Search

Assessing the intensity characteristics of specific soccer drills (matches, small-side game, and match-based exercises) could help practitioners to plan training sessions by providing the optimal stimulus for every player. In this paper, we propose a data analytics framework to assess the neuromuscular or metabolic characteristics of a soccer-specific exercise in relation with the expected match intensity. GPS data describing the physical tasks' external intensity during an entire season of twenty-eight semi-professional soccer players competing at the fourth Italian division were used in this study. A supervised machine-learning approach was tested in order to detect difference in playing positions in different sport-specific drills. Moreover, a non-supervised machine-learning model was used to profile the match neuromuscular and metabolic characteristics. Players' playing positions during matches and match-based exercises are characterised by specific metabolic and neuromuscular characteristics related to tactical demands, while in the small-side game these differences are not detected. Additionally, our framework permits to evaluate if the match performance request is mirrored during training drills. Practitioners could evaluate the type of stimulus performed by a player in a specific training drill in order to assess if they reflect the matches characteristics of their specific playing position. [ABSTRACT FROM AUTHOR]

Sociological literature on cultural practices seeking to understand the social differentiation of taste pays limited attention to what people avoid consuming, despite its potential as a strategic indicator of taste. Avoidance has special relevance for the understanding of eating and drinking practices which are often characterized by exclusion of items for health, hedonic, reputational, or spiritual reasons. Making use of rich data on twenty-three items commonly consumed by Italian adults, this paper investigates how avoidances—i.e. what people claim never to eat or drink—are clustered, socially patterned and have evolved over time. Methodologically, we propose the novel use and integration of two machine learning techniques—Self-Organizing Maps (SOM) and Boosted Regression Trees (BRT)— to identify nine highly homogeneous avoidance clusters and examine the power of social variables in predicting the probability of individuals' belonging to various clusters and to further characterize them. We conclude by discussing possible rationales behind avoidance. [ABSTRACT FROM AUTHOR]

This paper combines a theoretical-based model with a data-driven approach to develop an Early Warning System that detects students who are more likely to dropout. The model uses innovative multilevel statistical and machine learning methods. The paper demonstrates the validity of the approach by applying it to administrative data from a leading Italian university. [ABSTRACT FROM AUTHOR]

Increasing interest in natural gas-fired gensets is motivated by District Heating (DH) network applications, especially in urban areas. Even if they represent customary solutions, when used in DH, duty regimes are driven by network thermal energy demands resulting in discontinuous operation, which affects their remaining useful life. As such, the attention on effective condition-based maintenance has gained momentum. In this paper, a novel unsupervised anomaly detection framework is proposed for gensets in DH networks based on Supervisory Control And Data Acquisition (SCADA) data. The framework relies on multivariate Machine-Learning (ML) regression models trained with a Leave-One-Out Cross-Validation method. Model residuals generated during the testing phase are then post-processed with a sliding threshold approach based on a rolling average. This methodology is tested against nine major failures that occurred on the gas genset installed in the Aosta DH plant in Italy. The results show that the proposed framework successfully detects anomalies and anticipates SCADA alarms related to unscheduled downtime. [ABSTRACT FROM AUTHOR]

West Nile virus (WNV) is a mosquito-borne virus potentially causing serious illness in humans and other animals. Since 2004, several studies have highlighted the progressive spread of WNV Lineage 2 (L2) in Europe, with Italy being one of the countries with the highest number of cases of West Nile disease reported. In this paper, we give an overview of the epidemiological and genetic features characterising the spread and evolution of WNV L2 in Italy, leveraging data obtained from national surveillance activities between 2011 and 2021, including 46 newly assembled genomes that were analysed under both phylogeographic and phylodynamic frameworks. In addition, to better understand the seasonal patterns of the virus, we used a machine learning model predicting areas at high-risk of WNV spread. Our results show a progressive increase in WNV L2 in Italy, clarifying the dynamics of interregional circulation, with no significant introductions from other countries in recent years. Moreover, the predicting model identified the presence of suitable conditions for the 2022 earlier and wider spread of WNV in Italy, underlining the importance of using quantitative models for early warning detection of WNV outbreaks. Taken together, these findings can be used as a reference to develop new strategies to mitigate the impact of the pathogen on human and other animal health in endemic areas and new regions. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this paper is to describe a model for the design and development of a condition-based maintenance (CBM) strategy for the cutting group of a labeling machine. The CBM aims to ensure the quality of labels' cut and overall machine performances. Design/methodology/approach: In developing a complete CBM strategy, two main difficulties have to be overcome: (1) appropriately dealing with incomplete and low-quality production database and (2) selecting the most promising predictive model. The first issue has been addressed applying data cleansing operations and creating ad hoc methodology to enlarge the training data. The second issue has been handled developing and comparing an empirical model with a machine learning (ML)-based model; the comparison has been performed assessing capabilities thereof in predicting erroneous label cuts on data obtained from an operating plant located in Italy. Findings: Research results showed that both empirical and ML-based approaches exhibit good performances in detecting the operating conditions of the cutting machine. The advantage of adopting an ML-based model is that it can be used not only as a condition indicator (i.e. a model able to continuously provide the health status of an asset) but also in predictive maintenance policies (i.e. a CBM carried out following a forecast of the degradation of the item). Research limitations/implications: The study described in this manuscript has been developed on the practices of a labeling machine developed by an international company manufacturing bottling lines for beverage industry. The proposed approach might need some customization in case it is applied to other industries. Future researches can validate the applicability of such models on different rotary machines in other companies and similar industries. Originality/value: The main contribution of this paper lies in the empirical demonstration of the benefits of CBM and predictive maintenance in manufacturing, through the overcoming of a specific production issue. The large number of variables involved in thin label cutting lines (film thickness between 30 and 38 µm), the high throughput and the high costs due to production interruptions render the prediction of non-conforming labels an economically relevant, albeit challenging, goal. Moreover, despite the large scientific literature on CBM in rolling bearing and face cutting movements, papers dealing with rotary labeling machines are very unusual and unique. [ABSTRACT FROM AUTHOR]

The 3D modeling and representation of geological data have experienced significant growth within last years, due to the use of new technologies derived from advancements in land representation methods. These technologies enable interactive, intuitive and clear geological visualizations. This paper shows how, by using the open-source Python software (operable with a simple internet browser) for machine learning (linear and KNN interpolations), together with Geographic Information Systems (GIS), it is possible to achieve interactive 3D visualizations of geological features in sedimentary basins. This study is performed in the onshore-offshore Crotone area (southern Italy) where a large amount of stratigraphic datasets are available from core perforation and seismic profiles due to the presence of a natural gas extraction field. Thanks to a database of 63 drilling lithologic records and 43 check points obtained from 9 interpreted seismic sections, several 3D HTML models were constructed defining three stratigraphic units (Pre-Messinian, Messinian, and Post-Messinian). An overlap of the Post-Messinian top surface and an erosional truncation of the Messinian top surface toward the N were observed, together with a rising of the Pre-Messinian top surface in the northwestern area. This stratigraphic architecture may indicate differential subsidence and/or uplifting due to syn-sedimentary fault kinematics in the whole studied area. The 3D models with the stratigraphic unit boundary surfaces obtained with KNN interpolation (showing stepped and abrupt edges) allowed the interpretation in terms of structural architecture and syn-sedimentary fault kinematics. Three main sets of faults were deduced: N–S; NNW-SSE, and ENE-WSW. A minorly represented E-W set was added to the main sets. These faults generated a horsts-grabens structure, and in many cases a determinate set of faults caused a progressive lowering or rising of some areas with an "en echelon" arrangement. According to previous works, these deduced sets of faults (most of them strike-slip faults) have a good agreement with the general structural architecture and defined faults in the area. • 3D modeling and representation of geological borehole data. • Open-source Python libraries for machine learning linear interpolation and KNN algorithms, along with Geographic Information Systems (GIS). • 3D HTML model for the three-dimensional visualization of the boundary surfaces and volumes of the stratigraphic units obtained with KNN interpolation. • Interpretation of the stratigraphic architecture and syn-tectonic sedimentation of the Messinian deposits in the Crotone Basin. • Fault analysis and interpretation of structural architecture and syn-sedimentary fault actuation in the Crotone Basin. [ABSTRACT FROM AUTHOR]

Smart monitoring systems in orchards can automate agriculture monitoring processes and provide useful information about the presence of insects, such as the Brown Marmorated Stink Bug (BMSB), that threaten the production quantity and quality of fruit such as pears. Unlike other approaches in the literature, we propose a low-cost image monitoring system which exhibits a very low power consumption without compromising much of the accuracy that existing expensive systems incorporating significant computing and processing capability can achieve in such applications. The proposed system relies on a microcontroller unit and a camera which can take pictures of a double-sided sticky insect trap which, with the help of novel machine learning algorithms, can report on the presence of BMSB via a long-range communication link. The Internet of Things data capture and analysis system has recently been deployed in a real orchard in Italy which is subject to BMSB infestation and the first images have been analysed. This paper presents how the system works, the image processing, detection and classification algorithms, as well as a demonstration of the memory and energy consumption associated with the processing algorithms. The system achieves an accuracy of over 90% with multiple times less memory and energy consumption compared to other similar approaches in the literature. • Low-Power Edge-based insect monitoring system. • Insect detection and classification on resource-constrained microcontroller units (MCUs). • Extremely lightweight classification model for Halyomorpha Halys detection. • Joint improvement of hardware metrics without considerably compromising accuracy. [ABSTRACT FROM AUTHOR]

Food insecurity and food surplus are two pressing issues that have been exacerbated by the COVID-19 pandemic. This paper presents a novel approach to addressing these problems using blockchain technology. More specifically, data from the Italian Regusto platform are analysed to identify factors that determine the volume and economic value of surplus food redistribution. From a methodological statistical perspective, the performance of Stepwise Multiple Linear Regression and Random Forest are compared in a blockchain data analysis. The effective machine-learning-based analysis reveals that the Regusto platform gives people greater access to the surplus food redistributed by non-profit organizations and suppliers through both donations and sales. The study also highlights the potential effects of redistributing surplus food on the beneficiaries' diets and health and we find that redistributing surplus food can reduce household food insecurity among low-income families and communities measured by food poverty and COVID-19 indexes at different spatial locations. Overall, by offering a unique perspective on these issues through the lens of blockchain technology, our study can inspire further research on how this technology can ensure everyone has enough affordable, nutritious food to lead healthy lives. • Blockchain technology can address food insecurity and surplus by unlocking the value of surplus food and ensuring equitable distribution. • The Regusto platform facilitates food surplus management and increases access in areas at risk of food insecurity during COVID-19 crisis. • Surplus food traveled across Italy, not only between big cities and agricultural provinces but also over short distances. • Forward Stepwise MLR and Random Forest models used to identify factors influencing food transactions on Regusto platform. [ABSTRACT FROM AUTHOR]

Particular Matter (PM) data are the most used for the assessment of air quality, but it is also useful to monitor VOC and CO. The health impact of PM increases with decreasing aerodynamic dimensions, therefore most of the monitoring is aimed at PM10 (fraction of PM with aerodynamic dimensions smaller than 10 µm) and PM2.5 (fraction with aerodynamic dimensions lower than 2.5 µm). Generally, anthropogenic emissions contribute mainly to PM2.5 levels, whereas natural sources can largely affect PM10 concentrations. PM2.5/PM10 ratio can be used as a proxy of the origin (anthropogenic vs natural) of the PM, providing a useful indication about the main sources of PM that characterizes a specific geographical or urban setting. This paper presents the results of the analysis of continuous measurements of PM10 and PM2.5 concentrations at eight stations of the regional air quality monitoring network in Abruzzo (Central Italy), in the period 2017–2018. The application of models based on machine learning technique shows that PM2.5/PM10 ratio can be used to classify PM emissions and to know the nature of the emission source (natural and anthropogenic), under determinate conditions, and properly taking into account the meteorological parameters. [ABSTRACT FROM AUTHOR]

Estimates of the real death toll of the COVID-19 pandemic have proven to be problematic in many countries, Italy being no exception. Mortality estimates at the local level are even more uncertain as they require stringent conditions, such as granularity and accuracy of the data at hand, which are rarely met. The "official" approach adopted by public institutions to estimate the "excess mortality" during the pandemic draws on a comparison between observed all-cause mortality data for 2020 and averages of mortality figures in the past years for the same period. In this paper, we apply the recently developed machine learning control method to build a more realistic counterfactual scenario of mortality in the absence of COVID-19. We demonstrate that supervised machine learning techniques outperform the official method by substantially improving the prediction accuracy of the local mortality in "ordinary" years, especially in small- and medium-sized municipalities. We then apply the best-performing algorithms to derive estimates of local excess mortality for the period between February and September 2020. Such estimates allow us to provide insights about the demographic evolution of the first wave of the pandemic throughout the country. To help improve diagnostic and monitoring efforts, our dataset is freely available to the research community. [ABSTRACT FROM AUTHOR]

One of the most significant indicators for assessing the quality of university careers is the dropout rate between the first and second year. Both literature on the subjects and the results that emerged from numerous specific investigations into the dropouts of the university system, showed the crucial importance of this junction between the first and the second year. Reasons for dropping out can be quite varied, ranging from incorrect and/or insufficient prospective student orientation, the willingness or need to find a job as quickly as possible, to a lack of awareness of not being able to cope with a particular course of study rather than another. In this paper we focus specifically on the problem of dropouts in Italy, addressing it from a dual point of view. At an aggregate level, the analysis deals with dropout rates in Italy between the first and second year, in order to identify the main trends and dynamics at the national level. Subsequently, we analyze individual-level data from the University of Bari Aldo Moro, aiming to identify the most important contributing factors. This individual-level approach has emerged over recent years, and is generally known as 'Educational Data Mining', focused on the development of ad hoc methods that can be used to discover regularities and new information within databases from contexts related to education. Using supervised classification methods, we are able to identify retrospectively the profile of students who are most likely to dropout. [ABSTRACT FROM AUTHOR]

This paper investigates the possibility of the implementation of Genetic Programming (GP) algorithm on a publicly available COVID-19 data set, in order to obtain mathematical models which could be used for estimation of confirmed, deceased, and recovered cases and the estimation of epidemiology curve for specific countries, with a high number of cases, such as China, Italy, Spain, and USA and as well as on the global scale. The conducted investigation shows that the best mathematical models produced for estimating confirmed and deceased cases achieved R2 scores of 0.999, while the models developed for estimation of recovered cases achieved the R2 score of 0.998. The equations generated for confirmed, deceased, and recovered cases were combined in order to estimate the epidemiology curve of specific countries and on the global scale. The estimated epidemiology curve for each country obtained from these equations is almost identical to the real data contained within the data set [ABSTRACT FROM AUTHOR]

The knowledge of crop evapotranspiration is crucial for several hydrological processes, including those related to the management of agricultural water sources. In particular, the estimations of actual evapotranspiration fluxes within fields are essential to managing irrigation strategies to save water and preserve water resources. Among the indirect methods to estimate actual evapotranspiration, ET a , the eddy covariance (EC) method allows to acquire continuous measurement of latent heat flux (LE). However, the time series of EC measurements are sometimes characterized by a lack of data due to the sensors' malfunctions. At this aim, Machine Learning (ML) techniques could represent a powerful tool to fill possible gaps in the time series. In this paper, the ML technique was applied using the Gaussian Process Regression (GPR) algorithm to fill gaps in daily actual evapotranspiration. The technique was tested in six different plots, two in Italy, three in the United States of America, and one in Canada, with different crops and climatic conditions in order to consider the suitability of the ML model in various contexts. For each site, the climate variables were not the same, therefore, the performance of the method was investigated on the basis of the available information. Initially, a comparison of ground and reanalysis data, where both databases were available, and between two different satellite products, when both databases were available, have been conducted. Then, the GPR model was tested. The mean and the covariance functions were set by considering a database of climate variables, soil water status measurements, and remotely sensed vegetation indices. Then, five different combinations of variables were analyzed to verify the suitability of the ML approach when limited input data are available or when the weather variables are replaced with reanalysis data. Cross-validation was used to assess the performance of the procedure. The model performances were assessed based on the statistical indicators: Root Mean Square Error (RMSE), coefficient of determination (R2), Mean Absolute Error (MAE), regression coefficient (b), and Nash-Sutcliffe efficiency coefficient (NSE). The quite high Nash Sutcliffe Efficiency (NSE) coefficient, and the root mean square error (RMSE) low values confirm the suitability of the proposed algorithm. • GPR algorithm is suitable to fill gaps in daily ET a time series. • The best m(x) and k(x,x') functions required by the GPR algorithm were identified. • The best results were obtained when the dataset included climate data, SWC and VIs. • The use of ERA5-L data and VIs retrieved by Sentinel 2 or MODIS is a good alternative. • GPR algorithm was tested for different crops in continental and temperate zones. [ABSTRACT FROM AUTHOR]

The spiraling growth of the world's population and unregulated urbanization have resulted in many environmental problems, including poor quality of air, which is associated with a wide range of health issues. Machine learning approaches have been extensively employed to predict air quality, attracting the attention of the scientific community worldwide. Bibliometric studies provide a useful means by which to visualize and analyze published works, helping researchers to make novel scientific contributions by filling existing knowledge gaps in the research. To acquire an in-depth understanding of the topic, this paper presents a bibliometric analysis of all published articles on the use of machine learning networks to predict air quality found in the Web of Science (WoS) search engine from 1992 to 2021. S-curve analysis and social network analysis were used to identify the temporal distribution of articles, productivity by countries/continents, research institutions, and scientific metrics of journal productivity. This study indicated that maximum expansion of the literature witnessed during 2017–2021 (second phase) which represents an expansion or growth stage of machine learning and air quality prediction research. The number of published works increased significantly with 1432 articles accounting for 68.51% of all publications. As a result of the increased interest in machine learning-based prediction tools, the number of articles grew 2.17-fold compared to the 1992–2016 (first phase). In terms of international collaboration impact, Italy emerged as the most successful country (43.44), followed by Greece (31.22) and Spain (23.29). Author keywords analysis was employed to explore and evaluate the emerging research trends on the subject of air quality using machine learning models. Keywords that appear most frequently in this study are 'air pollution', 'air quality', 'machine learning', and 'forecasting'. Citation burst analysis, research productivity analysis, highly influential and highly cited works were also employed to examine various research themes and questions. In this study we also discussed how conventional methods were transformed into machine learning approaches. It is expected that this paper will provide technical guidelines, research priorities, and future opportunities for the precise prediction of air quality and emergency management of air pollution globally. • Interest in air quality prediction through machine learning model is expanding. • China and US were found productive countries in terms of countries collaboration. • Big data, Internet of Things, and Smart city are emerging topic for future research. • Significant difference between citations, funded and non-funded research. • Ensemble modeling is popular in air quality prediction research. [ABSTRACT FROM AUTHOR]

The spiraling growth of the world's population and unregulated urbanization have resulted in many environmental problems, including poor quality of air, which is associated with a wide range of health issues. Machine learning approaches have been extensively employed to predict air quality, attracting the attention of the scientific community worldwide. Bibliometric studies provide a useful means by which to visualize and analyze published works, helping researchers to make novel scientific contributions by filling existing knowledge gaps in the research. To acquire an in-depth understanding of the topic, this paper presents a bibliometric analysis of all published articles on the use of machine learning networks to predict air quality found in the Web of Science (WoS) search engine from 1992 to 2021. S-curve analysis and social network analysis were used to identify the temporal distribution of articles, productivity by countries/continents, research institutions, and scientific metrics of journal productivity. This study indicated that maximum expansion of the literature witnessed during 2017–2021 (second phase) which represents an expansion or growth stage of machine learning and air quality prediction research. The number of published works increased significantly with 1432 articles accounting for 68.51% of all publications. As a result of the increased interest in machine learning-based prediction tools, the number of articles grew 2.17-fold compared to the 1992–2016 (first phase). In terms of international collaboration impact, Italy emerged as the most successful country (43.44), followed by Greece (31.22) and Spain (23.29). Author keywords analysis was employed to explore and evaluate the emerging research trends on the subject of air quality using machine learning models. Keywords that appear most frequently in this study are 'air pollution', 'air quality', 'machine learning', and 'forecasting'. Citation burst analysis, research productivity analysis, highly influential and highly cited works were also employed to examine various research themes and questions. In this study we also discussed how conventional methods were transformed into machine learning approaches. It is expected that this paper will provide technical guidelines, research priorities, and future opportunities for the precise prediction of air quality and emergency management of air pollution globally. • Interest in air quality prediction through machine learning model is expanding. • China and US were found productive countries in terms of countries collaboration. • Big data, Internet of Things, and Smart city are emerging topic for future research. • Significant difference between citations, funded and non-funded research. • Ensemble modeling is popular in air quality prediction research. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) is fast becoming a general purpose technology with outstanding impacts in industries worldwide, thus supporting the Industry 4.0 revolution. In particular, the energy sector is one of those that has taken more advantages from the implementation of AI approaches, especially Machine Learning models, for several applications, including energy performance benchmarking of buildings. However, the black-box approach could lead to a lack of result interpretability thus preventing the effective application of AI in some real-world scenarios. For this reason, eXplainable Artificial Intelligence (XAI) tools can be effectively embedded within an AI-based Energy Analytics methodology in order to enhance the explainability of the model results. In this paper, we propose an explainable AI-based benchmarking framework for estimating the membership to specific energy performance classes of a large set of Energy Performance Certificates (EPCs) of flats. The classification is obtained by leveraging different black-box classifiers characterized by high accuracy, yet their inference mechanism is not human-readable. Therefore, a generalizable XAI methodology, based on the combination of a local explainer together with a clustering algorithm, is employed to explain the model results and causal effects between the predictors and target variable to better understand the model behaviour, and the motivations behind correct and wrong performed classifications. The paper provides a general methodological approach capable to exploit a limited number of instances to extract, explain and interpret inference mechanisms learnt by the model that are useful for the end-user. The framework was tested on about 100,000 EPCs of flats located in Italy. • A data-driven benchmarking process of building energy performance is proposed. • A set of about 100,000 energy performance certificates of buildings is analysed. • Five classification algorithms are considered for developing the benchmarking tool. • Clustering analysis and XAI are coupled for extracting human-readable patterns. • Classification results are explained for understanding the model behaviour. [ABSTRACT FROM AUTHOR]

The influence of training, posture, nutrition or psychological attitudes on an athlete’s career is well described in literature. An additional factor of success that is widely recognized as crucial is the network of matches that an athlete plays during a season. The hypothesis is that the quality of a player’s opponents affects her long-term ranking and performance. Even though the relevance of these factors is widely recognized as important, a quantitative characterization is missing. In this paper, we try to fill this gap combining network analysis and machine learning to estimate the contribution of the network of matches in predicting an athlete’s success. We consider all the official games played by the Italian table tennis players between 2011 and 2016. We observe that the matches network shows scale-free behavior, typical of several real-world systems, and that different structural properties are positively correlated with the athletes’ performance (Spearman , p-value ). Using these findings, we implement three different tasks, such as talent identification, performance and ranking prediction. Results shows consistently that machine learning approaches are able to predict players’ success and that the topological features play an effective role in increasing their predictive power. [ABSTRACT FROM AUTHOR]

This paper discusses an intelligent data analysis approach, based on machine learning techniques, and aimed at the definition of methods for chemical data analysis assessment of the authenticity and protection, against fake versions, of some of the highest value Nebbiolo-based wines from Piedmont (Italy). This is an important and very relevant issue in the wine market, where commercial frauds related to such a kind of products are estimated to be worth millions of Euros. The objective is twofold: to show that the problem can be addressed without expensive and hyper-specialized wine chemical analyses, and to demonstrate the actual usefulness of classification algorithms for data mining and machine learning on the resulting chemical profiles. Following Wagstaff's proposal for practical exploitation of machine learning approaches, we describe how data have been collected and prepared for the production of different datasets, how suitable classification models have been identified and how the interpretation of the results suggests the emergence of an active role of machine learning classification techniques, based on standard chemical profiling, for the assesment of the authenticity of the wines target of the study. Experiments have been performed with both datasets of real samples and with syntethic datasets which have been artificially generated from real data. [ABSTRACT FROM AUTHOR]

• Cumulative rain depths overcome the lack of temporal memory of Feed Forward NN. • The Softmax function in the ML models enables the probabilistic nowcasts. • 95 models were independently trained for lead times up to 6 h. • The models provided better nowcasts when the extension of the event was homogeneous. • According to physical models, as the lead-time increases, predictive accuracy decreases. Rainfall nowcasting supports emergency decision-making in hydrological, agricultural, and economical sectors. However, short-term prediction is challenging because meteorological variables are strongly interconnected and rapidly change during an event. Since machine learning do not require any previous physical assumption, this study investigates their ability to provide reliable and quick forecasts. This paper proposes a machine learning model for probabilistic rainfall nowcasting at 10 min intervals for short lead times - from 30 min up to 6 h. The model employs cumulative rainfall fields from station data as inputs for a feed forward neural network to predict rainfall interval and the corresponding probability of occurrence. Cumulative rainfall depths from station data were used to overcome the lack of temporal memory of the feed forward neural networks. In this way, using only the current rain field as input, the model exploited pattern recognition techniques combining both temporal - cumulative rainfall depth - and spatial - cumulative rainfall field – information. Based on 359 rain events observed in an area of 1619 km2 in Southern Italy, 95 machine learning models were independently trained for 19 recording stations and for each target lead-time (30, 60, 120, 180 and 360 min). Comprehensive nowcasts verification was performed to analyse the reliability of probabilistic nowcasts using both continuous (RMSE and RAE) and categorical (POD, FAR and CSI) indicators. The performance of the models was also compared with the results of Eulerian Persistence. All the models produced consistent nowcasts and learnt the complex relationship describing space–time rainfall evolution. As expected, predictive accuracy gradually decreased as the lead-time increase, according to physically based models. Results showed that the use of both temporal and spatial information enables the model to predict short-term rainfall using only the current measurements as input, resulting in a rapid, easily replicable and convenient nowcasting approach. The procedure is an effective way to predict multi-step rainfall fields and is suitable for operational early warning system. [ABSTRACT FROM AUTHOR]

This paper proposes a methodology for correlating products derived by Synthetic Aperture Radar (SAR) measurements and laser profilometric road roughness surveys. The procedure stems from two previous studies, in which several Machine Learning Algorithms (MLAs) have been calibrated for predicting the average vertical displacement (in terms of mm/year) of road pavements as a result of exogenous phenomena occurrence, such as subsidence. Such algorithms are based on surveys performed with Persistent Scatterer Interferometric SAR (PS-InSAR) over an area of 964 km2 in the Tuscany Region, Central Italy. Starting from this basis, in this paper, we propose to integrate the information provided by these MLAs with 10 km of in situ profilometric measurements of the pavement surface roughness and relative calculation of the International Roughness Index (IRI). Accordingly, the aim is to appreciate whether and to what extent there is an association between displacements estimated by MLAs and IRI values. If a dependence exists, we may argue that road regularity is driven by exogenous phenomena and MLAs allow for the replacement of in situ surveys, saving considerable time and money. In this research framework, results reveal that there are several road sections that manifest a clear association among these two methods, while others denote that the relationship is weaker, and in situ activities cannot be bypassed to evaluate the real pavement conditions. We could wrap up that, in these stretches, the road regularity is driven by endogenous factors which MLAs did not integrate during their training. Once additional MLAs conditioned by endogenous factors have been developed (such as traffic flow, the structure of the pavement layers, and material characteristics), practitioners should be able to estimate the quality of pavement over extensive and complex road networks quickly, automatically, and with relatively low costs. [ABSTRACT FROM AUTHOR]

Nowadays the introduction of energy marketplaces in several countries pushed the development of machine learning approaches for devising effective predictions about both energy needs and energy productions. In this paper we address the problem of predicting the amount of electrical power produced using non-renewable sources, as getting an estimate of the amount of electrical power produced using the various kinds of non-renewable sources yields a big competitive advantage for energy market investors. Specifically, we devise a forecasting technique obtained by trying and combining various machine learning techniques which is able to provide energy production estimates with a remarkably low error. Finally, since the input data available for predictions are in general not sufficient to determine the amounts of produced energy for the various source types, we provide an estimate of the impact of unknown latent variable on the amounts of produced energy, by devising a prediction model which is capable of estimating the prediction error for the specific data at hand. These informations can be exploited by investors to get an idea of the risk levels of their investments. • New model for predicting the amount of non-renewable energy produced in Italy. • The model uses mostly publicly available information sources. • The experiments allow us to assess that GBRT is the best model for this task. • Experimentally investigation of the possibility of identifying hard cases. • KNN is the only technique that is able to identify hard cases. [ABSTRACT FROM AUTHOR]

• A FE model calibration based on AVT and machine learning process is presented. • The dynamic parameters of the investigated tower are estimated via OMA techniques. • Different parameterization and modelling assumptions are employed for the updating. • The calibrated model accurately reproduces the real dynamic behaviour of the tower. Cultural Heritage preservation requires the combination of in situ investigations and accurate Finite Elements models in order to correctly interpret the empirical evidence and successfully apply advanced structural analyses for health assessment purposes, allowing to infer about the future evolution of the structural response and timely detect deviations from the expected behaviour. In this paper the actual dynamic behaviour of the Civic Tower of Ostra, Italy, is thoroughly investigated by means of a detailed numerical model built and calibrated using the experimental modal features estimated through field dynamic testing. To this end, a fully automated Finite Element Model Updating procedure based on genetic algorithms and machine learning is conceived and employed, allowing the successful estimation of the unknown material properties of the tower, considering both isotropic and orthotropic behavioural models for masonry. The results enabled to establish baseline information on the current structural condition of the heritage and to set performance standards that will serve to optimise the control of the structural integrity over time. [ABSTRACT FROM AUTHOR]

[Display omitted] • Mapping and monitoring of slow-moving landslides. • Remote Sensing, statistical and ground-based measurements have been combined. • Integration of Machine Learning and InSAR techniques for landslide risk assessment. This paper describes a novel methodology where Machine Learning Algorithms (MLAs) have been integrated to assess the landslide risk for slow moving mass movements, processes whose intermittent activity makes challenging any risk analysis worldwide. MLAs has been trained on datasets including Interferometric Synthetic Aperture Radar (InSAR) and additional remote sensing datasets such as aerial stereo photographs and LiDAR and tested in the Termini-Nerano landslides system (southern Apennines, Italy). The availability of such a wealth of materials allows also an unprecedented spatio-temporal reconstruction of the volume and the kinematic of the landslides system through which we could generate and validate the hazard map. Our analysis identifies fifteen slow-moving phenomena, traceable since 1955, whose total area amounts to 4.1 × 105 m2 and volume to ~1.4 × 106 m3. InSAR results prove that seven out of the fifteen slow-moving landslides are currently active and characterized by seasonal velocity patterns. These new insights on the dynamic of the landslides system have been selected as the main independent variables to train three MLAs (Artificial Neural Network, Generalized Boosting Model and Maximum Entropy) and derive the landslide hazard for the area. Finally, official population and buildings census data have been used to assess the landslide risk whose highest values are located in the crown area, south of Termini village, and nearby Nerano. This new methodology provides a different landslide risk scenario compared to the existing official documents for the study area and overall new insights on how to develop landslide risk management strategies worldwide based on a better understanding of slope processes thanks to the latest satellite technologies available. [ABSTRACT FROM AUTHOR]

• Two-phase training algorithm able to boost the Machine Learning accuracy. • Accurate bankruptcy prediction up to 60 months by a Machine Learning algorithm. • Integration of the Machine Learning algorithm in a DSS for policy making. • Test of the DSS on the Italian SMEs, with a focus on the COVID-19 effects. In the field of detection and prediction of company defaults and bankruptcy, significant effort has been devoted to evaluating financial ratios as predictors using statistical models and machine learning techniques. This problem becomes crucially important when financial decision-makers are provided with predictions on which to act, based on the output of prediction models. However, research has shown that such predictors are sufficiently accurate in the short-term, with the focus mainly directed towards large and medium-large companies. In contrast, in this paper, we focus on mid- and long-term bankruptcy prediction (up to 60 months) targeting small and/or medium enterprises. The key contribution of this study is a substantial improvement of the prediction accuracy in the short-term (12 months) using machine learning techniques, compared to the state-of-the-art, while also making accurate mid- and long-term predictions (measure of the area under the ROC curve of 0.88 with a 60 month prediction horizon). Extensive computational tests on the entire set of companies in Italy highlight the efficiency and accuracy of the developed method, as well as demonstrating the possibility of using it as a tool for the development of strategies and policies for entire economic systems. Considering the recent COVID-19 pandemic, we show how our method can be used as a viable tool for large-scale policy-making. [ABSTRACT FROM AUTHOR]

Photovoltaic (PV) plants typically suffer from a significant degradation in performance over time due to multiple factors. Operation and maintenance systems aim at increasing the efficiency and profitability of PV plants by analyzing the monitoring data and by applying data-driven methods for assessing the causes of such performance degradation. Two main classes of degradation exist, being it either gradual or a sudden anomaly in the PV system. This has motivated our work to develop and implement statistical methods that can reliably and accurately detect the performance issues in a cost-effective manner. In this paper, we introduce different approaches for both gradual degradation assessment and anomaly detection. Depending on the data available in the PV plant monitoring system, the appropriate method for each degradation class can be selected. The performance of the introduced methods is demonstrated on data from three different PV plants located in Slovenia and Italy monitored for several years. Our work has led us to conclude that the introduced approaches can contribute to the prompt and accurate identification of both gradual degradation and sudden anomalies in PV plants. [ABSTRACT FROM AUTHOR]

District Heating (DH) technology is considered to be a sustainable and quasi-renewable way of producing and distributing hot water along the city to heat buildings. However, the main obstacle to wider adoption of DH technology is represented by the thermal request peak in the morning hours of winter days, especially in Mediterranean countries. In this paper, this peak-shaving problem is tackled by combining three different approaches. A thermodynamic model is used to monitor the buildings' thermal response to energy profile modifications. An agent-based model is adopted in order to represent the end-users and their adaptability to variations of temperatures in buildings. Finally, a Reinforcement Learning algorithm is used to optimally mediate between two needs: on the one hand, a set of anticipations and delays is applied to the energy profiles in order to reduce the thermal request peak. On the other hand, the algorithm learns by trial and error the individual agents' sensitivity to thermal comfort, avoiding drastic modifications for the most sensitive users. The experiments carried out in the DH network in Torino (north-west of Italy) demonstrate that the proposed approach, compared with a literature solution chosen as a baseline, allows to achieve better results in terms of overall performances and speed of convergence. [ABSTRACT FROM AUTHOR]

In the light of the "Biological Diversity" concept, habitats are cardinal pieces for biodiversity quantitative estimation at a local and global scale. In Europe EUNIS (European Nature Information System) is a system tool for habitat identification and assessment. Earth Observation (EO) data, which are acquired by satellite sensors, offer new opportunities for environmental sciences and they are revolutionizing the methodologies applied. These are providing unprecedented insights for habitat monitoring and for evaluating the Sustainable Development Goals (SDGs) indicators. This paper shows the results of a novel approach for a spatially explicit habitat mapping in Italy at a national scale, using a supervised machine learning model (SMLM), through the combination of vegetation plot database (as response variable), and both spectral and environmental predictors. The procedure integrates forest habitat data in Italy from the European Vegetation Archive (EVA), with Sentinel-2 imagery processing (vegetation indices time series, spectral indices, and single bands spectral signals) and environmental data variables (i.e., climatic and topographic), to parameterize a Random Forests (RF) classifier. The obtained results classify 24 forest habitats according to the EUNIS III level: 12 broadleaved deciduous (T1), 4 broadleaved evergreen (T2) and eight needleleaved forest habitats (T3), and achieved an overall accuracy of 87% at the EUNIS II level classes (T1, T2, T3), and an overall accuracy of 76.14% at the EUNIS III level. The highest overall accuracy value was obtained for the broadleaved evergreen forest equal to 91%, followed by 76% and 68% for needleleaved and broadleaved deciduous habitat forests, respectively. The results of the proposed methodology open the way to increase the EUNIS habitat categories to be mapped together with their geographical extent, and to test different semi-supervised machine learning algorithms and ensemble modelling methods. [ABSTRACT FROM AUTHOR]

In this paper, multi-frequency synthetic aperture radar (SAR) data at L- and C-bands (ALOS PALSAR and Envisat/ASAR) were used to estimate forest biomass in Tuscany, in Central Italy. The ground measurements of woody volume (WV, in m3/ha), which can be considered as a proxy of forest biomass, were retrieved from the Italian National Forest Inventory (NFI). After a preliminary investigation to assess the sensitivity of backscatter at C- and L-bands to forest biomass, an approach based on an artificial neural network (ANN) was implemented. The ANN was trained using the backscattering coefficient at L-band (ALOS PALSAR, HH and HV polarization) and C-band (Envisat ASAR in HH polarization) as inputs. Spatially distributed WV values for the entire test area were derived by the integration (fusion) of a canopy height map derived from the Ice, Cloud, and Land Elevation Geoscience Laser Altimeter System (ICESat GLAS) and the NFI data, in order to build a significant ground truth dataset for the training stage. The analysis of the backscattering sensitivity to WV showed a moderate correlation at L-band and was almost negligible at C-band. Despite this, the ANN algorithm was able to exploit the synergy of SAR frequencies and polarizations, estimating WV with average Pearson's correlation coefficient (R) = 0.96 and root mean square error (RMSE) ≃ 39 m3/ha when applied to the test dataset and average R = 0.86 and RMSE ≃ 75 m3/ha when validated on the direct measurements from the NFI. Considering the heterogeneity of the scenario (Mediterranean mixed forests in hilly landscape) and the small amount of available ground measurements with respect to the spatial variability of different plots, the obtained results can be considered satisfactory. Moreover, the successful use of WV from global maps for implementing the algorithm suggests the possibility to apply the algorithm to wider areas or even to global scales. [ABSTRACT FROM AUTHOR]

This paper introduces a methodology for predicting and mapping surface motion beneath road pavement structures caused by environmental factors. Persistent Scatterer Interferometric Synthetic Aperture Radar (PS-InSAR) measurements, geospatial analyses, and Machine Learning Algorithms (MLAs) are employed for achieving the purpose. Two single learners, i.e., Regression Tree (RT) and Support Vector Machine (SVM), and two ensemble learners, i.e., Boosted Regression Trees (BRT) and Random Forest (RF) are utilized for estimating the surface motion ratio in terms of mm/year over the Province of Pistoia (Tuscany Region, central Italy, 964 km2), in which strong subsidence phenomena have occurred. The interferometric process of 210 Sentinel-1 images from 2014 to 2019 allows exploiting the average displacements of 52,257 Persistent Scatterers as output targets to predict. A set of 29 environmental-related factors are preprocessed by SAGA-GIS, version 2.3.2, and ESRI ArcGIS, version 10.5, and employed as input features. Once the dataset has been prepared, three wrapper feature selection approaches (backward, forward, and bi-directional) are used for recognizing the set of most relevant features to be used in the modeling. A random splitting of the dataset in 70% and 30% is implemented to identify the training and test set. Through a Bayesian Optimization Algorithm (BOA) and a 10-Fold Cross-Validation (CV), the algorithms are trained and validated. Therefore, the Predictive Performance of MLAs is evaluated and compared by plotting the Taylor Diagram. Outcomes show that SVM and BRT are the most suitable algorithms; in the test phase, BRT has the highest Correlation Coefficient (0.96) and the lowest Root Mean Square Error (0.44 mm/year), while the SVM has the lowest difference between the standard deviation of its predictions (2.05 mm/year) and that of the reference samples (2.09 mm/year). Finally, algorithms are used for mapping surface motion over the study area. We propose three case studies on critical stretches of two-lane rural roads for evaluating the reliability of the procedure. Road authorities could consider the proposed methodology for their monitoring, management, and planning activities. [ABSTRACT FROM AUTHOR]

Xylella fastidiosa (Xf) is a well-known bacterial plant pathogen mainly transmitted by vector insects and is associated with serious diseases affecting a wide variety of plants, both wild and cultivated; it is known that over 350 plant species are prone to Xf attack. In olive trees, it causes olive quick decline syndrome (OQDS), which is currently a serious threat to the survival of hundreds of thousands of olive trees in the south of Italy and in other countries in the European Union. Controls and countermeasures are in place to limit the further spreading of the bacterium, but it is a tough war to fight mainly due to the invasiveness of the actions that can be taken against it. The most effective weapons against the spread of Xf infection in olive trees are the detection of its presence as early as possible and attacks to the development of its vector insects. In this paper, image processing of high-resolution visible and multispectral images acquired by a purposely equipped multirotor unmanned aerial vehicle (UAV) is proposed for fast detection of Xf symptoms in olive trees. Acquired images were processed using a new segmentation algorithm to recognize trees which were subsequently classified using linear discriminant analysis. Preliminary experimental results obtained by flying over olive groves in selected sites in the south of Italy are presented, demonstrating a mean Sørensen–Dice similarity coefficient of about 70% for segmentation, and 98% sensitivity and 93% precision for the classification of affected trees. The high similarity coefficient indicated that the segmentation algorithm was successful at isolating the regions of interest containing trees, while the high sensitivity and precision showed that OQDS can be detected with a low relative number of both false positives and false negatives. [ABSTRACT FROM AUTHOR]

Lack of accurate and up-to-date data associated with irrigated areas and related irrigation amounts is hampering the full implementation and compliance of the Water Framework Directive (WFD). In this paper, we describe the framework that we developed and implemented within the DIANA project to map the actual extent of irrigated areas in the Campania region (Southern Italy) during the 2018 irrigation season. For this purpose, we considered 202 images from the Harmonized Landsat Sentinel-2 (HLS) products (57 images from Landsat 8 and 145 images from Sentinel-2). Such data were preprocessed in order to extract a multitemporal Normalized Difference Vegetation Index (NDVI) map, which was then smoothed through a gap-filling algorithm. We further integrated data coming from high-resolution (4 km) global satellite precipitation Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks (PERSIANN)-Cloud Classification System (CCS) products. We collected an extensive ground truth in the field represented by 2992 data points coming from three main thematic classes: bare soil and rainfed (class 0), herbaceous (class 1), and tree crop (class 2). This information was exploited to generate irrigated area maps by adopting a machine learning classification approach. We compared six different types of classifiers through a cross-validation approach and found that, in general, random forests, support vector machines, and boosted decision trees exhibited the best performances in terms of classification accuracy and robustness to different tested scenarios. We found an overall accuracy close to 90% in discriminating among the three thematic classes, which highlighted promising capabilities in the detection of irrigated areas from HLS products. [ABSTRACT FROM AUTHOR]

The diagnosis of psychogenic nonepileptic seizures (PNES) by means of electroencephalography (EEG) is not a trivial task during clinical practice for neurologists. No clear PNES electrophysiological biomarker has yet been found, and the only tool available for diagnosis is video EEG monitoring with recording of a typical episode and clinical history of the subject. In this paper, a data-driven machine learning (ML) pipeline for classifying EEG segments (i.e., epochs) of PNES and healthy controls (CNT) is introduced. This software pipeline consists of a semiautomatic signal processing technique and a supervised ML classifier to aid clinical discriminative diagnosis of PNES by means of an EEG time series. In our ML pipeline, statistical features like the mean, standard deviation, kurtosis, and skewness are extracted in a power spectral density (PSD) map split up in five conventional EEG rhythms (delta, theta, alpha, beta, and the whole band, i.e., 1–32 Hz). Then, the feature vector is fed into three different supervised ML algorithms, namely, the support vector machine (SVM), linear discriminant analysis (LDA), and Bayesian network (BN), to perform EEG segment classification tasks for CNT vs. PNES. The performance of the pipeline algorithm was evaluated on a dataset of 20 EEG signals (10 PNES and 10 CNT) that was recorded in eyes-closed resting condition at the Regional Epilepsy Centre, Great Metropolitan Hospital of Reggio Calabria, University of Catanzaro, Italy. The experimental results showed that PNES vs. CNT discrimination tasks performed via the ML algorithm and validated with random split (RS) achieved an average accuracy of 0.97 ± 0.013 (RS-SVM), 0.99 ± 0.02 (RS-LDA), and 0.82 ± 0.109 (RS-BN). Meanwhile, with leave-one-out (LOO) validation, an average accuracy of 0.98 ± 0.0233 (LOO-SVM), 0.98 ± 0.124 (LOO-LDA), and 0.81 ± 0.109 (LOO-BN) was achieved. Our findings showed that BN was outperformed by SVM and LDA. The promising results of the proposed software pipeline suggest that it may be a valuable tool to support existing clinical diagnosis. [ABSTRACT FROM AUTHOR]

In this paper, multifrequency synthetic aperture radar (SAR) images from ALOS/PALSAR, ENVISAT/ASAR and Cosmo-SkyMed sensors were studied for forest classification in a test area in Central Italy (San Rossore), where detailed in-situ measurements were available. A preliminary discrimination of the main land cover classes and forest types was carried out by exploiting the synergy among L-, C- and X-bands and different polarizations. SAR data were preliminarily inspected to assess the capabilities of discriminating forest from non-forest and separating broadleaf from coniferous forests. The temporal average backscattering coefficient ( σ ¯ °) was computed for each sensor-polarization pair and labeled on a pixel basis according to the reference map. Several classification methods based on the machine learning framework were applied and validated considering different features, in order to highlight the contribution of bands and polarizations, as well as to assess the classifiers' performance. The experimental results indicate that the different surface types are best identified by using all bands, followed by joint L- and X-bands. In the former case, the best overall average accuracy (83.1%) is achieved by random forest classification. Finally, the classification maps on class edges are discussed to highlight the misclassification errors. [ABSTRACT FROM AUTHOR]