The effects of climate change are causing an increase in the frequency and extent of natural disasters. Because of their morphological characteristics, rivers can cause major flooding events. Indeed, they can be subjected to variations in discharge in response to heavy rainfall and riverbank failures. Among the emerging methodologies that address the monitoring of river flooding, those that include the combination of Unmanned Aerial Vehicle (UAV) and photogrammetric techniques (i.e., Structure from Motion-SfM) ensure the high-frequency acquisition of high-resolution spatial data over wide areas and so the generation of orthomosaics, useful for automatic feature extraction. Trainable Weka Segmentation (TWS) is an automatic feature extraction open-source tool. It was developed to primarily fulfill supervised classification purposes of biological microscope images, but its usefulness has been demonstrated in several image pipelines. At the same time, there is a significant lack of published studies on the applicability of TWS with the identification of a universal and efficient combination of machine learning classifiers and segmentation approach, in particular with respect to classifying UAV images of riverine environments. In this perspective, we present a study comparing the accuracy of nine combinations, classifier plus image segmentation filter, using TWS, also with respect to human photo-interpretation, in order to identify an effective supervised approach for automatic river features extraction from UAV multi-temporal orthomosaics. The results, which are very close to human interpretation, indicate that the proposed approach could prove to be a valuable tool to support and improve the hydro-geomorphological and flooding hazard assessments in riverine environments.

The combined use of Unmanned Aerial Vehicles (UAVs) and Structure from Motion (SfM) photogrammetry allows the collection and processing of high-resolution data on demand, which is key for the constant and detailed monitoring of the fluvial environment. In addition, through the ever-increasing development of new techniques of mapping and data processing (i.e., UAVs swarm, BVLOS flight missions, high-performance photogrammetry workflow), it is now possible to detect large areas at high-resolution, providing support for spatiotemporal insights into hydro-geomorphological processes and hazard assessment, in order to ensure an effective management and to prevent catastrophic phenomena (i.e., floods). The main goal of this paper is to use UAV-based high-resolution topographic data to constrain the probabilistic hazard assessment of extended reaches of Basento river (Basilicata, Italy). To demonstrate the influence of geomorphology and riverbed sediment on hazard assessment, a sensitivity analysis was carried out on the resolution of the UAV-derived DEMs; on the riverbed roughness coefficient resulting from photo-sieving analysis and on the morphological change detection over short-time ranges (2019-2021). We found that lower resolution DEMs lead to an increase of flooding probability (in several river cross-sections an increase even higher than 99 % resulted), and that a greater roughness coefficient involves an increase in the probability of flooding (with a maximum increase of about 9 %). Moreover, the multitemporal high-resolution outputs resulting from SfM allowed the identification of morphological changes, in short-times, caused by an anthropic modification of the river bank, which significantly affected the flooding hazard.

High-resolution flood monitoring can be achieved relying on multi-temporal analysis of remote sensing SAR data, through the implementation of semi-automated systems. Exploiting a Bayesian inference framework, conditioned probabilities can be estimated for the presence of floodwater at each image location and each acquisition date. We developed a procedure for efficient monitoring of floodwaters from SAR data cubes, which adopts a statistical modelling framework for SAR backscatter time series over normally unflooded areas based on Gaussian processes (GPs), in order to highlight flood events as outliers, causing abrupt variations in the trends. We found that non-parametric time series modelling improves the performances of Bayesian probabilistic inference with respect to state-of-the-art methodologies using, e.g., parametric fits based on periodic functions, by both reducing false detections and increasing true positives. Our approach also exploits ancillary data derived from a digital elevation model, including slopes, normalized heights above nearest drainage (HAND), and SAR imaging parameters such as shadow and layover conditions. It is here tested over an area that includes the so-called Metaponto Coastal Plain (MCP), in the Basilicata region (southern Italy), which is recurrently subject to floods. We illustrate the ability of our system to detect known (although not ground-truthed) and smaller, undocumented inundation events over large areas, and propose some consideration about its prospective use for contexts affected by similar events, over various land cover scenarios and climatic settings.

Digital elevation models (DEMs) represent a fundamental resource in geomorphological analysis. The increasing availability of open‐access DEMs over wide areas is advantageous, but requires an evaluation of DEM quality and errors. This work applies a hierarchical assessment of global, continental and national DEMs in Italy in order to explore the differences and analyze the vertical accuracy, spatial error distribution and agreement of morphometric measurements. The selected DEMs are compared with local reference data as a ground points dataset, extracted from the national geodetic network, and regional DEMs at high spatial resolution, through both a qualitative and a quantitative approach. The results identify limits and potentialities of the selected DEMs, showing accuracy and errors in height representation, also affected by the topographic characteristics of the surface, such as steep slope in mountain zones and some defects in hydromorphological derivatives that could condition the geomorphological applications.

In this study, different approaches for detecting of beach litter (BL) items in coastal environments are applied: the direct in situ survey, an indirect image analysis based on the manual visual screening approach, and two different automatic segmentation and classification tools. One is a Mask-RCNN based-algorithm, already used in a previous work, but specifically improved in this study for multi-class analysis. Test cases were carried out at the Torre Guaceto Marine Protected Area (Apulia Region, southern Italy), using a novel dataset from images acquired in different coastal environments by tailored photogrammetric Unmanned Aerial Vehicle (UAV) surveys. The analysis of the overall methodologies used in this study highlights the potential exhibited by the two machine learning (ML) techniques (Mask-RCCN-based and SVM algorithms), but they still show some limitations concerning direct methodologies. The results of the analysis show that the Mask-RCNN-based algorithm requires further improvements and a consistent increase in the number of training elements, while the SVM algorithm shows limitations related to pixel-based classification. Furthermore, the outcomes of this research highlight the high suitability of ML tools for assessing BL pollution and contributing to coastal conservation efforts.

Over the past two decades, natural hazards have claimed the lives of tens of thousands of people worldwide, every year. Unmanned Aerial Vehicles (UAVs) are pivotal in natural hazard management, offering rapid deployment, flexibility, and cost-effectiveness. Advances such as Beyond Visual Line Of Sight (BVLOS) missions, swarm surveying, Artificial Intelligence (AI), edge-computing, and Structure from Motion (SfM) photogrammetry enhance their high-resolution spatiotemporal data capabilities, but the need for large datasets poses challenges in terms of storage, computational resources and, especially, processing time. This work introduces an original high-performance UAV photogrammetry workflow through the implementation of an open-source distributed approach using the ReCaS-Bari HPC cluster. Performance tests of the workflow, that includes computing parallelism, GPU usage, and hybrid bundle adjustment, demonstrate a significant reduction in processing time for large UAV image datasets. The workflow outperformed current methods, reducing processing time from 908 down to 104 min for 2,691 images and handling 11,549 images in just 7.8 h (a 70 % improvement over leading commercial software). Comparative analysis with cluster-based state-of-the-art approaches revealed noteworthy reductions, reaching up to 86 % for about 7,000 images. A case study, focusing on the Basento river (Southern Italy) flood event occurred in May 2023, proved the workflow practical implications in emergency management. A change detection assessment facilitated the identification and quantification of flood-induced morphological alterations along a 3 km of river reach length within about 3 h. The results highlight the workflow utility in providing accurate and near real-time information for emergency management, enhancing situational awareness and facilitating informed decision-making during disastrous events.