The increased development of computer vision technology combined with the increased availability of innovative platforms with ultra-high-resolution sensors, has generated new opportunities and fields for investigation in the engineering geology domain in general and landslide identification and characterization in particular. During the last decade, the so-called Unmanned Aerial Vehicles (UAVs) have been evaluated for diverse applications such as 3D terrain analysis, slope stability, mass movement hazard and risk management. Their advantages of detailed data acquisition at a low cost and effective performance identifies them as leading platforms for site-specific 3D modelling. In this study, the proposed methodology has been developed based on Object-Based Image Analysis (OBIA) and fusion of multivariate data resulted from UAV photogrammetry processing in order to take full advantage of the produced data. Two landslide case studies within the territory of Greece, with different geological and geomorphological characteristics, have been investigated in order to assess the developed landslide detection and characterization algorithm performance in distinct scenarios. The methodology outputs demonstrate the potential for an accurate characterization of individual landslide objects within this natural process based on ultra high-resolution data from close range photogrammetry and OBIA techniques for landslide conceptualization. This proposed study shows that UAV-based landslide modelling on the specific case sites provides a detailed characterization of local scale events in an automated sense with high adaptability on the specific case site.

The 6 February 2023 earthquake doublet (Mw 7.7 and Mw 7.6) that occurred on the East Anatolian Fault Zone (EAFZ) triggered a significant amount of soil liquefaction phenomena in SE Türkiye and NW Syria. The great areal extent of the affected area and the necessity of rapid response led to the adoption and improvement of a workflow for mapping liquefaction phenomena based on remote sensing data. Using satellite imagery, we identified 1850 sites with liquefaction manifestation and lateral spreading deformation. We acquired a thorough map of earthquake-triggered liquefaction based on visual mapping with optical satellite imagery (high and very high-resolution) and the aid of radar satellite imagery and interferometry. The majority of sites are found along meandering sections of river valleys, coastal plains, drained lakes, swamps, and lacustrine basins along the East Anatolian Fault, highlighting once again the influence of geomorphology/surficial geology on the distribution of liquefaction phenomena. A total of 95% of the liquefaction occurrences were mapped within 25 km from the surface trace of the fault, confirming the distance from fault rupture as a more effective tool for predicting the distribution of liquefaction than epicentral distance. Thus, taking into consideration the rapid documentation of these phenomena without the limitations in terms of time, cost, and accessibility of the field investigation techniques, this desktop-based approach can result in a rapid and comprehensive map of liquefaction from a strong earthquake, and can also be used as a future guide for subsequent field investigations for liquefaction hazard mapping.

Landslides are a critical geological phenomenon with devastating and catastrophic consequences. With the recent advancements in the geoinformation domain, landslide documentation and inventorization can be achieved with automated workflows using aerial platforms such as unmanned aerial vehicles (UAVs). As a result, ultra-high-resolution datasets are available for analysis at low operational costs. In this study, different segmentation and classification approaches were utilized for object-based landslide mapping. An integrated object-based image analysis (OBIA) workflow is presented incorporating orthophotomosaics and digital surface models (DSMs) with expert-based and machine learning (ML) algorithms. For segmentation, trial and error tests and the Estimation of Scale Parameter 2 (ESP 2) tool were implemented for the evaluation of different scale parameters. For classification, machine learning algorithms (K- Nearest Neighbor, Decision Tree, and Random Forest) were assessed with the inclusion of spectral, spatial, and contextual characteristics. For the ML classification of landslide zones, 60% of the reference segments have been used for training and 40% for validation of the models. The quality metrics of Precision, Recall, and F1 were implemented to evaluate the models’ performance under the different segmentation configurations. Results highlight higher performances for landslide mapping when DSM information was integrated. Hence, the configuration of spectral and DSM layers with the RF classifier resulted in the highest classification agreement with an F1 value of 0.85.

Late years, innovative close-range remote sensing technology such as Unmanned Aerial Vehicle (UAV) photogrammetry and Terrestrial Laser Scanning (TLS) are widely applied in the field of geoscience due to their efficiency in collecting data about surface morphology. Their main advantage stands on the fact that conventional methods are mainly collecting point measurements such as compass measurements of bedding and fracture orientation solely from accessible areas. The current research aims to demonstrate the applicability of UAVs in managing landslide and rockfall hazard in mountainous environments during emergency situations using object-based approach. Specifically, a detailed UAV survey took place in a test site namely as Proussos, one of the most visited and famous Monasteries in the territory of Evritania prefecture, in central Greece. An unstable steep slope across the sole road network results in continuous failures and road cuts after heavy rainfall events. Structure from Motion (SfM) photogrammetry is used to provide detailed 3D point clouds describing the surface morphology of landslide objects. The latter resulted from an object-based classification approach of the photogrammetric point cloud products into homogeneous and spatially connected elements. In specific, a knowledge-based ruleset has been developed in accordance with the local morphometric parameters. Orthomosaic and DSM were segmented in meaningful objects based on a number of geometrical and contextual properties and classified as a landslide object (scarp, depletion zone, accumulation zone). The resulted models were used to detect and characterize 3D landslide features and provide a hazard assessment in respect to the road network. Moreover, a detailed assessment of the identified failure mechanism has been provided. The proposed study presents the effectiveness and efficiency of UAV platforms to acquire accurate photogrammetric datasets from high-mountain environments and complex surface topographies and provide a holistic object-based framework to characterize the failure site based on semantic classification of the landslide objects.