Geomorphology in the Digital Age: A Case Study Project of Quantitative Geomorphology from Images Anselme Muzirafuti dept. Mathematics, Informatics, Physics and Earth Sciences University of Messina Messina, Italy anselme.muzirafuti@unime.it Giancarlo Faina CoReMa Spiagge srl, Bologna, Italy gfaina2@gmail.com Stefania Lanza Geologis srl Messina, Italy stefania.lanza@unime.it Mohammed El Hafyani Moulay Ismail University, Morocco m.elhafyani@edu.umi.ac.ma Diego Paltrinieri CoReMa Spiagge srl, Bologna, Italy dpaltrinieri59@gmail.com Giovanni Randazzo dept. Mathematics, Informatics, Physics and Earth Sciences University of Messina Messina, Italy giovanni.randazzo@unime.it Abstract—In this paper we present the framework, data description, and main steps involved in the implementation of monitoring and forecasting systems aiming at the quantitative geomorphology of coastal areas. We demonstrate that such an objective can be achieved by considering current advanced technologies in Earth Observation and in remote sensing related research fields which provide the amount of data containing information on different geomorphological processes and landforms. Interpretation and analyses of these data into a Geographic information system (GIS) environment and the ability to share, visualize and store the results using the internet, allows for the implementation of monitoring and forecasting system through WebGIS necessary for product display and infrastructures at-risk assessment. Keywords—UAV, photogrammetry, LiDAR, Remote sensing, machine learning, Land cover/land use, robotics, drone, satellite, WebGIS I. INTRODUCTION Globally, natural ecosystems are being affected by the current changes in climate [1]. The effects have been observed on littoral territories of coastal areas in the Mediterranean and low-laying regions in general [2]. In Italy, discussions related to the mitigation of hydrogeological risks, the protection of nature, and biodiversity have been the dominant subject for geoscientists [3]. Recently, several funding instruments for research activities have been adopted, primary for recovering from the effects of Covid-19 but also for promoting cohesion and sustaining regional development. In this case, the need to create networks for monitoring in support of planning which could counter the effects of territorial instability linked to the effects of Climate Change is essential. However, such tasks require an advanced and integrated monitoring and forecasting system [4]. In Sicily, to overcome hydrogeological territory instabilities we must move on from the current management tools to a dynamic planning system that is strongly interconnected between local administrations and central government [5]. In this sense, the Regional Plan Against Coastal Erosion has been drafted and approved as a scientific management tool taking into consideration geomorphological and sedimentological aspects [6]. Based on the know-how acquired during the pocket Beach Management and Remote Surveillance System (BESS) (Interreg Italia Malta) project [5] we proposed the “Quantitative Geomorphology from Images” project. The main objectives and the purpose of this project is to harness the lasted remote sensing technological advancement in Robotics, platforms (Satellite and drones), geologic mapping, and Artificial intelligence (Machine learning algorithms) (Figs. 1, 2, 3), (Tabs. I, II) and develop coastal monitoring tools that are crucial for studying climate change impacts in low laying ecosystems territories. In this way, we proposed mathematical models useful for (1) satellite-derived bathymetry mapping, (2) shoreline forecasting, (3) sediment volume estimation, and (4) infrastructure-at-risk assessment studies. TABLE I. SENSORS DESCRIPTIONS Advanced Sensors Bands used and sensor characteristics Sentinel 2 MSI For 4 bands of 10 m of spatial resolution B2 458-523 (nm) Blue B3 543-578 (nm) Green B4 650-680 (nm) Red B10 785-900 (nm) NIR Landsat 8, 9 OLI For 4 bands of 30 m of spatial resolution B2 450-510 (nm) Blue B3 530-590 (nm) Green B4 640-670 (nm) Red B5 850-880 (nm) NIR Mavic 2 Pro Hasselblad camera with 3 bands (RGB) GNSS TOPCON Hiper HR receiver Differential global positioning system LiDAR Zenmuse L1 High precision IMU, Mid70 LiDAR Sensor, Visual assistant camera, 1 inch CMOS camera (45 Mpix), 3 Axis Gimbal Single beam Echosounder DGPS Garmin CSX 60 signal differential WAAS EGNOA