Advancing Sustainability: Research Initiatives at the Signals and Images Lab Antonio Bruno1 , Claudia Caudai1 , Francesco Conti1,2 , G. Riccardo Leone1 , Massimo Magrini1 , Massimo Martinelli1 , Davide Moroni1,∗ , Awais Ch Muhammad1,3,4 , Oscar Papini1 , Maria Antonietta Pascali1 , Gabriele Pieri1 , Marco Reggiannini1,3 , Marco Righi1 , Emanuele Salerno1 , Andrea Scozzari1 and Marco Tampucci1 1 Signals and Images Lab, Istituto di Scienza e Tecnologie dell’Informazione “A. Faedo”, ISTI-CNR, 56124, Pisa 2 Dipartimento di Matematica, Università di Pisa, 56127, Pisa 3 Dipartimento di Informatica, Università di Pisa, 56127, Pisa 4 National Biodiversity Future Center, Palermo, 90133, Italy Abstract In this paper, we aim to briefly survey the relations of the work conducted at the Signals and Images Lab of CNR-ISTI, Pisa, with the themes of sustainability. We explore both the broader implications and the application-specific aspects of our work, highlighting references to published research and collaborative projects undertaken with key stakeholders and industrial partners. Keywords Sustainability, Computer vision, Deep learning, Ensembling, Topological data analysis, Smart cameras, Precision agriculture, Hydrological modelling, Artificial Groundwater Recharge, Medical waste, Urban mobility, Environmental monitoring, Citizen science 1. Introduction explainability, trustworthiness, and accountability of AI models emerges as crucial, as these attributes are con- The relationship between Sustainability and Artificial In- sidered fundamental for ensuring the sustainability and telligence (AI) is multifaceted. On the one hand, Artificial acceptance of AI technologies. Intelligence can aid in addressing the challenges of mod- Despite the recent concerns and regulatory initiatives ernization that may potentially conflict with sustainabil- of the European Community, AI holds immense potential ity goals. However, on the other hand, energy-intensive to be harnessed for advancing the sustainable develop- methods employed in artificial intelligence applications ment goals outlined by the United Nations, surpassing may themselves pose sustainability concerns. In addition, established targets and identifying new challenges. many paradigms and models within artificial intelligence Given the significance of these themes, numerous are difficult to manage and maintain in a sustainable facets of the research conducted at the Signals and Im- bias-free way, particularly under the dynamic and non- ages Lab (SI Lab) of CNR-ISTI have been directed towards stationary nature of societal and technological changes. enhancing sustainability across various levels and encom- In this context, the association with the principles of passing a broad spectrum of globally relevant applica- tions. Ital-IA 2024: 4th National Conference on Artificial Intelligence, orga- In particular, after describing efficient models based nized by CINI, May 29-30, 2024, Naples, Italy on a new ensembling strategy in Section 2.1, we report ∗ Corresponding author. recent results concerning agriculture (Section 2.2), hydro- Envelope-Open antonio.bruno@isti.cnr.it (A. Bruno); claudia.caudai@isti.cnr.it dynamical modelling and access to water resources (Sec- (C. Caudai); francesco.conti@isti.cnr.it (F. Conti); giuseppericcardo.leone@cnr.it (G. R. Leone); tion 2.3), recycling and end-of-waste for medical waste massimo.magrini@isti.cnr.it (M. Magrini); (Section 2.4), urban mobility (Section 2.5), biodiversity massimo.martinelli@isti.cnr.it (M. Martinelli); (Section 2.6) and citizen science for maritime applications davide.moroni@isti.cnr.it (D. Moroni); (Section 2.7). chmuhammad.awais@phd.unipi.it (A. Ch Muhammad); To address such a wide group of applications, an arse- oscar.papini@isti.cnr.it (O. Papini); maria.antonietta.pascali@isti.cnr.it (M. A. Pascali); nal of different methods was devised, tested and validated; gabriele.pieri@isti.cnr.it (G. Pieri); marco.reggiannini@isti.cnr.it they can be tracked back mainly to general machine learn- (M. Reggiannini); marco.righi@isti.cnr.it (M. Righi); ing theory, computer vision and pervasive computing, emanuele.salerno@isti.cnr.it (E. Salerno); topological data analysis and reliability analysis of ob- andrea.scozzari@isti.cnr.it (A. Scozzari); marco.tampucci@isti.cnr.it served data. (M. Tampucci) © 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). CEUR ceur-ws.org Workshop ISSN 1613-0073 Proceedings Output b0 weak learners trained to overfit on their respective Combination Layer subsets. In the study, we explored the limits of ensem- ble size by utilizing only two weak learners. We found Features Features 1 2 that this adaptive ensemble strategy remains efficient, Output Module Output Module even when extended to include up to five weak learners. Features 1 2 Features Additionally, we identified potential avenues for further Feature Feature improvements, such as implementing various bagging Extractor Extractor strategies (e.g., training weak learners on subsets cate- gorized by class dimensionality, clustering, or different Input Input colour space mappings of inputs). The basic idea of the method is depicted in Figure 1; in particular, ensembling Input is accomplished by an innovative strategy of performing bagging at the deep feature level. Namely, only the con- Figure 1: Proposed ensembling method volutional layers of each trained weak model are kept, while the final decisional layers are neglected; in this way, each weak model is turned into an extractor of deep 2. Research topics features. The deep features of each weak model are then concatenated and fed to a trainable final decision layer. 2.1. Adapting ensembling for green AI These findings lay the groundwork for exploring simi- In the realm of greenAI, computer vision stands out as a lar strategies in various domains, such as Object Detec- field greatly benefiting from deep learning, continually tion (by performing the ensemble at the feature extrac- advancing the state-of-the-art through the utilization of tion backbone level) and Segmentation (by conducting convolutional neural networks (CNNs) and visual trans- the ensemble on the encoding within typical encoder- formers. Across various computer vision scenarios, in decoder architectures). the last years, complexity has appeared to escalate ex- ponentially, even for marginal enhancements, affecting 2.2. AI and sustainable agriculture both the number of parameters and of Floating Point The early detection of plant stress stands as a pivotal prac- Operations (FLOPs). Among various machine learning tice in agriculture. Plant stress can be categorized into methodologies, ensembling emerges as a technique that biotic stress, caused by living organisms such as viruses, fuses multiple models, termed weak learners, to produce bacteria, fungi, nematodes, insects, arachnids, and weeds, a model with superior performance than any individ- and abiotic stress, resulting from environmental factors ual weak learner. Typically, this amalgamation involves like drought, heat, cold, strong winds, flooding, and nutri- aggregating the weak learners’ outputs, often through ent deficiencies. Both forms of stress significantly impact voting or averaging for classification or regression tasks, crop yield and quality, leading to substantial economic respectively. Factors such as ensemble size (i.e., the num- losses when stress thresholds are surpassed. Despite ad- ber of weak learners) and ensemble techniques (e.g., bag- vancements in genetics providing cultivars increasingly ging, boosting, stacking) play crucial roles in achieving resistant to various stresses, yield and quality losses re- satisfactory results. However, ensembling necessitates main critical globally, particularly with the concurrent training several models, rendering the overall validation occurrence of abiotic and biotic stresses due to climate process more resource-intensive, with model complexity change. Presently, most plant inspections rely on man- growing at least linearly relative to the ensemble size. ual methods involving direct visual analysis, which may Additionally, ensembling is time-consuming, thus posing not always facilitate accurately identifying diseases and a significant barrier to its widespread adoption, particu- stress types, especially in underdeveloped areas of the larly in computer vision applications. world. Farmers typically rely on naked-eye inspections, Contrary to these challenges, in [1] we introduced a necessitating constant observation, high levels of skill, technique aimed at reversing the prevailing trend in im- and experience. While some farmers may utilize guide- age classification, characterized by marginal performance lines containing basic concepts and visual aids (such as gains accompanied by substantial increases in complexity. pictures or notes) to distinguish between biotic and abi- Specifically, our approach involves a reimagined form otic injuries and determine appropriate solutions, others of ensembling designed to surpass the state-of-the-art may require technical assistance for formal and compre- while maintaining constrained complexity in terms of hensive diagnoses. However, these methodologies are both parameter count and FLOPs. We demonstrated the often time-consuming and expensive, posing challenges feasibility of this approach by implementing bagging on for large farms or those with limited resources. Fur- two distinct subsets of data, employing two EfficientNet- thermore, identifying weed types, whether broadleaf or grassy, during their early stages (from germination to the High Atlas watershed [7]. Furthermore, investigations development of the first four/six leaves) presents signifi- have been conducted to infer how excess irrigation water cant difficulties, precisely when intervention would be from rice cultivation can mitigate saltwater intrusion and most effective. Consequently, there is a growing need for potentially contribute to recharging the north of the Nile automated infection recognition methods to enhance ac- Delta Aquifer [8]. The findings indicate that strategically curacy and efficiency. The increasing public concern for placing rice cultivation and utilizing natural recharge environmental conservation and the imperative for more methods can significantly reduce aquifer vulnerability. efficient agriculture to accommodate population growth amidst shrinking arable land underscores the importance 2.4. Computer vision for medical waste of developing cost-effective and sustainable solutions to support farmers. In this context, machine learning tech- Medical waste (MW) poses a significant challenge as niques can potentially revolutionize the timely suppres- healthcare facilities generate considerable quantities of sion of harmful plant organisms, thereby maintaining hazardous waste daily. Proper handling and treatment chemical treatment and other interventions at econom- are essential, necessitating specialized management prac- ically and ecologically justified levels. In the research tices. Typically, medical waste is deposited into desig- activities at the lab, the methods detailed in Section 2.1 nated containers at the point of origin, which are subse- have been applied to the agricultural domain. Initially, quently sealed and require prompt disposal. Disposal state-of-the-art results were attained on the PlantVillage methods, primarily through incineration or waste-to- dataset [2]. Subsequently, these methods were leveraged energy processes, take place in specialized treatment fa- to form the intelligent core of the mobile application Gra- cilities often situated at a considerable distance from the noscan, developed within the Agrosat project and made point of waste generation. Moreover, due to the potential available by Barilla on popular iOS and Android plat- biological hazards, manual handling of the waste post- forms [3]. Additionally, outstanding outcomes, coupled disposal is prohibited, with human intervention limited with a new dataset for weed classification, were docu- to critical situations and requiring specialized personal mented in [4]. Furthermore, an application targeting protective equipment. Recent years have seen a rise in Olive tree diseases, a vital sector in Italy’s agricultural medical waste production attributed to factors such as production, was presented in [5]. the expansion of the healthcare sector and increased uti- lization of disposable medical equipment. The emergence of COVID-19 further exacerbated this trend, resulting in 2.3. Hydrological modelling for resilience surges in the production of potentially hazardous and and equitable access to water infectious waste. Consequently, there is a pressing need Many basins in the Mediterranean and the MENA region for scalable and sustainable methods to manage medical (Middle-East North Africa) are currently facing recurring waste. Notably, medical devices are often composed of droughts and periods of water scarcity, often exacerbated high-quality virgin materials, predominantly polymers, by intermittent extreme events. Consequently, urgent alongside significant proportions of glass, textiles, and action is required to implement effective measures for metals. Therefore, sorting medical waste for recycling the sustainable management of water resources, with presents an opportunity for more sustainable waste man- a particular emphasis on groundwater. In this context, agement practices. However, primary sorting is essential Artificial Groundwater Recharge (AGR) has emerged as a as manual intervention at later stages is impractical due viable solution for addressing water scarcity challenges. to the associated hazards. Secondary sorting may only By capturing and storing surplus water during periods occur after the infectious and hazardous nature of the of intense precipitation or increased surface water avail- medical waste has been neutralized, typically through ability, artificial recharge can replenish depleted aquifers sterilization. Manual primary sorting of medical waste and serve as a dependable water source during drought is laborious and time-intensive, potentially overburden- periods. In collaboration with Ibn Tofail University (Ken- ing healthcare facility operators and increasing the risk itra, Morocco), considerable efforts have been directed of human error. Thus, there is a need for systems to towards enhancing the accuracy of hydrological models assist specialized staff during sorting, streamlining the and reducing uncertainty. This has involved incorporat- process and minimizing errors. To address this need, in ing various remote sensing-based Actual Evapotranspi- the framework of the project Medical Waste Treating ration (AET) products and assessing their effectiveness 4.0, in cooperation with industries and recycling experts, in improving the simulation of hydrological responses, we proposed research in the development of an artifi- both in single and multi-variable scenarios [6]. Simi- cial intelligence (AI) model leveraging deep learning and larly, the Soil and Water Assessment Tool (SWAT) model computer vision techniques to classify various types of and remotely sensed products have been incorporated to items comprising standard medical waste. Building upon characterize the dynamics of streamflow and snow in the previous work as reported in Section 2.1, we proposed a Figure 2: Acquisition system and sample images acquired in Medical Waste Treating 4.0 convolutional neural network based on the EfficientNet family. To train the network, a specialized dataset mim- icking a waste collection table equipped with a stereo Figure 3: Sample sea surface image segmented through multi- camera has been curated (see Figure 2). While the dataset thresholding is still expanding, initial results indicate promising per- formance [9]. Unlike existing studies on medical waste, the dataset is made publicly available to foster further research [10]. 2.6. Topological data analysis for biodiversity 2.5. Smart cameras for urban mobility Recent advancements in remote sensing have proven to In contemporary cities and urban environments, the sus- be highly effective in the realm of marine observation. tainability of mobility is posing growing concerns due This technology furnishes experts with an extensive array to several factors. These include the rise in the number of data gleaned from satellite sensors, necessitating the of cars on the roads, budget constraints leading to a re- development of automatic or semi-automatic methods for duction in free parking spaces, and economic challenges their analysis. In this context, one of the focuses of the SI during times of crisis, which diminish the efficiency of Lab lies in the categorization of upwelling regimes within public transportation systems. However, the increased the Iberia/Canary Current System (ICCS), an area that availability and power of computing facilities and de- remains relatively understudied within the domain of vices offers an opportunity to address two of the most upwelling ecosystems. Of particular interest among the pressing issues: congestion and traffic resulting from various underlying processes are mesoscale events such vehicles searching for parking spaces. In our research, as upwellings, countercurrents, and filaments. These we have explored approaches centred around wireless events play a crucial role in transporting nutrient-rich smart cameras for monitoring open-air public parking waters from deeper regions to the surface, thereby sig- areas and urban roads. More specifically, a smart camera nificantly influencing the biological parameters of the is a vision sensor equipped with artificial vision-logic for habitat and augmenting local biodiversity. Essentially, the on-board interpretation of acquired images and video there exists a correlation between the biogeochemical streams, along with a network interface to communicate and physical processes within a marine biological system. the processing outcome. A network of smart cameras is Sea Surface Temperature (SST), which measures the a sensor network whose nodes consist of a set of smart temperature of the water at the ocean’s surface, is a vi- cameras that cooperate for scene analysis, pervasively tal metric in this context. This temperature is assessed covering an area of interest. The primary strengths of the using satellite instruments that capture the energy emit- proposed solution lie in the autonomy and scalability of ted from the ocean surface across different wavelengths the proposed architecture. Indeed, autonomy is achieved on a global scale. Subsequently, these data are corrob- through the intelligent capabilities of smart cameras that orated with temperature readings obtained from ships can deploy powerful AI methods on board, ensuring inde- and buoys. The acquisition, processing, and comprehen- pendence from external systems. Scalability is facilitated sion of sea surface data (see Figure 3) hold significant by low-cost single nodes that can be integrated into a importance as they provide insights into the underlying broader sensor network without requiring expensive in- reasons behind regional temperature variations and their stallation requirements. Starting with very low resource repercussions on the marine ecosystem. Environmental cameras leveraging classical image processing methods changes can have profound effects on the lives of species [11], approaches have moved to large-scale Field Opera- inhabiting these regions, influencing factors such as food tional Tests (FOT) [12], also integrating and comparing accessibility, migration patterns, and mating opportuni- multimodal technologies [13] for parking lot monitoring; ties. To tackle the challenging task of categorizing marine a recent survey and way forwards are discussed in [14]. mesoscale patterns using remote sensing data, a pipeline of topological machine learning (TML) techniques has we addressed this gap by introducing an app founded on been used [15]. Such methods can be traced back to Al- a crowdsensing approach to enhance safety and aware- gebraic Topology (AT), a branch of mathematics dealing ness at sea. The app seamlessly integrates into broader with shapes. In a nutshell, AT assigns an algebraic ob- systems and frameworks for environmental monitoring, ject to a topological space. Then, it can compute several aligning with our envisioned future endeavors that are invariants and descriptors (the Euler characteristic, the currently explored in the EU Funded Nautilos project. Betti numbers, and the homology groups). Such invari- Additional research efforts are being spent in identifying ants and descriptors are used in computational topology AI methods to derive information from satellite images to to compare shapes and to define distances between them. observe and categorize marine traffic, possibly leading to One of the most used tools from computational topology understanding patterns as well as in identifying malicious is persistent homology, which is a method for comput- behaviors, such as Illegal, Unreported, and Unregulated ing topological features of a space across different scales. (IUU) fishing or prohibited discharges [20]. In this con- More persistent features are detected over a wide range text, Synthetic Aperture Radar (SAR) images allow for of spatial resolutions (have a long “lifespan”) and are vessel detection under most weather conditions. Image deemed more likely to represent important, or true fea- processing and computer vision methods have been used tures of the underlying space, rather than artefacts of in the framework of the ESA-funded OSIRIS and OSIRIS- sampling, or noise. Applications of persistent homol- FO projects to (i) detect the presence of vessel targets in ogy span from computer vision and shape analysis to the input imagery, (ii) estimate the vessel types based on biomedical imaging and complex network analysis. In their geometric and scatterometric features, (iii) estimate this perspective, one of the most promising trends is the the vessel kinematics, and (iv) classify the navigation merging of persistent homology with machine and deep behavior of the vessel and predict its route [21]. Optical learning. In our work, TML is used to tackle the task images, although they can’t be acquired on cloudy days of categorizing four distinct mesoscale patterns using and at night, may convey fine-grained information suit- remote sensing data—specifically patterns that can be able for the analysis and classification of small vessels, found in SST maps from the southwestern region of the potentially characterizing both industrial and small-scale Iberian Peninsula within the ICCS. Our initial investiga- fisheries, which is currently under consideration within tion attains a classification accuracy of 56% across the the PNRR NBFC Project. four labels [16]. These findings are promising, particu- larly given the presence of noise in the data and instances of low-quality or strong missing data (also due to weather 3. Conclusions conditions and cloudy sky). In this short paper, we provide an overview of the re- search conducted at SI Lab, focusing on themes related 2.7. AI for the marine environment: from to sustainability. The breadth of applications showcased citizen science to maritime traffic highlights the considerable value of AI as a tool to sen- monitoring sibly address the challenges of the future and facilitate ecological transition. The Sustainable Development Goals (SDGs) outlined by the United Nations encompass the marine and maritime domain, emphasizing the conservation and sustainable Acknowledgments utilization of oceans, seas, and their resources. Concur- rently, there is a pressing need for enhanced navigation This work has been partially supported by the CNR FOE safety, particularly in coastal regions. Presently, opera- Project DIT.AD022.207 “La Scienza per le TRansizioni In- tional services leverage advanced technologies, includ- dustriale, Verde, Energetica - STRIVE” and by the project ing remote sensing and in situ monitoring networks, to SAC.AD002.014 “Accordo bilaterale Marocco-CNRST”. aid navigation and environmental preservation efforts. This work is part of a project that has received fund- However, the potential benefits of crowdsensing remain ing from the European Union’s Horizon 2020 research largely untapped. A citizen science approach to monitor- and innovation programme under grant agreement No. ing oil spills was proposed in [17] within the framework 101000825 – NAUTILOS Project. of a more comprehensive Maritime Information System Funder: ProFunder: Project funded under the National (MIS), featuring proactive decision support services [18]. Recovery and Resilience Plan (NRRP), Mission 4 Com- However, the potential of using Volunteered Geographic ponent 2 Investment 1.4 - Call for tender No. 3138 of Information (VGI) and, more generally, crowdsensing in- 16 December 2021, rectified by Decree n.3175 of 18 De- formation has not been fully exploited to address broader cember 2021 of Italian Ministry of University and Re- safety and security-related events. With this aim, in [19], search funded by the European Union – NextGenera- tionEU. Award Number: Project code CN_00000033, Con- cession Decree No. 1034 of 17 June 2022 adopted by [10] A. Bruno, M. Martinelli, D. Moroni, Medical waste the Italian Ministry of University and Research, CUP 4.0 dataset, 2022. doi:10.5281/zenodo.7643417 . D33C22000960007, Project title “National Biodiversity [11] M. Magrini, D. Moroni, G. Palazzese, G. Pieri, Future Center - NBFC” - NBFC Project. G. Leone, O. Salvetti, Computer vision on embed- ded sensors for traffic flow monitoring, in: Intel- References ligent Transportation Systems (ITSC), 2015 IEEE 18th International Conference on, IEEE, 2015, pp. [1] A. Bruno, D. Moroni, M. Martinelli, Efficient adap- 161–166. tive ensembling for image classification, Expert [12] G. R. Leone, D. Moroni, G. Pieri, M. Petracca, O. Sal- Systems (2023). vetti, A. Azzarà, F. Marino, An intelligent coop- [2] A. Bruno, D. Moroni, R. Dainelli, L. Rocchi, erative visual sensor network for urban mobility, S. Morelli, E. Ferrari, P. Toscano, M. Martinelli, Im- Sensors 17 (2017) 2588. proving plant disease classification by adaptive min- [13] M. Alam, D. Moroni, G. Pieri, M. Tampucci, imal ensembling, Frontiers in Artificial Intelligence M. Gomes, J. Fonseca, J. Ferreira, Real-time smart 5 (2022) 868926. parking systems integration in distributed its for [3] R. Dainelli, A. Bruno, M. Martinelli, D. Moroni, smart cities, Journal of Advanced Transportation L. Rocchi, S. Morelli, E. Ferrari, M. Silvestri, 2018 (2018). S. Agostinelli, P. La Cava, et al., Granoscan: an [14] C. Biyik, Z. Allam, G. Pieri, D. Moroni, M. O’fraifer, ai-powered mobile app for in-field identification of E. O’Connell, S. Olariu, M. Khalid, Smart parking biotic threats of wheat, Frontiers in Plant Science systems: Reviewing the literature, architecture and 15 (2024) 1298791. ways forward, Smart Cities 4 (2021) 623–642. [4] R. Dainelli, M. Martinelli, A. Bruno, D. Moroni, [15] F. Conti, D. Moroni, M. A. Pascali, A topological S. Morelli, M. Silvestri, E. Ferrari, L. Rocchi, machine learning pipeline for classification, Math- P. Toscano, Recognition of weeds in cereals using ematics 10 (2022) 3086. ai architecture, in: Precision agriculture’23, Wa- [16] F. Conti, O. Papini, D. Moroni, G. Pieri, M. Reggian- geningen Academic Publishers, 2023, pp. 401–407. nini, M. A. Pascali, Analysis of sea surface tem- [5] A. Bruno, D. Moroni, M. Martinelli, Efficient deep perature maps via topological machine learning, learning approach for olive disease classification, in: 2023 IX International Conference on Informa- in: 2023 18th Conference on Computer Science tion Technology and Nanotechnology (ITNT), IEEE, and Intelligence Systems (FedCSIS), IEEE, 2023, pp. 2023, pp. 1–4. 889–894. [17] M. Martinelli, D. Moroni, Volunteered geographic [6] S. Taia, A. Scozzari, L. Erraioui, M. Kili, A. Mridekh, information for enhanced marine environment S. Haida, J. Chao, B. El Mansouri, Comparing the monitoring, Applied Sciences 8 (2018) 1743. ability of different remotely sensed evapotranspi- [18] D. Moroni, G. Pieri, M. Tampucci, Environmen- ration products in enhancing hydrological model tal decision support systems for monitoring small performance and reducing prediction uncertainty, scale oil spills: Existing solutions, best practices Ecological Informatics 78 (2023) 102352. and current challenges, Journal of Marine Science [7] S. Taia, L. Erraioui, Y. Arjdal, J. Chao, B. El Man- and Engineering 7 (2019) 19. souri, A. Scozzari, The application of SWAT model [19] D. Moroni, G. Pieri, M. Reggiannini, M. Tampucci, and remotely sensed products to characterize the A mobile crowdsensing app for improved maritime dynamic of streamflow and snow in a mountain- security and awareness, in: 2022 IEEE International ous watershed in the High Atlas, Sensors 23 (2023) Conference on Pervasive Computing and Commu- 1246. nications Workshops and other Affiliated Events [8] I. Abd-Elaty, G. A. Sallam, L. Pugliese, A. M. Negm, (PerCom Workshops), IEEE, 2022, pp. 103–105. S. Straface, A. Scozzari, A. Ahmed, Managing [20] M. Reggiannini, M. Righi, M. Tampucci, A. Lo Duca, coastal aquifer salinity under sea level rise using C. Bacciu, L. Bedini, A. D’Errico, C. Di Paola, rice cultivation recharge for sustainable land cover, A. Marchetti, M. Martinelli, et al., Remote sens- Journal of Hydrology: Regional Studies 48 (2023) ing for maritime prompt monitoring, Journal of 101466. Marine Science and Engineering 7 (2019) 202. [9] A. Bruno, C. Caudai, G. R. Leone, M. Martinelli, [21] M. Reggiannini, E. Salerno, C. Bacciu, A. D’Errico, D. Moroni, F. Crotti, Medical waste sorting: a com- A. Lo Duca, A. Marchetti, M. Martinelli, C. Mercurio, puter vision approach for assisted primary sort- A. Mistretta, M. Righi, et al., Remote sensing for ing, in: 2023 IEEE International Conference on maritime traffic understanding, Remote Sensing 16 Acoustics, Speech, and Signal Processing Work- (2024) 557. shops (ICASSPW), IEEE, 2023, pp. 1–5.