Mediterranean hurricanes, also known as medicanes, can cause significant damage to coastal communities. Consequently, they have been the subject of intense study in recent decades. Geographic Information Systems (GISs) and Web-GIS applications are essential for processing and analyzing geographic data from various sources, particularly in the field of spatial planning. Due to their ability to integrate heterogeneous information, these tools can provide experts with a comprehensive overview of relevant geospatial data. Here, we present ARCHIMEDE, a relational geodatabase connected to an open-source Web-GIS platform focused on Mediterranean hurricanes that contains data from recent research on these extreme weather phenomena. These datasets comprise climatic and oceanographic data obtained from remote sensing techniques as well as seismic and geomorphological data obtained from field observations. Consequently, this Web-GIS platform can enhance our understanding of Mediterranean cyclones by relating the physical properties of these natural phenomena with their impacts on coastal regions. ARCHIMEDE is an innovative tool for the dissemination of geographic information to stakeholders, researchers, and decision-makers, offering valuable support for the development of robust coastal management strategies aimed at mitigating the challenges posed by Mediterranean hurricanes.

A field assessment was carried out in May 2023 in a natural protected area in South Italy to investigate the real-time behavior and fate of common marine litter items at different depths at the nearshore and foreshore under low energetic conditions. The field data were also compared with theoretical values calculated using theoretical formulations considering the Stokes drift current, wind-induced current, and current at breaking position. The wind approached from N to W, with values ranging from 2.4 to 3.8 m/s. The propagated significant wave height ranged from 14 to 21 cm, with an associated period of 3 s. Items with a positive buoyancy recorded different velocities. Very protruding (above water surface) items were greatly affected by windage and recorded velocities from 0.23 to 0.33 m/s; higher than the theoretical values that do not take into account windage. Theoretical values correctly predicted the velocity of other less-protruding items but slightly underestimated the velocity of neutral buoyancy items, evidencing in both cases the low relevance of the Stokes drift current. Items with a negative buoyancy moved (or not) in the bottom with different velocities. Different behaviors were observed at the breaking point, where items surfed (or not) spilling breaking waves, and at the foreshore, where items moved along the plunge step or in a “zig–zag” movement due to a swash–backwash process.

The latest progress in deep learning approaches has garnered significant attention across a variety of research fields. These techniques have revolutionized the way marine parameters are measured, enabling automated and remote data collection. This work centers on employing a deep learning model for the automated evaluation of tide and surge, aiming to deliver accurate results through the analysis of surveillance camera images. A mode of deep learning based on the Inception v3 structure was applied to predict tide and storm surges from surveillance cameras located in two different coastal areas of Italy. This approach is particularly advantageous in situations where traditional tide sensors are inaccessible or distant from the measurement point, especially during extreme events that require accurate surge measurements. The conducted experiments illustrate that the algorithm efficiently measures tide and surge remotely, achieving an accuracy surpassing 90% and maintaining a loss value below 1, evaluated through Categorical Cross-Entropy Loss functions. The findings highlight its potential to bridge the gap in data collection in challenging coastal environments, providing valuable insights for coastal management and hazard assessments. This research contributes to the emerging field of remote sensing and machine learning applications in environmental monitoring, paving the way for enhanced understanding and decision-making in coastal regions.

Coastal monitoring is a rapidly evolving field essential for understanding meteorological and marine conditions, which in turn supports the development of effective strategies for managing coastal areas. This necessity is increasingly critical given the challenges posed by climate change, rising sea levels, and extreme weather events. Among the tools available, video surveillance, combined with advanced machine learning and computer vision techniques, has emerged as a powerful method. It offers detailed spatial and temporal data, essential for analyzing tidal phases, wave parameters, and storm dynamics across extensive geographic areas.In this study, we propose an innovative integration of optical flow techniques with video analysis to accurately quantify wave motion parameters. Optical flow, which evaluates object displacement between video frames, is applied to determine wavelength, wave height, and flow velocity. This approach is particularly suited for storm conditions where traditional methods face logistical and financial constraints. Our method enables high-precision, real-time measurements vital for analyzing coastal processes during extreme events. To ensure reliability, the results are cross-validated with in situ instrument data and verified through environmental reconstructions using point clouds and ground control points. This dual-validation strategy minimizes video distortions and enhances measurement accuracy, aligning optical flow results with physical realities.The proposed system has been tested in a controlled environment at the Coastal Engineering Laboratory of the University of Palermo. A two-dimensional laboratory flume simulated different coastal conditions, ranging from calm waters to storm-like scenarios, ensuring the robustness and adaptability of the methodology. By leveraging optical flow techniques with video surveillance, this approach promises a transformative impact on coastal monitoring, providing continuous, automated, and cost-effective data collection even in remote or inaccessible locations. It offers a scalable alternative to conventional methods, which often demand expensive installations and extensive manpower. The potential of this method to deliver high-quality real-time data, represent a significant advancement in coastal management and environmental monitoring.

Recent advances in Artificial Intelligence (AI) and computer vision have opened new opportunities for automated monitoring and analysis in geomorphology. Among these, optical flow methods represent a powerful approach for quantifying surface velocity fields in rivers using video data. This work presents the development and application of a low-cost optical flow tool designed to estimate river surface velocity from fixed monitoring points, offering a practical and scalable solution for hydrological and flood-risk management applications.The proposed method relies on the implementation of an AI-assisted optical flow algorithm capable of tracking the motion of water surface patterns (e.g., ripples, foam, floating debris) in standard RGB video sequences. By leveraging dense flow estimation and adaptive filtering, the tool produces high-resolution velocity maps that can be continuously updated in near real time. The system has been tested in different riverine environments, showing robust performance under varying lighting and flow conditions, and demonstrating its ability to capture both steady and transient flow dynamics.One of the key strengths of this approach lies in its low operational cost and flexibility. The method can be implemented using conventional cameras and open-source software, eliminating the need for expensive. This makes it particularly suitable for establishing permanent observation points in critical areas, such as flood-prone zones or regions with limited monitoring infrastructure. Continuous optical monitoring of surface velocity provides valuable information for calibrating hydrodynamic models, identifying changes in river morphology, and supporting early-warning systems for extreme hydrological events.Beyond the technical development, this research emphasizes the importance of integrating AI-based monitoring tools within broader frameworks for territorial management and risk mitigation. Establishing collaborations with stakeholders such as Basin Authorities, local governments, and civil protection agencies—can significantly enhance the effectiveness of these systems. Shared data platforms and automated AI-driven analytics could enable more proactive responses to extreme events, improving preparedness and resilience in flood-prone communities.In future developments, the integration of deep learning models for feature detection and noise reduction could further enhance the accuracy and robustness of surface velocity estimation. Combining optical flow data with other remote sensing sources (e.g., UAV imagery, satellite observations) could also provide a multi-scale understanding of fluvial dynamics. This research thus contributes to the growing field of AI applications in geomorphology, highlighting how intelligent, low-cost monitoring systems can play a crucial role in sustainable river management and flood risk assessment.