=Paper=
{{Paper
|id=Vol-3762/575
|storemode=property
|title=Safeguarding the Marine and Coastal Environment with Artificial Intelligence
|pdfUrl=https://ceur-ws.org/Vol-3762/575.pdf
|volume=Vol-3762
|authors=Paola Barra,Francesco Camastra,Angelo Ciaramella,Ciro Giuseppe De Vita,Emanuel Di Nardo,Raffaele Montella,Gennaro Mellone,Vincenzo Scarrica,Antonino Staiano
|dblpUrl=https://dblp.org/rec/conf/ital-ia/BarraCCVNMMSS24
}}
==Safeguarding the Marine and Coastal Environment with Artificial Intelligence==
https://ceur-ws.org/Vol-3762/575.pdf
Safeguarding the Marine and Coastal Environment with
Artificial Intelligence
Paola Barra1,2 , Francesco Camastra1,2 , Angelo Ciaramella1,2,* , Ciro Giuseppe De Vita1,2 ,
Emanuel Di Nardo1,2 , Raffaele Montella1,2 , Gennaro Mellone1,2 , Vincenzo Scarrica1,2 and
Antonino Staiano1,2
1
Dipartimento di Scienze e Tecnologie, Università di Napoli Parthenope, CDN Isola C4, Napoli, 80143, Italy
2
Neptun-IA Lab, Dipartimento di Scienze e Tecnologie, Università di Napoli Parthenope, CDN Isola C4, Napoli, 80143, Italy
Abstract
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 efforts aim to
develop innovative solutions for monitoring, identifying and managing marine areas, offering promising pathways towards
mitigating the impacts of human-induced environmental degradation on coastal and marine ecosystems.
Keywords
Undersea and Beach litter, Litter recognition, Object detection, Instance segmentation, Aerial and marine drone, Smart rover,
Deep optical flow, Digital twin
1. Introduction these processes of physical imbalance, there are, unfor-
tunately, those related to the overexploitation of sandy
Recent reports [1], [2] emphasize how human activity shores, with the consequent alteration of the beach en-
has disrupted coastal balance, exacerbating or even ini- vironment, and sometimes to the disfigurement of the
tiating irreversible erosion processes and leading to the maritime territory, with the consequent loss of landscape
intrusion of salt wedges into regions where agricultural and economic value. In particular, the uncontrolled re-
productivity is vital to the local economy. Moreover, in lease of large quantities of plastic material into the en-
recent years, several international reports by the IPCC 1 vironment is increasingly threatening our seas and the
have emphasized the importance of developing economic marine organisms that live in them. Many of these issues
models that are less dependent on fossil fuels. The lat- are discussed and supported by many relevant national
ter is primarily responsible for rising temperatures on and international bodies and organs, within the Euro-
a global scale, which in turn are responsible for rising pean Community, which seems to be strongly committed
sea levels. In the near future, entire coastal belts may to raising awareness of the above issues. To mention
be permanently invaded by the sea [3]. In addition to some of these bodies, among the most important are
the MedECC (Mediterranean Experts on Climate and
Ital-IA 2024: 4th National Conference on Artificial Intelligence, orga- Environmental Change) [4], regional sea conventions
nized by CINI, May 29-30, 2024, Naples, Italy (OSPAR Commission, Barcelona Convention UN Envi-
*
Corresponding author.
$ paola.barra@uniparthenope.it (P. Barra);
ronment/MAP, HELCOM, Black Sea Commission) [5],
francesco.camastra@uniparthenope.it (F. Camastra); the Italian association Legambiente. This has led the envi-
angelo.ciaramella@uniparthenope.it (A. Ciaramella); ronmental scientific community to promote new projects,
cirogiuseppe.devita@uniparthenope.it (C. G. De Vita); following protocols for the management and sustainable
emanuel.dinardo@uniparthenope.it (E. Di Nardo); use of coastal zones, such as ICZM (Integrated Coastal
raffaele.montella@uniparthenope.it (R. Montella);
gennaro.mellone1@studenti.uniparthenope.it (G. Mellone);
Zone Management) [2].
vinenzo.scarrica@uniparthenope.it (V. Scarrica);
antonino.staiano@uniparthenope.it (A. Staiano)
0000-0002-7692-0626 (P. Barra); 0000-0003-4439-7583 2. Research topics
(F. Camastra); 0000-0001-5592-7995 (A. Ciaramella);
0000-0002-3828-0170 (C. G. De Vita); 0000-0002-6589-9323 (E. Di The monitoring of coastal and marine environments is
Nardo); 0000-0002-4767-2045 (R. Montella); 0000-0002-9545-9978 carried out jointly by the Computer Vision and Pattern
(G. Mellone); 0000-0002-4708-5860 (A. Staiano) Recognition Laboratory (CVPRL) “Alfredo Petrosino”, the
© 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License
1
Attribution 4.0 International (CC BY 4.0).
International Panel on Climate Change - (www.ipcc.ch)
Computational Intelligence & Smart Systems Laboratory
CEUR
ceur-ws.org
Workshop ISSN 1613-0073
Proceedings
(CI&SS), the High-Performance Scientific Computing
Laboratory (HPSC) and the Neptun-IA Interdisciplinary
Laboratory of the University of Naples Parthenope. Arti-
ficial Intelligence (AI) techniques, in particular, Compu-
tational 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 (Mediter-
ranean 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 process-
ing of aerial and submarine images; the development
of object recognition techniques; the development of Figure 1: System workflow (top) and Litter recognition exam-
optimization strategies for garbage collection; the devel- ples (bottom).
opment of techniques for drone guidance; feature drift
detection [6]; Virtual Reality (VR) reconstruction of real
scenes captured by video cameras. The tools have a mini-
area of Apulia located on the Adriatic coast of Upper
mal impact on the environment and can be used in marine
Salento, and Torre Canne, a marine site located a few
protected areas and marine archaeological parks. The ac-
tens of kilometers from Brindisi, which falls within the
tivities are coordinated in the CVPRL “Alfredo Petrosino”
Regional Natural Park of the Dune Costiere, from Torre
and CI&SS labs, which are respectively the Parthenope
Canne to Torre San Leonardo. The results of the tests
node of the CINI Artificial and Intelligent Systems (AIIS)
carried out in this study allowed for defining 10𝑚 as
lab and the CINI BIG Data node, for the development
the desirable drone flight above ground. The proposed
and implementation of the AI algorithms. The HPSC lab
methodology represents a benchmark for the definition of
is the CINI HPC node and develops the HPC architec-
a standardized procedure for the indirect evaluation and
tures required for the AI algorithms. The Neptun-IA lab
monitoring of the coastal environmental status. Besides
provides the necessary expertise for coastal monitoring
allowing the investigation of large areas with limited hu-
issues and the synergy of activities between AI and the
man effort, the proposed system enables the evaluation
environmental domain.
of the beach litter spatial distribution and magnitude,
providing useful information for the assessment of tai-
3. 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 clas-
role in establishing effective 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] reaffirm 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 different eleva- annotated images to obtain significant results, and the an-
tions. 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 ap-
stance 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 hyper-
value and protected areas. The images were acquired graphs. Then, it trains a convolutional network archi-
at 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
This activity aims to study, develop and apply image
processing (IP), DP and CI methods for the detection of
underwater debris using drones. Recent research in the
iMTG (Innovative Marine Technology for Geology & Ar-
chaeology), CI&SS and Neptun-IA laboratories has aimed
at developing a system capable of detecting and recog-
nizing seafloor objects using the ARGO drone. ARGO
is a geophysical information-gathering drone equipped
with several onboard cameras and a device (i.e. Rasp-
berry PI) containing the object recognition module. The
Figure 2: New beach litter recognition and geolocalization limited computational capacity of the hardware and the
pipeline.
need for real-time response imply the design of a model
that optimizes and reduces computational and memory
requirements.
some weak signal. The outputs of the HyperGCN are ArgonautAI [14], is a containerized distributed pro-
called pseudo-labels, which are later used to train a fully cessing platform for autonomous surface vehicles. The
convolutional network for semantic segmentation. The ArgonautAI architecture uses a cluster of single-board
advantage of such a model is accurate semantic segmenta- computers with diverse and different characteristics (com-
tion with small training data sets. Besides, a new version puting power, CUDA GPUs, FPGAs, GPIOs, PWMs, spe-
of this study has been proposed. The updated framework cialized I/O), orchestrated using Kubernetes and a cus-
now incorporates both SAM (SegmentAnything Model) tomized programming interface. The proposed platform
[11] and VIT (Vision Transformer) [12] algorithms to has been applied to AI-based marine debris detection
enhance its capabilities [9]. SAM is utilized for robust using a hierarchical computer vision approach on het-
instance segmentation, ensuring accurate identification erogeneous onboard computing resources. In Fig. 3 the
and delineation of individual objects within the coastal architecture of the platform. This platform has been de-
environment. Additionally, VIT is employed for classifi- signed to be used on the ARGO marine drone for future
cation tasks, allowing for the categorization of various development.
coastal elements such as sand, vegetation, and sea. Fur- Latest studies, as part of the DataX4Sea project, in-
thermore, the geolocalization of each detected instance is clude upgrading the platform with a microservice man-
refined to ensure precise mapping of environmental fea- agement system called DataX[15], based on Kubernetes,
tures globally. This integration of advanced algorithms to improve resource utilization in a real-time manner. To
significantly improves the framework’s performance, en- improve the detection of underwater litter, a study was
abling comprehensive analysis and monitoring of coastal conducted combining two techniques, one for color re-
areas with enhanced accuracy and efficiency (Fig. 2). construction (SeaThru) useful for submarine color correc-
Beach litter recognition is a collaboration with the De-
partment of Earth and Geoenvironmental Sciences, Uni-
versity of Bari Aldo Moro, which provided the images
for analysis, whereas HyperGCN-WSS is a collaboration
with the MIA Laboratory of the University of La Rochelle,
France.
Furthermore, the use of CI based methodologies (i.e.,
deep learning and multi-objective optimization through
genetic algorithms) for predicting marine debris trajec-
tories by UAV and for optimal path recovery for an au-
tonomous vehicle was investigated [13]. For this purpose,
realistic data generated by an oceanographic model (e.g.
Lagrangian and particle drift models) on semi-submerged
bottles were studied. The methodology allows obtaining
the exact location of the marine debris over time and Figure 3: ArgonautAI Platform’s Architecture
then developing a recovery strategy to optimize the time
search (ARGO) is an open project prototype, optimized to
carry out non-invasive, high-resolution indirect surveys
in very shallow water areas, with almost no environmen-
tal impact, allowing it to be also used in marine protected
areas and underwater archaeological parks.
Figure 4: Pipeline for underwater marine litter detection -
Due to the lack of large datasets for underwater ob-
Image is pre-processed using Sea-Thru, then classification is
performed using SCOUTER ject 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 consid-
tion using monocular depth estimation, in conjunction ered environment. Experimental comparisons between a
with the SCOUTER slot-attention based classification general-purpose deep neural model and the same model
model for explainable learning (XAI) [16]. The entire specifically trained with the newly proposed dataset have
pipeline (Fig.4) for floating and underwater marine litter confirmed an increase in the accuracy of the final estima-
classification, was used as part of a particular marine tion.
data crowdsourcing platform, Citizien Science for the
Sea with Information Technologies (C4Sea-IT) for gath-
ering 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 indus-
particular class of CNNs that combines localization and trial plants, the agriculture, and the animal husbandry
classification using a single deep neural network, thus produce effects potentially compromising the aquatic
limiting the explosion of the computational complexity ecosystems, damaging the landscape and the social/eco-
of 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 pre-
systems based on approximate reasoning [19, 20] and vent any possible disease affecting human health, both
data integration methodologies [21]. In Fig. 5 results of chemical and biological origin [23]. However, lever-
of 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 conve-
on 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 hy-
the development and use of drones capable of efficiently 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 pre-
Figure 5: Heatmap of Scouter+ XAI methodology on metal Figure 6: The AIQUAM architecture and data flow for both
marine litter preprocessed by Sea-Thru training ad predict stages.
dict water quality as categorized indexes leveraging an 5. Conclusions
integrated approach between computational components
and artificial intelligence techniques. To face this issue, This paper proposes an overview of the research activ-
AIQUAM (Artificial Intelligence-based water QUAlity ities carried out in the various laboratories of the Uni-
Model), 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 effectively
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 different 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 Intelli-
sult. 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 efficiently
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 effective 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 Com- References
puting 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 effetti 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 time-
oratories of America. scales of days to decades, Coastal Engineering 168
• SE4I (Smart Energy Efficiency & Environment for (2021).
Industry), PON, area di specializzazione: Fabbrica [4] W. Cramer, J. Guiot, M. Fader, J. Garrabou, J.-P. Gat-
Intelligente. 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 mediter-
gistica 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. Sci-
Learning”. cchitano, A. Staiano, A novel beach litter analysis
system based on uav images and convolutional neu- nologies: an open platform for gathering marine
ral networks, Ecological Informatics 72 (2022). data and marine litter detection from leisure boat
[8] A. Sozio, V. M. Scarrica, P. P. Aucelli, G. Scicchitano, instruments, in: 2023 IEEE 19th International Con-
A. Staiano, A. Rizzo, Comparing meanshift/svm and ference on e-Science (e-Science), IEEE, 2023, pp.
mask-rcnn algorithms for beach litter detection on 1–9.
uavs images, in: 2023 IEEE International Workshop [18] A. Ciaramella, F. Perrotta, G. Pappone, P. Aucelli,
on Metrology for the Sea; Learning to Measure Sea P. F., G. Mattei, Environment object detection for
Health Parameters (MetroSea), 2023, pp. 483–487. marine argo drone by deep learning 1266 (2021).
[9] A. Sozio, A. Rizzo, V. M. Scarrica, P. P. C. Aucelli, [19] E. Di-Nardo, A. Ciaramella, Advanced fuzzy real-
G. Anfuso, G. Barracane, L. A. Dimuccio, R. Fer- tional neural network, in: Proccedings of The 13th
reira, M. La Salandra, A. Staiano, M. P. Tarantino, International Workshop on Fuzzy Logic and Appli-
G. Scicchitano, An innovative sam-vit based tool cations (WILF 2021), CEUR Workshop Proceedings,
for the automatic detection of litter items on sandy 2021.
beaches, in: EGU General Assembly 2024, 2024. [20] F. Camastra, et al., A fuzzy decision system for
[10] J. H. Giraldo, V. Scarrica, A. Staiano, F. Camastra, genetically modified plant environmental risk as-
T. Bouwmans, Hypergraph convolutional networks sessment using mamdani inference, Expert Systems
for weakly-supervised semantic segmentation, in: with Applications 42 (2015) 1710–1716.
2022 IEEE International Conference on Image Pro- [21] A. Ciaramella, D. Nardone, A. Staiano, Data inte-
cessing (ICIP), 2022, pp. 16–20. gration by fuzzy similarity-based hierarchical clus-
[11] A. Kirillov, E. Mintun, N. Ravi, H. Mao, C. Rolland, tering, BMC Bioinformatics 21 (2020).
L. Gustafson, T. Xiao, S. Whitehead, A. C. Berg, W.- [22] A. Ferone, M. Lazzaro, V. M. Scarrica, A. Ciaramella,
Y. Lo, P. Dollar, R. Girshick, Segment anything, in: A. Staiano, A synthetic dataset for learning optical
Proceedings of the IEEE/CVF International Confer- flow in underwater environment, in: Applications
ence on Computer Vision (ICCV), 2023, pp. 4015– of Artificial Intelligence and Neural Systems to Data
4026. Science, Smart Innovation, Systems and Technolo-
[12] A. Kolesnikov, et al., An image is worth 16x16 gies, in press.
words: Transformers for image recognition at scale, [23] A. Galletti, R. Montella, L. Marcellino, A. Riccio,
2021. D. Di Luccio, A. Brizius, I. Foster, Numerical and
[13] V. Bevilacqua, A. et al. Di Marino, A. Ciaramella, implementation issues in food quality modeling for
A. A. Biancardi, G. Budillon, P. de Ruggiero, human diseases prevention, in: Special Session on
E. Della Volpe, L. Gifuni, D. Mascolo, S. Pierini, Smart Medical Devices-From Lab to Clinical Prac-
E. Zambianchi, Computational Intelligence for Ma- tice, volume 6, SCITEPRESS, 2017, pp. 526–534.
rine Litter Recovery, Springer Nature Singapore, [24] R. Montella, D. Di Luccio, C. G. De Vita, G. Mel-
2023, pp. 137–145. lone, M. Lapegna, G. Ortega, L. Marcellino, E. Zam-
[14] G. Mellone, C. G. De Vita, D. D. Sánchez-Gallegos, bianchi, G. Giunta, A highly scalable high-
D. Di Luccio, G. Mattei, F. Peluso, P. P. C. Aucelli, performance lagrangian transport and diffusion
A. Ciaramella, R. Montella, A containerized dis- model for marine pollutants assessment, in: 2023
tributed processing platform for autonomous sur- 31st Euromicro International Conference on Par-
face vehicles: Preliminary results for marine litter allel, Distributed and Network-Based Processing
detection, in: 2023 31st Euromicro International (PDP), IEEE, 2023, pp. 17–26.
Conference on Parallel, Distributed and Network- [25] C. G. De Vita, G. Mellone, D. Di Luccio, S. Kosta,
Based Processing (PDP), IEEE, 2023, pp. 144–148. A. Ciaramella, R. Montella, Aiquam: Artificial
[15] G. Coviello, K. Rao, M. Sankaradas, S. Chakradhar, intelligence-based water quality model, in: 2022
Datax: A system for data exchange and transfor- IEEE 18th International Conference on e-Science
mation of streams, in: International Symposium (e-Science), IEEE, 2022, pp. 401–402.
on Intelligent and Distributed Computing, Springer, [26] C. G. De Vita, G. Mellone, F. Barchiesi, D. Di Luccio,
2021, pp. 319–329. A. Ciaramella, R. Montella, Artificial intelligence
[16] A. Maratea, A. Ferone, Deep neural networks and for mussels farm quality assessment and prediction,
explainable machine learning, in: R. Fullér, S. Giove, in: 2022 IEEE International Workshop on Metrol-
F. Masulli (Eds.), Fuzzy Logic and Applications, ogy for the Sea; Learning to Measure Sea Health
Springer International Publishing, Cham, 2019, pp. Parameters (MetroSea), IEEE, 2022, pp. 33–38.
253–256.
[17] C. G. De Vita, G. Mellone, D. D. Sanchez-Gallegos,
G. Coviello, D. Romano, M. Lapegna, A. Ciaramella,
Citizen science for the sea with information tech-