Coastal and marine ecosystems face ongoing threats from both human activities and natural processes. Human intervention over the past century has disrupted coastal equilibrium, leading to irreversible phenomena. The unchecked release of plastic waste, for example, further compounds these challenges, posing a severe threat to marine life, the health of our seas. In these last years, the CVPR, CI&SS, and HPSC Labs, associated with the interdisciplinary Lab Neptun-IA at the University of Napoli Parthenope's Department of Science and Technology, have embarked on initiatives to address beach and undersea litter detection and recognition. Leveraging Artificial Intelligence and Computer Vision technologies, these eforts aim to develop innovative solutions for monitoring, identifying and managing marine areas, ofering promising pathways towards mitigating the impacts of human-induced environmental degradation on coastal and marine ecosystems.
these processes of physical imbalance, there are, unfortunately, those related to the overexploitation of sandy shores, with the consequent alteration of the beach environment, and sometimes to the disfigurement of the maritime territory, with the consequent loss of landscape and economic value. In particular, the uncontrolled release of large quantities of plastic material into the environment is increasingly threatening our seas and the marine organisms that live in them. Many of these issues are discussed and supported by many relevant national and international bodies and organs, within the European Community, which seems to be strongly committed to raising awareness of the above issues. To mention some of these bodies, among the most important are the MedECC (Mediterranean Experts on Climate and Environmental Change) [4], regional sea conventions (OSPAR Commission, Barcelona Convention UN Environment/MAP, HELCOM, Black Sea Commission) [5], the Italian association Legambiente. This has led the environmental scientific community to promote new projects, following protocols for the management and sustainable use of coastal zones, such as ICZM (Integrated Coastal Zone Management) [2].
Recent reports [1], [2] emphasize how human activity has disrupted coastal balance, exacerbating or even initiating irreversible erosion processes and leading to the intrusion of salt wedges into regions where agricultural productivity is vital to the local economy. Moreover, in recent years, several international reports by the IPCC1 have emphasized the importance of developing economic models that are less dependent on fossil fuels. The latter is primarily responsible for rising temperatures on a global scale, which in turn are responsible for rising sea levels. In the near future, entire coastal belts may be permanently invaded by the sea [3]. In addition to (CI&SS), the High-Performance Scientific Computing Laboratory (HPSC) and the Neptun-IA Interdisciplinary Laboratory of the University of Naples Parthenope. Artiifcial Intelligence (AI) techniques, in particular, Computational Intelligence (CI), Machine Learning (ML), Deep Learning (DL), and Computer Vision (CV) are applied to the field of interest for the detection of anthropogenic debris released in coastal and marine environments using aerial and underwater drones. These activities follow the numerous guidelines established by MedECC (Mediterranean Experts on Climate and Environmental Change), with the support of the European Community, and aim at protecting those marine and coastal ecosystems where the rate of pollution is increasing. The research involves the implementation of several tasks, such as the processing of aerial and submarine images; the development of object recognition techniques; the development of optimization strategies for garbage collection; the development of techniques for drone guidance; feature drift detection [6]; Virtual Reality (VR) reconstruction of real scenes captured by video cameras. The tools have a minimal impact on the environment and can be used in marine protected areas and marine archaeological parks. The activities are coordinated in the CVPRL “Alfredo Petrosino” and CI&SS labs, which are respectively the Parthenope node of the CINI Artificial and Intelligent Systems (AIIS) lab and the CINI BIG Data node, for the development and implementation of the AI algorithms. The HPSC lab is the CINI HPC node and develops the HPC architectures required for the AI algorithms. The Neptun-IA lab provides the necessary expertise for coastal monitoring issues and the synergy of activities between AI and the environmental domain. area of Apulia located on the Adriatic coast of Upper Salento, and Torre Canne, a marine site located a few tens of kilometers from Brindisi, which falls within the Regional Natural Park of the Dune Costiere, from Torre Canne to Torre San Leonardo. The results of the tests carried out in this study allowed for defining 10 as the desirable drone flight above ground. The proposed methodology represents a benchmark for the definition of a standardized procedure for the indirect evaluation and monitoring of the coastal environmental status. Besides allowing the investigation of large areas with limited human efort, the proposed system enables the evaluation of the beach litter spatial distribution and magnitude, providing useful information for the assessment of tai3. Task descriptions lored beach quality indices. Additional comparisons in the realm of machine learning for beach litter monitoring 3.1. Beach litter recognition systems have been conducted, juxtaposing the QGIS ML Toolkit against the methodology presented in this study.
Beach litter monitoring [7], [8], [9] programs play a key The QGIS ML Toolkit employs segmentation and clasrole in establishing efective management measures to sification processes independently, utilizing Meanshift preserve the ecological, scenic, and economic value of and Support Vector Machine algorithms, respectively. the coastal areas. In this study, an innovative analysis The findings of [ 8] reafirm the superior performance of system is proposed for the automatic identification of Mask-RCNN when compared to traditional methods. beach debris on aerial-photogrammetric images acquired Since models for instance segmentation require many by unmanned aerial vehicles (UAV) at diferent eleva- annotated images to obtain significant results, and the antions. A first version of the workflow (Fig. 1) is based notation process, although supported by software tools on a Mask-RCNN model [7], here actually used for in- for labeling, is extremely time-consuming, a new apstance segmentation tasks (Fig. 1). Test cases were con- proach based on HyperGraph Convolutional Networks is ducted along the Adriatic sector of the Apulia region developed for a Weakly-supervised semantic segmenta(Italy), where the beaches have remarkable economic im- tion (HyperGCN-WSS) [10]. Specifically, HyperGCN-WSS portance, attracting national and international tourists, constructs spatial and k-Nearest Neighbor (k-NN) graphs and ecological values, hosting species of high ecological from the images in the dataset to generate the hypervalue and protected areas. The images were acquired graphs. Then, it trains a convolutional network archiat two coastal sites, Torre Guaceto, a marine protected tecture with specialized hypergraphs (HyperGCN) using and distance of the automated catamaran that will be responsible for the recovery of the marine debris. 3.2. Underwater litter detection tion using monocular depth estimation, in conjunction with the SCOUTER slot-attention based classification model for explainable learning (XAI) [16]. The entire pipeline (Fig.4) for floating and underwater marine litter classification, was used as part of a particular marine data crowdsourcing platform, Citizien Science for the Sea with Information Technologies (C4Sea-IT) for gathering marine data from leisure boat instruments[17]. For 3.3. Mussels farm quality assessment and the detection of environmental objects a system based prediction on a Deep Neural Networks [18] has been designed for The quality of coastal marine waters is representative of the marine ARGO drone. The proposed architecture is the environmental sustainability of the human activities based on the Single Shot MultiBox Detector model, a in the area. However, the urban settlements, the indusparticular class of CNNs that combines localization and trial plants, the agriculture, and the animal husbandry classification using a single deep neural network, thus produce efects potentially compromising the aquatic limiting the explosion of the computational complexity ecosystems, damaging the landscape and the social/ecoof the network. nomic sectors. Monitoring the impact of the pollutants
The expected results of the research are the produc- on the sea is crucial for coastal human activities, such tion of a tool capable of innovating and automating the as aquaculture. In addition, fish and mussel farms are process of detection and removal of solid waste in marine critically sensitive to seawater quality and thus require environments employing “explainable” decision-making continuous monitoring to enforce food security and presystems based on approximate reasoning [19, 20] and vent any possible disease afecting human health, both data integration methodologies [21]. In Fig. 5 results of chemical and biological origin [23]. However, leverof combining the color reconstruction technique for un- aging a continuous microbiological laboratory analysis derwater images (Sea-Thru) object classification based is unfeasible for costs and practical reasons. A conveon the SCOUTER model. The degree of innovation of nient solution is a computational approach to mitigate the proposed research is high, as there is currently no the coast connected to the in-situ monitoring and predict established scientific research in this direction involving the water quality evolution concerning the coastal hythe development and use of drones capable of eficiently drodynamics and the known pollution source activities exploring shallow-water marine coastal environments. [24].
Moreover, the marine drone that will be used in the re
This study aims to develop a novel methodology to presearch (ARGO) is an open project prototype, optimized to carry out non-invasive, high-resolution indirect surveys in very shallow water areas, with almost no environmental impact, allowing it to be also used in marine protected areas and underwater archaeological parks.
Due to the lack of large datasets for underwater object recognition tasks, a synthetic dataset of underwater scenes with optical flow labels [ 22] has been created to demonstrate the benefits of training a specific deep neural model for optical flow estimation in the considered environment. Experimental comparisons between a general-purpose deep neural model and the same model specifically trained with the newly proposed dataset have confirmed an increase in the accuracy of the final estimation.
dict water quality as categorized indexes leveraging an integrated approach between computational components and artificial intelligence techniques. To face this issue, This paper proposes an overview of the research activAIQUAM (Artificial Intelligence-based water QUAlity ities carried out in the various laboratories of the UniModel), a decision-making tool based on coupling HPC versity of Naples Parthenope that attempt, with strong numerical models with three artificial intelligence (AI) and close cooperation and collaboration, to efectively models [25, 26], has been developed (Fig. 6). AIQUAM address issues concerning the preservation of marine and implements an AI model for seawater quality predictions. coastal environments. As shown, they try to approach The model performs time series classification leverag- the various problems using low environmental impact ing various and diferent algorithms and then performs approaches, which therefore, neither damage nor modify a weighted majority report for predicting the best re- the pre-existing ecosystem. The use of Artificial Intellisult. AIQUAM aims to predict the contaminant levels in gence is a key factor in being able to enable such results, mussels to support the local authorities in monitoring using state-of-the-art techniques and developing new aquaculture. ones. This allows the results to be optimized to be reliable in a complex context such as maritime. In addition, the possibility of being able to use these systems eficiently 4. Projects is also possible thanks to the optimization obtained from the high-performance architectures modeled during the • SMARTWIN (Digital Twin and Fintech Services various research projects that are reported. The synergy for Sustainable Supply Chain), progetto MISE. between the laboratories and the other partners involved, • PAS (PAESAGGI ARCHEOLOGICI SOMMERSI allows, therefore, to attempt to solve the problems that
DELLA CAMPANIA), progetto MISE. man himself has created, making it efective and of great • Computational Intelligence Methods for Digital importance to continue to invest energies in the imple
Health, GNCS. mentation of such projects. • HPC-Based navigation system for Marine Litter hunting, FF4EUROHPC .
• Tecniche di Machine Learning e di Soft Computing per l’elaborazione di dati MultiVARIATI [1] M. D. V. L. Bonora, D. Carboni (Ed.), Eighth (SOFTMULAN), Dipartimento di Scienze e International Symposium on Monitoring Tecnologie, Università degli Studi di Napoli of Mediterranean Coastal Areas. Problems Parthenope. and Measurement Techniques, Proceeding • Progetto Parco Archeologico Urbano di Napoli and Report, Firenze University Press, 2020. (PAUN), PON 03PE 00164, Rete Intelligente dei doi:10.36253/978-88-5518-147-1.
Parchi Archeologici (RIPA - PAUN). [2] MATTM-Regioni, Linee Guida per la Difesa della • Erasmus+ “Framework for Gamified Program- Costa dai fenomeni di Erosione e dagli efetti dei ming Education” (FGPE). Cambiamenti climatici, Technical Report, Docu• Euro-HPC H2020 “Adaptive multi-tier intelligent mento elaborato dal Tavolo Nazionale sull’Erosione data manager for Exascale” (ADMIRE). Costiera MATTM-Regioni con il coordinamento • DataX4Sea project (DX4S) (CUP tecnico di ISPRA, 2018.
I63C22000270005) funded by the NEC Lab- [3] M. Davidson, Forecasting coastal evolution on timeoratories of America. scales of days to decades, Coastal Engineering 168 • SE4I (Smart Energy Eficiency & Environment for (2021).
Industry), PON, area di specializzazione: Fabbrica [4] W. Cramer, J. Guiot, M. Fader, J. Garrabou, J.-P. GatIntelligente. tuso, A. Iglesias, M. lange, P. Lionello, M. Llasat, • Convenzione con Unlimited Technology srl S. Paz, et al, Climate change and interconnected nell’ambito del progetto H2020 “Piattaforma Lo- risks to sustainable development in the meditergistica Integrata 4.0 - P.L.I 4.0”. ranean, Nature Climate Change 8 (2018) 972–980. • Convenzione di ricerca DIST-Università di Napoli [5] A. Addamo, P. Laroche, G. Hanke, Top marine beach Parthenope e Dipartimento di Scienze della Terra litter items in europe, 2017. doi:10.2760/496717. e Geoambientali dell’Università degli Studi di [6] A. Ferone, A. Maratea, Adaptive quick reduct for Bari “Aldo Moro”, “Monitoraggio dell’Ambiente feature drift detection, Algorithms 14 (2021). Costiero e della Marine & Beach Litter Attraverso [7] V. Scarrica, P. Aucelli, C. Cagnazzo, A. Casolaro, Metodi di Indagine Diretti, Indiretti e di Machine P. Fiore, M. L. Salandra, A. Rizzo, G. Scardino, G. SciLearning”. cchitano, A. Staiano, A novel beach litter analysis