Bayesian space-time data fusion for real-time forecasting and map uncertainty

Environmental computer models are deterministic models devoted to predict several environmental phenomena such as air pollution or meteorological events. Numerical model output is given in terms of averages over grid cells, usually at high spatial and temporal resolution. However, these outputs are often biased with unknown calibration and not equipped with any information about the associated uncertainty. Conversely, data collected at monitoring stations is more accurate since they essentially provide the true levels. Due the leading role played by numerical models, it now important to compare model output with observations. Statistical methods developed to combine numerical model output and station data are usually referred to as data fusion. In this work, we first combine ozone monitoring data with ozone predictions from the Eta-CMAQ air quality model in order to forecast real-time current 8-hour average ozone level defined as the average of the previous four hours, current hour, and predictions for the next three hours. We propose a Bayesian downscaler model based on first differences with a flexible coefficient structure and an efficient computational strategy to fit model parameters. Model validation for the eastern United States shows consequential improvement of our fully inferential approach compared with the current real-time forecasting system. Furthermore, we consider the introduction of temperature data from a weather forecast model into the downscaler, showing improved real-time ozone predictions. Finally, we introduce a hierarchical model to obtain spatially varying uncertainty associated with numerical model output. We show how we can learn about such uncertainty through suitable stochastic data fusion modeling using some external validation data. We illustrate our Bayesian model by providing the uncertainty map associated with a temperature output over the northeastern United States.

Progetto di reti Sensori Wireless e tecniche di Fusione Sensoriale

Ambient Intelligence (AmI) envisions a world where smart, electronic environments are aware and responsive to their context. People moving into these settings engage many computational devices and systems simultaneously even if they are not aware of their presence. AmI stems from the convergence of three key technologies: ubiquitous computing, ubiquitous communication and natural interfaces. The dependence on a large amount of fixed and mobile sensors embedded into the environment makes of Wireless Sensor Networks one of the most relevant enabling technologies for AmI. WSN are complex systems made up of a number of sensor nodes, simple devices that typically embed a low power computational unit (microcontrollers, FPGAs etc.), a wireless communication unit, one or more sensors and a some form of energy supply (either batteries or energy scavenger modules). Low-cost, low-computational power, low energy consumption and small size are characteristics that must be taken into consideration when designing and dealing with WSNs. In order to handle the large amount of data generated by a WSN several multi sensor data fusion techniques have been developed. The aim of multisensor data fusion is to combine data to achieve better accuracy and inferences than could be achieved by the use of a single sensor alone. In this dissertation we present our results in building several AmI applications suitable for a WSN implementation. The work can be divided into two main areas: Multimodal Surveillance and Activity Recognition. Novel techniques to handle data from a network of low-cost, low-power Pyroelectric InfraRed (PIR) sensors are presented. Such techniques allow the detection of the number of people moving in the environment, their direction of movement and their position. We discuss how a mesh of PIR sensors can be integrated with a video surveillance system to increase its performance in people tracking. Furthermore we embed a PIR sensor within the design of a Wireless Video Sensor Node (WVSN) to extend its lifetime. Activity recognition is a fundamental block in natural interfaces. A challenging objective is to design an activity recognition system that is able to exploit a redundant but unreliable WSN. We present our activity in building a novel activity recognition architecture for such a dynamic system. The architecture has a hierarchical structure where simple nodes performs gesture classification and a high level meta classifiers fuses a changing number of classifier outputs. We demonstrate the benefit of such architecture in terms of increased recognition performance, and fault and noise robustness. Furthermore we show how we can extend network lifetime by performing a performance-power trade-off. Smart objects can enhance user experience within smart environments. We present our work in extending the capabilities of the Smart Micrel Cube (SMCube), a smart object used as tangible interface within a tangible computing framework, through the development of a gesture recognition algorithm suitable for this limited computational power device. Finally the development of activity recognition techniques can greatly benefit from the availability of shared dataset. We report our experience in building a dataset for activity recognition. Such dataset is freely available to the scientific community for research purposes and can be used as a testbench for developing, testing and comparing different activity recognition techniques.

Reverse Engineering tools: development and experimentation of innovative methods for physical and geometrical data integration and post-processing

In recent years, the use of Reverse Engineering systems has got a considerable interest for a wide number of applications. Therefore, many research activities are focused on accuracy and precision of the acquired data and post processing phase improvements. In this context, this PhD Thesis deals with the definition of two novel methods for data post processing and data fusion between physical and geometrical information. In particular a technique has been defined for error definition in 3D points’ coordinates acquired by an optical triangulation laser scanner, with the aim to identify adequate correction arrays to apply under different acquisition parameters and operative conditions. Systematic error in data acquired is thus compensated, in order to increase accuracy value. Moreover, the definition of a 3D thermogram is examined. Object geometrical information and its thermal properties, coming from a thermographic inspection, are combined in order to have a temperature value for each recognizable point. Data acquired by an optical triangulation laser scanner are also used to normalize temperature values and make thermal data independent from thermal-camera point of view.

Governing algorithms in the big data era for balancing new digital rights - designing GDPR compliant and trustworthy XAI systems

This thesis investigates the legal, ethical, technical, and psychological issues of general data processing and artificial intelligence practices and the explainability of AI systems. It consists of two main parts. In the initial section, we provide a comprehensive overview of the big data processing ecosystem and the main challenges we face today. We then evaluate the GDPR’s data privacy framework in the European Union. The Trustworthy AI Framework proposed by the EU’s High-Level Expert Group on AI (AI HLEG) is examined in detail. The ethical principles for the foundation and realization of Trustworthy AI are analyzed along with the assessment list prepared by the AI HLEG. Then, we list the main big data challenges the European researchers and institutions identified and provide a literature review on the technical and organizational measures to address these challenges. A quantitative analysis is conducted on the identified big data challenges and the measures to address them, which leads to practical recommendations for better data processing and AI practices in the EU. In the subsequent part, we concentrate on the explainability of AI systems. We clarify the terminology and list the goals aimed at the explainability of AI systems. We identify the reasons for the explainability-accuracy trade-off and how we can address it. We conduct a comparative cognitive analysis between human reasoning and machine-generated explanations with the aim of understanding how explainable AI can contribute to human reasoning. We then focus on the technical and legal responses to remedy the explainability problem. In this part, GDPR’s right to explanation framework and safeguards are analyzed in-depth with their contribution to the realization of Trustworthy AI. Then, we analyze the explanation techniques applicable at different stages of machine learning and propose several recommendations in chronological order to develop GDPR-compliant and Trustworthy XAI systems.

Surveillance risks in IoT applied to smart cities

Nowadays, cities deal with unprecedented pollution and overpopulation problems, and Internet of Things (IoT) technologies are supporting them in facing these issues and becoming increasingly smart. IoT sensors embedded in public infrastructure can provide granular data on the urban environment, and help public authorities to make their cities more sustainable and efficient. Nonetheless, this pervasive data collection also raises high surveillance risks, jeopardizing privacy and data protection rights. Against this backdrop, this thesis addresses how IoT surveillance technologies can be implemented in a legally compliant and ethically acceptable fashion in smart cities. An interdisciplinary approach is embraced to investigate this question, combining doctrinal legal research (on privacy, data protection, criminal procedure) with insights from philosophy, governance, and urban studies. The fundamental normative argument of this work is that surveillance constitutes a necessary feature of modern information societies. Nonetheless, as the complexity of surveillance phenomena increases, there emerges a need to develop more fine-attuned proportionality assessments to ensure a legitimate implementation of monitoring technologies. This research tackles this gap from different perspectives, analyzing the EU data protection legislation and the United States and European case law on privacy expectations and surveillance. Specifically, a coherent multi-factor test assessing privacy expectations in public IoT environments and a surveillance taxonomy are proposed to inform proportionality assessments of surveillance initiatives in smart cities. These insights are also applied to four use cases: facial recognition technologies, drones, environmental policing, and smart nudging. Lastly, the investigation examines competing data governance models in the digital domain and the smart city, reviewing the EU upcoming data governance framework. It is argued that, despite the stated policy goals, the balance of interests may often favor corporate strategies in data sharing, to the detriment of common good uses of data in the urban context.

La nuova eGovernance sanitaria europea: verso una piena integrazione della digitalizzazione nei sistemi sanitari degli Stati membri

L’elaborato approfondisce il diritto alla salute nell’ordinamento dell’Unione europea, con la consapevolezza che il settore della sanità, nella complessità di una tensione perdurante tra la sua matrice sociale e l’applicazione di logiche europee di mercato, rappresenta un ambito da sempre sottratto all’intervento diretto e vincolante delle istituzioni. Contemporaneamente, prende spunto dall’osservazione della transizione digitale dei sistemi sanitari nazionali per proporre una rilettura dei tradizionali equilibri istituzionali tra ordinamenti e constatare il grado di influenza dell’Unione oltre la dimensione transfrontaliera. Infatti, per le attuali esigenze di sostenibilità dei sistemi di tutela della salute e per il valore aggiunto riconosciuto alle azioni europee nel corso della gestione della pandemia da Covid-19, l’eHealth ha rappresentato l’occasione per una vigorosa intrusione delle istituzioni europee entro prerogative tipicamente statuali, fino all’emersione di una eGovernance sanitaria europea. Pertanto, la trattazione compie un percorso evolutivo che muove dalla Direttiva 2011/24 sull’assistenza transfrontaliera e l’assistenza sanitaria online, in combinato disposto con il complesso degli atti di soft law connessi, per verificarne l’esiguo impatto sui sistemi sanitari degli Stati membri e, alla luce dei recenti investimenti strategici ed interventi normativi rilevanti in tema di tecnologie applicate alla sanità, riconoscerne il sostanziale superamento. In particolare, il confronto tra l’insufficiente livello di digitalizzazione raggiunto finora nei sistemi sanitari degli Stati membri ed il tenore della Proposta di regolamento sullo European Health Data Space suggerisce l’evoluzione dell’impianto di governo dei dati sanitari stabilito nella Direttiva, a partire dalla previsione di una disciplina comune sulla cartella sanitaria. A questo proposito, l’interoperabilità tra tecnologie diviene un presupposto operativo indefettibile, che corrobora la natura ‘tecnologicamente condizionata’ del diritto alla salute e propone l’idea che la sanità digitale rappresenti un passo in avanti verso un’assistenza europea uniforme.

Towards a Reconstruction of Thermal Properties of Light Nuclei from Fusion - Evaporation reactions

This thesis work has been developed in the framework of a new experimental campaign, proposed by the NUCL-EX Collaboration (INFN III Group), in order to progress in the understanding of the statistical properties of light nuclei, at excitation energies above particle emission threshold, by measuring exclusive data from fusion-evaporation reactions. The determination of the nuclear level density in the A~20 region, the understanding of the statistical behavior of light nuclei with excitation energies ~3 A.MeV, and the measurement of observables linked to the presence of cluster structures of nuclear excited levels are the main physics goals of this work. On the theory side, the contribution to this project given by this work lies in the development of a dedicated Monte-Carlo Hauser-Feshbach code for the evaporation of the compound nucleus. The experimental part of this thesis has consisted in the participation to the measurement 12C+12C at 95 MeV beam energy, at Laboratori Nazionali di Legnaro - INFN, using the GARFIELD+Ring Counter(RCo) set-up, from the beam-time request to the data taking, data reduction, detector calibrations and data analysis. Different results of the data analysis are presented in this thesis, together with a theoretical study of the system, performed with the new statistical decay code. As a result of this work, constraints on the nuclear level density at high excitation energy for light systems ranging from C up to Mg are given. Moreover, pre-equilibrium effects, tentatively interpreted as alpha-clustering effects, are put in evidence, both in the entrance channel of the reaction and in the dissipative dynamics on the path towards thermalisation.

New approaches to open problems in gene expression microarray data

In the past decade, the advent of efficient genome sequencing tools and high-throughput experimental biotechnology has lead to enormous progress in the life science. Among the most important innovations is the microarray tecnology. It allows to quantify the expression for thousands of genes simultaneously by measurin the hybridization from a tissue of interest to probes on a small glass or plastic slide. The characteristics of these data include a fair amount of random noise, a predictor dimension in the thousand, and a sample noise in the dozens. One of the most exciting areas to which microarray technology has been applied is the challenge of deciphering complex disease such as cancer. In these studies, samples are taken from two or more groups of individuals with heterogeneous phenotypes, pathologies, or clinical outcomes. these samples are hybridized to microarrays in an effort to find a small number of genes which are strongly correlated with the group of individuals. Eventhough today methods to analyse the data are welle developed and close to reach a standard organization (through the effort of preposed International project like Microarray Gene Expression Data -MGED- Society [1]) it is not unfrequant to stumble in a clinician's question that do not have a compelling statistical method that could permit to answer it.The contribution of this dissertation in deciphering disease regards the development of new approaches aiming at handle open problems posed by clinicians in handle specific experimental designs. In Chapter 1 starting from a biological necessary introduction, we revise the microarray tecnologies and all the important steps that involve an experiment from the production of the array, to the quality controls ending with preprocessing steps that will be used into the data analysis in the rest of the dissertation. While in Chapter 2 a critical review of standard analysis methods are provided stressing most of problems that In Chapter 3 is introduced a method to adress the issue of unbalanced design of miacroarray experiments. In microarray experiments, experimental design is a crucial starting-point for obtaining reasonable results. In a two-class problem, an equal or similar number of samples it should be collected between the two classes. However in some cases, e.g. rare pathologies, the approach to be taken is less evident. We propose to address this issue by applying a modified version of SAM [2]. MultiSAM consists in a reiterated application of a SAM analysis, comparing the less populated class (LPC) with 1,000 random samplings of the same size from the more populated class (MPC) A list of the differentially expressed genes is generated for each SAM application. After 1,000 reiterations, each single probe given a "score" ranging from 0 to 1,000 based on its recurrence in the 1,000 lists as differentially expressed. The performance of MultiSAM was compared to the performance of SAM and LIMMA [3] over two simulated data sets via beta and exponential distribution. The results of all three algorithms over low- noise data sets seems acceptable However, on a real unbalanced two-channel data set reagardin Chronic Lymphocitic Leukemia, LIMMA finds no significant probe, SAM finds 23 significantly changed probes but cannot separate the two classes, while MultiSAM finds 122 probes with score >300 and separates the data into two clusters by hierarchical clustering. We also report extra-assay validation in terms of differentially expressed genes Although standard algorithms perform well over low-noise simulated data sets, multi-SAM seems to be the only one able to reveal subtle differences in gene expression profiles on real unbalanced data. In Chapter 4 a method to adress similarities evaluation in a three-class prblem by means of Relevance Vector Machine [4] is described. In fact, looking at microarray data in a prognostic and diagnostic clinical framework, not only differences could have a crucial role. In some cases similarities can give useful and, sometimes even more, important information. The goal, given three classes, could be to establish, with a certain level of confidence, if the third one is similar to the first or the second one. In this work we show that Relevance Vector Machine (RVM) [2] could be a possible solutions to the limitation of standard supervised classification. In fact, RVM offers many advantages compared, for example, with his well-known precursor (Support Vector Machine - SVM [3]). Among these advantages, the estimate of posterior probability of class membership represents a key feature to address the similarity issue. This is a highly important, but often overlooked, option of any practical pattern recognition system. We focused on Tumor-Grade-three-class problem, so we have 67 samples of grade I (G1), 54 samples of grade 3 (G3) and 100 samples of grade 2 (G2). The goal is to find a model able to separate G1 from G3, then evaluate the third class G2 as test-set to obtain the probability for samples of G2 to be member of class G1 or class G3. The analysis showed that breast cancer samples of grade II have a molecular profile more similar to breast cancer samples of grade I. Looking at the literature this result have been guessed, but no measure of significance was gived before.

Kernel Methods for Tree Structured Data

Machine learning comprises a series of techniques for automatic extraction of meaningful information from large collections of noisy data. In many real world applications, data is naturally represented in structured form. Since traditional methods in machine learning deal with vectorial information, they require an a priori form of preprocessing. Among all the learning techniques for dealing with structured data, kernel methods are recognized to have a strong theoretical background and to be effective approaches. They do not require an explicit vectorial representation of the data in terms of features, but rely on a measure of similarity between any pair of objects of a domain, the kernel function. Designing fast and good kernel functions is a challenging problem. In the case of tree structured data two issues become relevant: kernel for trees should not be sparse and should be fast to compute. The sparsity problem arises when, given a dataset and a kernel function, most structures of the dataset are completely dissimilar to one another. In those cases the classifier has too few information for making correct predictions on unseen data. In fact, it tends to produce a discriminating function behaving as the nearest neighbour rule. Sparsity is likely to arise for some standard tree kernel functions, such as the subtree and subset tree kernel, when they are applied to datasets with node labels belonging to a large domain. A second drawback of using tree kernels is the time complexity required both in learning and classification phases. Such a complexity can sometimes prevents the kernel application in scenarios involving large amount of data. This thesis proposes three contributions for resolving the above issues of kernel for trees. A first contribution aims at creating kernel functions which adapt to the statistical properties of the dataset, thus reducing its sparsity with respect to traditional tree kernel functions. Specifically, we propose to encode the input trees by an algorithm able to project the data onto a lower dimensional space with the property that similar structures are mapped similarly. By building kernel functions on the lower dimensional representation, we are able to perform inexact matchings between different inputs in the original space. A second contribution is the proposal of a novel kernel function based on the convolution kernel framework. Convolution kernel measures the similarity of two objects in terms of the similarities of their subparts. Most convolution kernels are based on counting the number of shared substructures, partially discarding information about their position in the original structure. The kernel function we propose is, instead, especially focused on this aspect. A third contribution is devoted at reducing the computational burden related to the calculation of a kernel function between a tree and a forest of trees, which is a typical operation in the classification phase and, for some algorithms, also in the learning phase. We propose a general methodology applicable to convolution kernels. Moreover, we show an instantiation of our technique when kernels such as the subtree and subset tree kernels are employed. In those cases, Direct Acyclic Graphs can be used to compactly represent shared substructures in different trees, thus reducing the computational burden and storage requirements.

Procedures of quality control and data analysis of multi-site ground-based observations for the absolute flux calibration of Gaia

The Gaia space mission is a major project for the European astronomical community. As challenging as it is, the processing and analysis of the huge data-flow incoming from Gaia is the subject of thorough study and preparatory work by the DPAC (Data Processing and Analysis Consortium), in charge of all aspects of the Gaia data reduction. This PhD Thesis was carried out in the framework of the DPAC, within the team based in Bologna. The task of the Bologna team is to define the calibration model and to build a grid of spectro-photometric standard stars (SPSS) suitable for the absolute flux calibration of the Gaia G-band photometry and the BP/RP spectrophotometry. Such a flux calibration can be performed by repeatedly observing each SPSS during the life-time of the Gaia mission and by comparing the observed Gaia spectra to the spectra obtained by our ground-based observations. Due to both the different observing sites involved and the huge amount of frames expected (≃100000), it is essential to maintain the maximum homogeneity in data quality, acquisition and treatment, and a particular care has to be used to test the capabilities of each telescope/instrument combination (through the “instrument familiarization plan”), to devise methods to keep under control, and eventually to correct for, the typical instrumental effects that can affect the high precision required for the Gaia SPSS grid (a few % with respect to Vega). I contributed to the ground-based survey of Gaia SPSS in many respects: with the observations, the instrument familiarization plan, the data reduction and analysis activities (both photometry and spectroscopy), and to the maintenance of the data archives. However, the field I was personally responsible for was photometry and in particular relative photometry for the production of short-term light curves. In this context I defined and tested a semi-automated pipeline which allows for the pre-reduction of imaging SPSS data and the production of aperture photometry catalogues ready to be used for further analysis. A series of semi-automated quality control criteria are included in the pipeline at various levels, from pre-reduction, to aperture photometry, to light curves production and analysis.

Spectroscopic studies on Cyclodextrin and Metal Organic Framework based potential nanovectors for delivery of Anticancer and Antiviral drugs

The aim of this work is to contribute to the development of new multifunctional nanocarriers for improved encapsulation and delivery of anticancer and antiviral drugs. The work focused on water soluble and biocompatible oligosaccharides, the cyclodextrins (CyDs), and a new family of nanostructured, biodegradable carrier materials made of porous metal-organic frameworks (nanoMOFs). The drugs of choice were the anticancer doxorubicin (DOX), azidothymidine (AZT) and its phosphate derivatives and artemisinin (ART). DOX possesses a pharmacological drawback due to its self-aggregation tendency in water. The non covalent binding of DOX to a series of CyD derivatives, such as g-CyD, an epichlorohydrin crosslinked b-CyD polymer (pb-CyD) and a citric acid crosslinked g-CyD polymer (pg-CyD) was studied by UV visible absorption, circular dichroism and fluorescence. Multivariate global analysis of multiwavelength data from spectroscopic titrations allowed identification and characterization of the stable complexes. pg-CyD proved to be the best carrier showing both high association constants and ability to monomerize DOX. AZT is an important antiretroviral drug. The active form is AZT-triphosphate (AZT-TP), formed in metabolic paths of low efficiency. Direct administration of AZT-TP is limited by its poor stability in biological media. So the development of suitable carriers is highly important. In this context we studied the binding of some phosphorilated derivatives to nanoMOFs by spectroscopic methods. The results obtained with iron(III)-trimesate nanoMOFs allowed to prove that the binding of these drugs mainly occurs by strong iono-covalent bonds to iron(III) centers. On the basis of these and other results obtained in partner laboratories, it was possible to propose this highly versatile and “green” carrier system for delivery of phosphorylated nucleoside analogues. The interaction of DOX with nanoMOFs was also studied. Finally the binding of the antimalarial drug, artemisinin (ART) with two cyclodextrin-based carriers,the pb-CyD and a light responsive bis(b-CyD) host, was also studied.

A Semantic-based Framework for Digital Survey of Architectural Heritage

The research aims at developing a framework for semantic-based digital survey of architectural heritage. Rooted in knowledge-based modeling which extracts mathematical constraints of geometry from architectural treatises, as-built information of architecture obtained from image-based modeling is integrated with the ideal model in BIM platform. The knowledge-based modeling transforms the geometry and parametric relation of architectural components from 2D printings to 3D digital models, and create large amount variations based on shape grammar in real time thanks to parametric modeling. It also provides prior knowledge for semantically segmenting unorganized survey data. The emergence of SfM (Structure from Motion) provides access to reconstruct large complex architectural scenes with high flexibility, low cost and full automation, but low reliability of metric accuracy. We solve this problem by combing photogrammetric approaches which consists of camera configuration, image enhancement, and bundle adjustment, etc. Experiments show the accuracy of image-based modeling following our workflow is comparable to that from range-based modeling. We also demonstrate positive results of our optimized approach in digital reconstruction of portico where low-texture-vault and dramatical transition of illumination bring huge difficulties in the workflow without optimization. Once the as-built model is obtained, it is integrated with the ideal model in BIM platform which allows multiple data enrichment. In spite of its promising prospect in AEC industry, BIM is developed with limited consideration of reverse-engineering from survey data. Besides representing the architectural heritage in parallel ways (ideal model and as-built model) and comparing their difference, we concern how to create as-built model in BIM software which is still an open area to be addressed. The research is supposed to be fundamental for research of architectural history, documentation and conservation of architectural heritage, and renovation of existing buildings.

Differential expression analysis for sequence count data via mixtures of negative binomials

The recent advent of Next-generation sequencing technologies has revolutionized the way of analyzing the genome. This innovation allows to get deeper information at a lower cost and in less time, and provides data that are discrete measurements. One of the most important applications with these data is the differential analysis, that is investigating if one gene exhibit a different expression level in correspondence of two (or more) biological conditions (such as disease states, treatments received and so on). As for the statistical analysis, the final aim will be statistical testing and for modeling these data the Negative Binomial distribution is considered the most adequate one especially because it allows for "over dispersion". However, the estimation of the dispersion parameter is a very delicate issue because few information are usually available for estimating it. Many strategies have been proposed, but they often result in procedures based on plug-in estimates, and in this thesis we show that this discrepancy between the estimation and the testing framework can lead to uncontrolled first-type errors. We propose a mixture model that allows each gene to share information with other genes that exhibit similar variability. Afterwards, three consistent statistical tests are developed for differential expression analysis. We show that the proposed method improves the sensitivity of detecting differentially expressed genes with respect to the common procedures, since it is the best one in reaching the nominal value for the first-type error, while keeping elevate power. The method is finally illustrated on prostate cancer RNA-seq data.

Dynamics of coastal aquifers: data-driven forecasting and risk analysis

This work is focused on the study of saltwater intrusion in coastal aquifers, and in particular on the realization of conceptual schemes to evaluate the risk associated with it. Saltwater intrusion depends on different natural and anthropic factors, both presenting a strong aleatory behaviour, that should be considered for an optimal management of the territory and water resources. Given the uncertainty of problem parameters, the risk associated with salinization needs to be cast in a probabilistic framework. On the basis of a widely adopted sharp interface formulation, key hydrogeological problem parameters are modeled as random variables, and global sensitivity analysis is used to determine their influence on the position of saltwater interface. The analyses presented in this work rely on an efficient model reduction technique, based on Polynomial Chaos Expansion, able to combine the best description of the model without great computational burden. When the assumptions of classical analytical models are not respected, and this occurs several times in the applications to real cases of study, as in the area analyzed in the present work, one can adopt data-driven techniques, based on the analysis of the data characterizing the system under study. It follows that a model can be defined on the basis of connections between the system state variables, with only a limited number of assumptions about the "physical" behaviour of the system.