Committee on Earth Observation Satellites (CEOS). Ensuring consistency across missions requires robust geometric and radiometric calibration and validation. However, traditional reliance on ground control points (GCPs) is limited by sparse global coverage, temporal instability, and dependence on surveyed accuracy. While alternative geospatial datasets, including satellite and aerial imagery, Light Detection and Ranging (LiDAR) point clouds, and vector databases, can serve as references, challenges remain in data access, automation, and cross-sensor applicability. This study proposes a generative adversarial network (GAN)–based approach to generate geometrically consistent image chips from vector maps. Two models were trained at 50 cm and 10 m resolution within the ESA-supported Generative Ground Control Point (GenCP) study, using Sentinel-2 and very-high-resolution RGB imagery. The generated GenCP image chips are evaluated using image-based similarity (radiometric consistency), geometric, and model-performance metrics. Results demonstrate their suitability for automated Cal/Val workflows and their potential as scalable, fit-for-purpose reference datasets.

This study presents a digital twin–based framework for assessing rockfall hazards at the immediate vicinity of the Rumkale Archaeological Site, a geologically sensitive and culturally significant location in southeastern Türkiye. Historically associated with early Christianity and strategically located along the Euphrates, Rumkale is a protected heritage site that attracts increasing numbers of visitors. Here, high-resolution photogrammetric models were generated using imagery acquired from a remotely piloted aircraft system and post-processed with ground control points to produce a spatially accurate 3D digital twin. Field-based geomechanical measurements including discontinuity orientations, joint classifications, and strength parameters were integrated with digital analyses to identify and evaluate hazardous rock blocks. Kinematic assessments conducted in the study revealed susceptibility to planar, wedge, and toppling failures. The results showed the role of lithological structure, active tectonics, and environmental factors in driving slope instability. The proposed methodology demonstrates effective use of digital twin technologies in conjunction with traditional geotechnical techniques, offering a replicable and non-invasive approach for site-scale hazard evaluation and conservation planning in heritage contexts. This work contributes to the advancement of interdisciplinary methods for geohazard-informed management of cultural landscapes.

Discontinuity is a key element used by geoscientists and civil engineers to characterize rock masses. The traditional approach to detecting and measuring rock discontinuity relies on fieldwork, which poses dangers to human life. Photogrammetric pattern recognition and 3D measurement techniques offer new possibilities without direct contact with rock masses. This study proposes a new approach to detect discontinuities using close-range photogrammetric techniques and convolutional neural networks (CNNs) trained on a small amount of data. Investigations were conducted on basalts in Bala, Ankara, Türkiye. A total of 34 multi-view images were collected with a remotely piloted aircraft system (RPAS), and discontinuity lines were manually delineated on a point cloud generated from these images. The lines were back-projected onto the raw images to increase the amount of data, a process we call multi-view (3D) augmentation. We further evaluated radiometric and geometric augmentation methods, the contribution of multi-view augmentation to the proposed model, and the transfer learning performance of six different CNN architectures. The highest performance was achieved with U-Net + SE-ResNeXt-50 with an F1-score of 90.6%. The CNN model trained from scratch with local features also yielded a similar F1-score (91.7%), which is the highest performance reported in the literature.

The detection and continuous updating of buildings in geodatabases has long been a major research area in geographic information science and is an important theme for national mapping agencies. Advancements in machine learning techniques, particularly state-of-the-art deep learning (DL) models, offer promising solutions for extracting and modeling building rooftops from images. However, tasks such as automatic labelling of learning data and the generalizability of models remain challenging. In this study, we assessed the sensor and geographic area adaptation capabilities of a pretrained DL model implemented in the ArcGIS environment using very-high-resolution (50 cm) SkySat imagery. The model was trained for digitizing building footprints via Mask R‑CNN with a ResNet50 backbone using aerial and satellite images from parts of the USA. Here, we utilized images from three different SkySat satellites with various acquisition dates and off-nadir angles and refined the pretrained model using small numbers of buildings as training data (5–53 buildings) over Ankara. We evaluated the buildings in areas with different characteristics, such as urban transformation, slums, regular, and obtained high accuracies with F‑1 scores of 0.92, 0.94, and 0.96 from SkySat 4, 7, and 17, respectively. The study findings showed that the DL model has high transfer learning capability for Ankara using only a few buildings and that the recent SkySat satellites demonstrate superior image quality.

Surface modeling constitutes is a crucial aspect in numerous engineering inquiries and earth observation endeavors. In contemporary times, the acquisition of geospatial data essential for the digital representation of local regions is increasingly facilitated through drone-based methodologies, supplanting conventional terrestrial data gathering techniques. The market presently hosts a plethora of cost-effective, "ready-to-fly" unmanned aerial vehicles (UAVs), offering users the capability to generate photogrammetric outputs, including high geometric precision Digital Elevation Models (DEMs). Moreover, modularly structured drone development kits, designed for multifarious applications, are readily accessible for purchase. These drone kits offer an economically advantageous platform that users can customize to suit their specific needs. Nevertheless, the geometric precision of DEMs created using these kits hinges upon the capabilities of the imaging and navigation systems, in addition to the stabilization of the platform during autonomous flight. In this study, using a drone development kit and a commercial drone, simultaneous image acquisition was performed for the same study area and two different DEMs were produced. The efficacy of the DEM generated using the drone development kit was assessed through a comparative analysis with the DEM obtained from a commercial drone. In addition, geometric accuracy assessment was conducted for both DEMs using ground control points. The findings reveal the usability of drone development kits in precision DEM production, as well as their limitations.

Cal/Val activities within the Earthnet Data Assessment Pilot (EDAP) Project of the European Space Agency (ESA) cover several Earth Observation (EO) satellite sensors, including Third-Party Missions (TPMs). As part of the validation studies of very-high-resolution (VHR) sensor data, the geometric and radiometric quality of the images and the mission compliance of the SkySat satellites owned by Planet were evaluated in this study. The SkySat constellation provides optical images with a nominal spatial resolution of 50 cm, and has the capacity for multiple visits of any place on Earth each day. The evaluations performed over several test sites for the purpose of the EDAP Maturity Matrix generation show that the high resolution requirement is fulfilled with high geometric accuracy, although various systematic and random errors could be observed. The 2D and 3D information extracted from SkySat data conform to the quality expectations for the given resolution, although improvements to the vendor-provided rational polynomial coefficients (RPCs) are essential. The results show that the SkySat constellation is compliant with the specifications and the accuracy results are within the ranges claimed by the vendor. The signal-to-noise ratio assessments revealed that the quality is high, but variations occur between the different sensors.

Earthquake, depending on its intensity and location of epicentre, is one of the destructive hazards. Disaster mitigation after a severe earthquake are important to minimize its detrimental effects. Nowadays, several scientific disciplines, such as biodiversity, ecology, geosciences, natural hazards etc., utilize the Citizen Science (CitSci) approaches for various purposes, since the relevant attributes can easily be provided by non-experts with mobile devices. With the CitSci method, disaster related information can be identified and provided rapidly by locals during or after a disaster. Timely, in-situ data after an earthquake can also be collected with CitSci approaches via mobile devices, which can be even more important for all countries. In addition, scientific studies on earthquakes can be enriched and accelerated by using the information provided by volunteers. By collecting reliable data with the CitSci method, the disaster mitigation efforts can be improved, and losses may be decreased. This study aims at developing a CitSci pilot project by using the data collected by volunteers (citizens) to reduce the need for field work in creating earthquake iso-intensity maps and produce them promptly. The present study was based on the 6.8 Mw Elazig earthquake occurred at 20:55 UTC on January 24th, 2020. Through the mobile application “I felt the quake”, the observations of citizens regarding the earthquake were collected. The intensities were revised from the Modified Mercalli Intensity Scale. With the help of data, an iso-intensity map was created and compared to the map produced by The Disaster and Emergency Management Presidency (AFAD), Turkey.

Nowadays several scientific disciplines utilize Citizen Science (CitSci) as a research approach. Natural hazard research and disaster management also benefit from CitSci since people can provide geodata and the relevant attributes using their mobile devices easily and rapidly during or after an event. An earthquake, depending on its intensity, is among the highly destructive natural hazards. Coordination efforts after a severe earthquake event are vital to minimize its harmful effects and timely in-situ data are crucial for this purpose. The aim of this study is to perform a CitSci pilot study to demonstrate the usability of data obtained by volunteers (citizens) for creating earthquake iso-intensity maps in a short time. The data were collected after a 5.8 Mw Istanbul earthquake which occurred on 26 September 2019. Through the mobile app “I felt the quake”, citizen observations regarding the earthquake intensity were collected from various locations. The intensity values in the app represent a revised form of the Mercalli intensity scale. The iso-intensity map was generated using a spatial kriging algorithm and compared with the one produced by The Disaster and Emergency Management Presidency (AFAD), Turkey, empirically. The results show that collecting the intensity information via trained users is a plausible method for producing such maps.