Search

Background: To compare the difference in rebubbling rates between patients undergoing Descemet membrane endothelial keratoplasty (DMEK) with endothelium-in using a standard IOL cartridge and those with endothelium-out DMEK utilizing a no-touch technique with borosilicate glass cartridge transplantation. Methods: This retrospective study included all eyes that underwent preloaded endothelium-in or endothelium-out DMEK transplantation from June 2019 to December 2023 at the Hanusch Hospital, Vienna, Austria. All DMEKs were harvested, prepared and preloaded at the European Eye Bank of Venice, Italy. DMEK surgeries were done by one experienced surgeon and the procedure was completed by air tamponade of the anterior chamber. Results: Overall, 32 eyes each of 31 endothelium-out patients and of 29 endothelium-in patients were included. 32 preloaded endothelium-in procedures were followed by 32 preloaded endothelium-out procedures. Rebubbling rate for endothelium-in was 15/32 (47%) and for endothelium-out was 7/25 (28%) (p = 0.035, Pearson's chi-squared test). Donor age was the most important variable for rebubbling in a random forest algorithm model (ROC: 0.69). Conclusions: Rebubbling rate in endothelium-out DMEK was less than two-thirds compared to endothelium-in DMEK favoring no-touch endothelium-out DMEK as the preferred technique of DMEK transplantation. [ABSTRACT FROM AUTHOR]

Salmonellosis, one of the most common foodborne infections in Europe, is monitored by food safety surveillance programmes, resulting in the generation of extensive databases. By leveraging tree-based machine learning (ML) algorithms, we exploited data from food safety audits to predict spatiotemporal patterns of salmonellosis in northwestern Italy. Data on human cases confirmed in 2015–2018 (n = 1969) and food surveillance data collected in 2014–2018 were used to develop ML algorithms. We integrated the monthly municipal human incidence with 27 potential predictors, including the observed prevalence of Salmonella in food. We applied the tree regression, random forest and gradient boosting algorithms considering different scenarios and evaluated their predictivity in terms of the mean absolute percentage error (MAPE) and R2. Using a similar dataset from the year 2019, spatiotemporal predictions and their relative sensitivities and specificities were obtained. Random forest and gradient boosting (R2 = 0.55, MAPE = 7.5%) outperformed the tree regression algorithm (R2 = 0.42, MAPE = 8.8%). Salmonella prevalence in food; spatial features; and monitoring efforts in ready-to-eat milk, fruits and vegetables, and pig meat products contributed the most to the models' predictivity, reducing the variance by 90.5%. Conversely, the number of positive samples obtained for specific food matrices minimally influenced the predictions (2.9%). Spatiotemporal predictions for 2019 showed sensitivity and specificity levels of 46.5% (due to the lack of some infection hotspots) and 78.5%, respectively. This study demonstrates the added value of integrating data from human and veterinary health services to develop predictive models of human salmonellosis occurrence, providing early warnings useful for mitigating foodborne disease impacts on public health. [ABSTRACT FROM AUTHOR]

Predicting electricity production from renewable energy sources, such as solar photovoltaic installations, is crucial for effective grid management and energy planning in the transition towards a sustainable future. This study proposes machine learning approaches for predicting electricity production from solar photovoltaic installations at a regional level in Italy, not using data on individual installations. Addressing the challenge of diverse data availability between pinpoint meteorological inputs and aggregated power data for entire regions, we propose leveraging meteorological data from the centroid of each Italian province within each region. Particular attention is given to the selection of the best input features, which leads to augmenting the input with 1-hour-lagged meteorological data and previous-hour power data. Several ML approaches were compared and examined, optimizing the hyperparameters through five-fold cross-validation. The hourly predictions encompass a time horizon ranging from 1 to 24 h. Among tested methods, Kernel Ridge Regression and Random Forest Regression emerge as the most effective models for our specific application. We also performed experiments to assess how frequently the models should be retrained and how frequently the hyperparameters should be optimized in order to comprise between accuracy and computational costs. Our results indicate that once trained, the model can provide accurate predictions for extended periods without frequent retraining, highlighting its long-term reliability. [ABSTRACT FROM AUTHOR]

Simple Summary: The differential diagnosis between uterine leiomyosarcomas and leiomyomas based on imaging represents one of the major challenges for gynecologists and radiologists. Currently, only histological examination can definitively resolve doubts in suspicious cases. The purpose of this study is to develop a machine learning model that can support clinical decision making. One of the proposed approaches, i.e., using the general linear model (GLM) classifier, has been patented by our team and has demonstrated good performance in retrospective analyses, with predicted area under the curve (AUC), sensitivity, and specificity on the test set ranging from 0.78 to 0.82, from 0.78 to 0.89, and from 0.67 to 0.87, respectively. The next step will involve validation at other medical centers and its prospective application. Background: The accurate discrimination of uterine leiomyosarcomas and leiomyomas in a pre-operative setting remains a current challenge. To date, the diagnosis is made by a pathologist on the excised tumor. The aim of this study was to develop a machine learning algorithm using radiomic data extracted from contrast-enhanced computed tomography (CECT) images that could accurately distinguish leiomyosarcomas from leiomyomas. Methods: Pre-operative CECT images from patients submitted to surgery with a histological diagnosis of leiomyoma or leiomyosarcoma were used for the region of interest identification and radiomic feature extraction. Feature extraction was conducted using the PyRadiomics library, and three feature selection methods combined with the general linear model (GLM), random forest (RF), and support vector machine (SVM) classifiers were built, trained, and tested for the binary classification task (malignant vs. benign). In parallel, radiologists assessed the diagnosis with or without clinical data. Results: A total of 30 patients with leiomyosarcoma (mean age 59 years) and 35 patients with leiomyoma (mean age 48 years) were included in the study, comprising 30 and 51 lesions, respectively. Out of nine machine learning models, the three feature selection methods combined with the GLM and RF classifiers showed good performances, with predicted area under the curve (AUC), sensitivity, and specificity ranging from 0.78 to 0.97, from 0.78 to 1.00, and from 0.67 to 0.93, respectively, when compared to the results obtained from experienced radiologists when blinded to the clinical profile (AUC = 0.73 95%CI = 0.62–0.84), as well as when the clinical data were consulted (AUC = 0.75 95%CI = 0.65–0.85). Conclusions: CECT images integrated with radiomics have great potential in differentiating uterine leiomyomas from leiomyosarcomas. Such a tool can be used to mitigate the risks of eventual surgical spread in the case of leiomyosarcoma and allow for safer fertility-sparing treatment in patients with benign uterine lesions. [ABSTRACT FROM AUTHOR]

Invasive mosquitoes are an emerging public health issue, as many species are competent vectors for pathogens. We assessed how multiple environmental and socio-economic factors affected the engagement of municipalities in Italy (n = 7679) in actions against Aedes albopictus, an invasive mosquito affecting human health and well-being, between 2000 and 2020. We collected information about mosquito control from official documents and municipal websites and modeled the role played by multiple environmental and socioeconomic factors characterizing each municipality through the random forest algorithm. Municipalities are more prone to manage A. albopictus if more urbanized, in lowlands and with long infestation periods. Moreover, these variables are more predictive of management in municipalities with a high median income and thus more economic resources. Only 25.5% of Italian municipalities approved regulations for managing A. albopictus, and very few of them were in Southern Italy, the most deprived area of the country. Our findings indicate that local economic conditions moderate the effect of other drivers of mosquito control and ultimately can lead to better management of A. albopictus. If the management of invasive mosquitoes, or other forms of global change, is subjected to local economic conditions, economic inequalities will jeopardize the success of large-scale policies, also raising issues of environmental and climate justice. [ABSTRACT FROM AUTHOR]

Determining spatial thickness (z) of fallout pyroclastic deposits plays a key role in volcanological studies and shedding light on geomorphological and hydrogeological processes. However, this is a challenging line of research because: (1) field-based measurements are expensive and time-consuming; (2) the ash might have been dispersed in the atmosphere by several volcanic eruptions; and (3) wind characteristics during an eruptive event and soil-forming/denudation processes after ash deposition on the ground surface affect the expected spatial distribution of the fallout pyroclastic deposits. This article tries to bridge this knowledge gap by applying statistical techniques for making representative predictions. First, we compiled a field-based thickness measurement dataset (https://doi.org/10.5281/zenodo.8399487 ; Matano et al., 2023) of fallout pyroclastic deposits in several municipalities of Campania region, southern Italy. Second, 18 predictor variables were derived mainly from digital elevation models and satellite imageries and assigned to each measurement point. Third, the stepwise regression (STPW) model and random forest (RF) machine learning technique are used for thickness modeling. Fourth, the estimations are compared with those of three models that already exist in the literature. Finally, the statistical combination of different predictions is implemented to develop a less biased model for estimating pyroclastic thickness. The results show that prediction accuracy of RF (RMSE < 82.46 and MAE < 48.36) is better than that existing literature models. Moreover, statistical combination of the predictions obtained from the above-mentioned models through Least Absolute Deviation (LAD) combination approach leads to the most representative thickness estimation (MAE < 45.12) in the study area. The maps for the values estimated by RF and LAD (as the best single model and combination approach, respectively) illustrate that the spatial patterns did not alter significantly, but the estimations by LAD are smaller. This combined approach can help in estimating thickness of fallout pyroclastic deposits in other volcanic regions and in managing geohazards in areas covered with loose pyroclastic materials. [ABSTRACT FROM AUTHOR]

Lampetra zanandreai (Vladykov, 1955) is a non-parasitic, freshwater lamprey endemic to the ancient Po basin. A few, mostly very dated studies have investigated some aspect of the biology of this lamprey, but surprisingly, despite it being considered a threatened species, information on its ecology is practically absent. Specifically, information about habitat preferences is generic and qualitative. Since most of the life cycle is spent in the fossorial larval stage, which is also the only one in which organisms feed, information about ecological requirements of ammocoetes is essential for any conservation strategy. In this study we provide the first data about physical habitat preferences for lamprey ammocoetes by analyzing their presence within sampled hydromorphological units (HMUs), following the approach of habitat attribute description of the MesoHABSIM (MesoHABitat SImulation Model) methodology. To explore the relationship between lamprey presence and HMU characteristics, a random forest (RF) model was developed and tested using data collected in five stream reaches of the Po basin (NW Italy). The final parsimonious RF model performed well in terms of accuracy (95.2%) and true skill statistic (90.4%), allowing us to identify the most significant mesohabitat attributes for the considered species. Furthermore, in the Ghiandone River, where the highest density and number of individuals were found, a granulometric analysis of the riverbed material was carried out. Results showed that selected strains of sand and fine gravel, with low organic content, are preferred by ammocoetes. To our knowledge, this is the first study exploring the habitat preference of this endangered species, listed in Annex II of the European Habitats Directive. [ABSTRACT FROM AUTHOR]

State-of-the-art snow sensing technologies currently provide an unprecedented amount of data from both remote sensing and ground sensors, but their assimilation into dynamic models is bounded to data quality, which is often low – especially in mountain, high-elevation, and unattended regions where snow is the predominant land-cover feature. To maximize the value of snow-depth measurements, we developed a random forest classifier to automatize the quality assurance and quality control (QA/QC) procedure of near-surface snow-depth measurements collected through ultrasonic sensors, with particular reference to the differentiation of snow cover from grass or bare-ground data and to the detection of random errors (e.g., spikes). The model was trained and validated using a split-sample approach of an already manually classified dataset of 18 years of data from 43 sensors in Aosta Valley (northwestern Italian Alps) and then further validated using 3 years of data from 27 stations across the rest of Italy (with no further training or tuning). The F1 score was used as scoring metric, it being the most suited to describe the performances of a model in the case of a multiclass imbalanced classification problem. The model proved to be both robust and reliable in the classification of snow cover vs. grass/bare ground in Aosta Valley (F1 values above 90 %) yet less reliable in rare random-error detection, mostly due to the dataset imbalance (samples distribution: 46.46 % snow, 49.21 % grass/bare ground, 4.34 % error). No clear correlation with snow-season climatology was found in the training dataset, which further suggests the robustness of our approach. The application across the rest of Italy yielded F1 scores on the order of 90 % for snow and grass/bare ground, thus confirming results from the testing region and corroborating model robustness and reliability, with again a less skillful classification of random errors (values below 5 %). This machine learning algorithm of data quality assessment will provide more reliable snow data, enhancing their use in snow models. [ABSTRACT FROM AUTHOR]

Understanding and monitoring the ecological quality of coastal waters is crucial for preserving marine ecosystems. Eutrophication is one of the major problems affecting the ecological state of coastal marine waters. For this reason, the control of the trophic conditions of aquatic ecosystems is needed for the evaluation of their ecological quality. This study leverages space-based Sentinel-3 Ocean and Land Color Instrument imagery (OLCI) to assess the ecological quality of Mediterranean coastal waters using the Trophic Index (TRIX) key indicator. In particular, we explore the feasibility of coupling remote sensing and machine learning techniques to estimate the TRIX levels in the Ligurian, Tyrrhenian, and Ionian coastal regions of Italy. Our research reveals distinct geographical patterns in TRIX values across the study area, with some regions exhibiting eutrophic conditions near estuaries and others showing oligotrophic characteristics. We employ the Random Forest Regression algorithm, optimizing calibration parameters to predict TRIX levels. Feature importance analysis highlights the significance of latitude, longitude, and specific spectral bands in TRIX prediction. A final statistical assessment validates our model's performance, demonstrating a moderate level of error (MAE of 0.51) and explanatory power (R2 of 0.37). These results highlight the potential of Sentinel-3 OLCI imagery in assessing ecological quality, contributing to our understanding of coastal water ecology. They also underscore the importance of merging remote sensing and machine learning in environmental monitoring and management. Future research should refine methodologies and expand datasets to enhance TRIX monitoring capabilities from space. [ABSTRACT FROM AUTHOR]

Predicting the occurrence of erosive rain events and quantifying the corresponding soil loss is extremely useful in all applications where assessing phenomenon impacts is required. These problems, addressed in the literature at different spatial and temporal scales and according to the most diverse approaches, are here addressed by implementing random forest (RF) machine learning models. For this purpose, we used the datasets built through many years of soil loss observations at the plot-scale experimental site SERLAB (central Italy). Based on 32 features describing rainfall characteristics, the RF classifier has achieved a global accuracy of 84.8% in recognizing erosive and non-erosive events, thus demonstrating slightly higher performances than previously used (non-machine learning) methodologies. A critical performance is the percentage of erosive events correctly recognized to the observed total (72.3%). However, since the most relevant erosive events are correctly identified, we found only a slight underestimation of the total rainfall erosivity (91%). The RF regression model for estimating the event soil loss, based on three event features (runoff coefficient, erosivity, and period of occurrence), demonstrates better performances (RMSE = 2.30 Mg ha−1) than traditional regression models (RMSE = 3.34 Mg ha−1). [ABSTRACT FROM AUTHOR]

BACKGROUND: The role of chronic exposure to ambient air pollutants in increasing COVID-19 fatality is still unclear. OBJECTIVES: The study aimed to investigate the association between long-term exposure to air pollutants and mortality among 4 million COVID-19 cases in Italy. METHODS: We obtained individual records of all COVID-19 cases identified in Italy from February 2020 to June 2021. We assigned 2016-2019 mean concentrations of particulate matter (PM) with aerodynamic diameter =10 μm (PM10), PM with aerodynamic diameter = 2.5 μm (PM2.5), and nitrogen dioxide (NO2) to each municipality (푛 = 7,800) as estimates of chronic exposures. We applied a principal component analysis (PCA) and a generalized propensity score (GPS) approach to an extensive list of area-level covariates to account for major determinants of the spatial distribution of COVID-19 case-fatality rates. Then, we applied generalized negative binomial models matched on GPS, age, sex, province, and month. As additional analyses, we fit separate models by pandemic periods, age, and sex; we quantified the numbers of COVID-19 deaths attributable to exceedances in annual air pollutant concentrations above predefined thresholds; and we explored associations between air pollution and alternative outcomes of COVID-19 severity, namely hospitalizations or accesses to intensive care units. RESULTS: We analyzed 3,995,202 COVID-19 cases, which generated 124,346 deaths. Overall, case-fatality rates increased by 0.7% [95% confidence interval (CI): 0.5%, 0.9%], 0.3% (95% CI: 0.2%, 0.5%), and 0.6% (95% CI: 0.5%, 0.8%) per 1 μg/m³ increment in PM2.5, PM10, and NO2, respectively. Associations were higher among elderly subjects and during the first (February 2020-June 2020) and the third (December 2020-June 2021) pandemic waves. We estimated ~8%COVID-19 deaths were attributable to pollutant levels above the World Health Organization 2021 air quality guidelines. DISCUSSION: We found suggestive evidence of an association between long-term exposure to ambient air pollutants with mortality among 4 million COVID-19 cases in Italy. [ABSTRACT FROM AUTHOR]

In recent years, immediate breast reconstruction after mastectomy surgery has steadily increased in the treatment pathway of breast cancer (BC) patients due to its potential impact on both the morpho-functional and aesthetic type of the breast and the quality of life. Although recent studies have demonstrated how recent radiotherapy techniques have allowed a reduction of adverse events related to breast reconstruction, capsular contracture (CC) remains the main complication after post-mastectomy radio-therapy (PMRT). In this study, we evaluated the association of the occurrence of CC with some clinical, histological and therapeutic parameters related to BC patients. We firstly performed bivariate statistical tests and we then evaluated the prognostic predictive power of the collected data by using machine learning techniques. Out of a sample of 59 patients referred to our institute, 28 patients (i.e., 47%) showed contracture after PMRT. As a result, only estrogen receptor status (ER) and molecular subtypes were significantly associated with the occurrence of CC after PMRT. Different machine learning models were trained on a subset of clinical features selected by a feature importance approach. Experimental results have shown that collected features have a non-negligible predictive power. The extreme gradient boosting classifier achieved an area under the curve (AUC) value of 68% and accuracy, sensitivity, and specificity values of 68%, 64%, and 74%, respectively. Such a support tool, after further suitable optimization and validation, would allow clinicians to identify the best therapeutic strategy and reconstructive timing. [ABSTRACT FROM AUTHOR]

Afforestation is one of the most effective processes for removing carbon dioxide from the atmosphere and combating global warming. Landsat data and machine learning approaches can be used to map afforestation (i) indirectly, by constructing two maps of the same area over different periods and then predicting changes, or (ii) directly, by constructing a single map and analyzing observations of change in both the response and remotely sensed variables. Of crucial importance, no comprehensive comparisons of direct and indirect approaches for afforestation monitoring are known to have been conducted to date. Afforestation maps estimated through the analysis of remotely sensed data may serve as intermediate products for guiding the selection of samples and the production of statistics. In this and similar studies, a huge effort is dedicated to collecting validation data. In turn, those validation datasets have varying sampling intensities in different areas, which complicates their use for assessing the accuracies of new maps. As a result, the work done to collect data is often not sufficiently exploited, with some validation datasets being used just once. In this study, we addressed two main aims. First, we implemented a methodology to reuse validation data acquired via stratified sampling with strata constructed from remote sensing maps. Second, we used this method for acquiring data for comparing map accuracy estimates and the precision of estimates for direct and indirect approaches for country-wide mapping of afforestation that occurred in Italy between 1985 and 2019. To facilitate these comparisons, we used Landsat imagery, random forest classification, and Google Earth Engine. The herein-presented method produced different accuracy estimates with 95% confidence interval and for different map classes. Afforestation accuracies ranged between 53 ± 5.9% for the indirect map class inside the buffer—defined as a stratum within 120 m of the forest/non-forest mask boundaries—and 26 ± 3.4% for the direct map outside the buffer. The accuracy in non-afforestation map classes was much greater, ranging from 87 ± 1.9% for the indirect map inside the buffer to 99 ± 1.3% for the direct map outside the buffer. Additionally, overall accuracies (with 95% CI) were estimated with large precision for both direct and indirect maps (87 ± 1.3% and 89 ± 1.6%, respectively), confirming (i) the effectiveness of the method we introduced for reusing samples and (ii) the relevance of remotely sensed data and machine learning for monitoring afforestation. [ABSTRACT FROM AUTHOR]

The objective of this study was to determine the relationship between weather conditions and hospital admissions for cardiovascular diseases (CVD). The analysed data of CVD hospital admissions were part of the database of the Policlinico Giovanni XXIII of Bari (southern Italy) within a reference period of 4 years (2013–2016). CVD hospital admissions have been aggregated with daily meteorological recordings for the reference time interval. The decomposition of the time series allowed us to filter trend components; consequently, the non-linear exposure–response relationship between hospitalizations and meteo-climatic parameters was modelled with the application of a Distributed Lag Non-linear model (DLNM) without smoothing functions. The relevance of each meteorological variable in the simulation process was determined by means of machine learning feature importance technique. The study employed a Random Forest algorithm to identify the most representative features and their respective importance in predicting the phenomenon. As a result of the process, the mean temperature, maximum temperature, apparent temperature, and relative humidity have been determined to be the most suitable meteorological variables as the best variables for the process simulation. The study examined daily admissions to emergency rooms for cardiovascular diseases. Using a predictive analysis of the time series, an increase in the relative risk associated with colder temperatures was found between 8.3 °C and 10.3 °C. This increase occurred instantly and significantly 0–1 days after the event. The increase in hospitalizations for CVD has been shown to be correlated to high temperatures above 28.6 °C for lag day 5. [ABSTRACT FROM AUTHOR]

Afforestation processes, natural and anthropogenic, involve the conversion of other land uses to forest, and they represent one of the most important land use transformations, influencing numerous ecosystem services. Although remotely sensed data are commonly used to monitor forest disturbance, only a few reported studies have used these data to monitor afforestation. The objectives of this study were two fold: (1) to develop and illustrate a method that exploits the 1985–2019 Landsat time series for predicting afforestation areas at 30 m resolution at the national scale, and (2) to estimate afforestation areas statistically rigorously within Italian administrative regions and land elevation classes. We used a Landsat best-available-pixel time series (1985–2019) to calculate a set of temporal predictors that, together with the random forests prediction technique, facilitated construction of a map of afforested areas in Italy. Then, the map was used to guide selection of an estimation sample dataset which, after a complex photointerpretation phase, was used to estimate afforestation areas and associated confidence intervals. The classification approach achieved an accuracy of 87%. At the national level, the afforestation area between 1985 and 2019 covered 2.8 ± 0.2 million ha, corresponding to a potential C-sequestration of 200 million t. The administrative region with the largest afforested area was Sardinia, with 260,670 ± 58,522 ha, while the smallest area of 28,644 ± 12,114 ha was in Valle d'Aosta. Considering elevation classes of 200 m, the greatest afforestation area was between 400 and 600 m above sea level, where it was 549,497 ± 84,979 ha. Our results help to understand the afforestation process in Italy between 1985 and 2019 in relation to geographical location and altitude, and they could be the basis of further studies on the species composition of afforestation areas and land management conditions. [ABSTRACT FROM AUTHOR]

A personalized approach is strongly advocated for treatment selection in Multiple Sclerosis patients due to the high number of available drugs. Machine learning methods proved to be valuable tools in the context of precision medicine. In the present work, we applied machine learning methods to identify a combined clinical and genetic signature of response to fingolimod that could support the prediction of drug response. Two cohorts of fingolimod-treated patients from Italy and France were enrolled and divided into training, validation, and test set. Random forest training and robust feature selection were performed in the first two sets respectively, and the independent test set was used to evaluate model performance. A genetic-only model and a combined clinical–genetic model were obtained. Overall, 381 patients were classified according to the NEDA-3 criterion at 2 years; we identified a genetic model, including 123 SNPs, that was able to predict fingolimod response with an AUROC= 0.65 in the independent test set. When combining clinical data, the model accuracy increased to an AUROC= 0.71. Integrating clinical and genetic data by means of machine learning methods can help in the prediction of response to fingolimod, even though further studies are required to definitely extend this approach to clinical applications [ABSTRACT FROM AUTHOR]

Despite being a natural ecological process, wildfires are dramatic events that, accelerated by global change, could negatively affect ecosystem services depending on their severity level. However, because of data processing constraints, fire severity has been mostly neglected in risk analysis (especially at regional levels). Indeed, previous studies addressing fire severity focused mainly on analyzing single fire events, preventing the projection of the results over large areas. Although, building and projecting robust models of fire severity to integrate into risk analysis is of main importance to best anticipate decisions. Here, taking advantage of free data-processing platforms, such as Google Earth Engine, we use more than 1000 fire records from Western Italy and Southern France in the years 2004–2017, to assess the performance of random forest models predicting the relativized delta normalized burn ratio (rdNBR) used as proxy of fire severity. Furthermore, we explore the explanatory capacity and meaning of several variables related to topography, vegetation, and burning conditions. To show the potentialities of this approach for operational purposes, we projected the model for one of the regions (Sardinia) within the study area. Results showed that machine learning algorithms explain up to 75% of the variability in rdNBR, with variables related to vegetation amount and topography being the most important. These results highlight the potential usefulness of these tools for mapping fire severity in risk assessments. [ABSTRACT FROM AUTHOR]

Precise and accurate delineation of flooding areas with synthetic aperture radar (SAR) and multi-spectral (MS) data is challenging because flooded areas are inherently heterogeneous as emergent vegetation (EV) and turbid water (TW) are common. We addressed these challenges by developing and applying a new stepwise sequence of unsupervised and supervised classification methods using both SAR and MS data. The MS and SAR signatures of land and water targets in the study area were evaluated prior to the classification to identify the land and water classes that could be delineated. The delineation based on a simple thresholding method provided a satisfactory estimate of the total flooded area but did not perform well on heterogeneous surface water. To deal with the heterogeneity and fragmentation of water patches, a new unsupervised classification approach based on a combination of thresholding and segmentation (CThS) was developed. Since sandy areas and emergent vegetation could not be classified by the SAR-based unsupervised methods, supervised random forest (RF) classification was applied to a time series of SAR and co-event MS data, both combined and separated. The new stepwise approach was tested for determining the flood extent of two events in Italy. The results showed that all the classification methods applied to MS data outperformed the ones applied to SAR data. Although the supervised RF classification may lead to better accuracies, the CThS (unsupervised) method achieved precision and accuracy comparable to the RF, making it more appropriate for rapid flood mapping due to its ease of implementation. [ABSTRACT FROM AUTHOR]

The study of afforestation is crucial to monitor land transformations and represents a central topic in sustainable development procedures, in terms of climate change, ecosystem services monitoring, and planning policies activities. Although surveying afforestation is important, the assessment of the growing forests is difficult, since land cover has different durations depending on the species. In this context, remote sensing can be a valid instrument to evaluate the afforestation process. Nevertheless, while a vast literature on forest disturbance exists, only a few studies focus on afforestation and almost none directly exploits remote sensing data. This study aims to automatically classify non-forest, afforestation, and forest areas using remote sensing data. To this purpose, we constructed a reference dataset of 61 polygons that suffered a change from non-forest to forest in the period 1988-2020. The reference data were constructed with the Land Use Inventory of Italy and through photointerpretation of orthophotos (1988-2012, spatial resolution 50 × 50 cm) and very high-resolution images (2012-2020, spatial resolution 30 × 30 cm). Using Landsat Best Available Pixel composites time-series (1984-2020) we calculated 52 temporal predictors: four temporal metrics (median, standard deviation, Pearson's correlation coefficient R, and slope) calculated for 13 different bands (the six Landsat spectral bands, three Spectral Vegetation Indices, and four Tasseled Cap Indices). To verify the possibility of distinguishing afforestation from non-forest and forest, given the differences between them can be minimal, we tested four different models aiming at classifying the following categories: (i) non-forest/afforestation, (ii) afforestation/forest, (iii) non-forest/forest and (iv) non-forest/afforestation/forest. Temporal predictors were used with random forest which was calibrated using random search, validated using k-fold Cross-Validation Overall Accuracy (OAcv), and further using out-ofbag independent data (OAoob). Results illustrate that the distinction of afforestation/forest reaches the largest OAcv (87%), followed by non-forest/forest (83%), non-forest/afforestation (75%) and non-forest/afforestation/forest (72%). The different OA values confirm that the difference in photosynthetic activity between forest and afforestation can be analysed through remote sensing to distinguish them. Although remote sensing data are currently not exploited to monitor afforestation areas our results suggest it may be a valid support for country-level monitoring and reporting. [ABSTRACT FROM AUTHOR]

Miscanthus holds a great potential in the frame of the bioeconomy, and yield prediction can help improve Miscanthus' logistic supply chain. Breeding programs in several countries are attempting to produce high-yielding Miscanthus hybrids better adapted to different climates and end-uses. Multispectral images acquired from unmanned aerial vehicles (UAVs) in Italy and in the UK in 2021 and 2022 were used to investigate the feasibility of high-throughput phenotyping (HTP) of novel Miscanthus hybrids for yield prediction and crop traits estimation. An intercalibration procedure was performed using simulated data from the PROSAIL model to link vegetation indices (VIs) derived from two different multispectral sensors. The random forest algorithm estimated with good accuracy yield traits (light interception, plant height, green leaf biomass, and standing biomass) using 15 VIs time series, and predicted yield using peak descriptors derived from these VIs time series with root mean square error of 2.3 Mg DM ha−1. The study demonstrates the potential of UAVs' multispectral images in HTP applications and in yield prediction, providing important information needed to increase sustainable biomass production. [ABSTRACT FROM AUTHOR]

In the domain of landslide risk science, landslide susceptibility mapping (LSM) is very important, as it helps spatially identify potential landslide-prone regions. This study used a statistical ensemble model (frequency ratio and evidence belief function) and two machine learning (ML) models (random forest and XGBoost; eXtreme Gradient Boosting) for LSM in the province of Belluno (region of Veneto, northeastern Italy). The study investigated the importance of the conditioning factors in predicting landslide occurrences using the mentioned models. In this paper, we evaluated the importance of the conditioning factors in the overall prediction capabilities of the statistical and ML algorithms. By the trial-and-error method, we eliminated the least "important" features by using a common threshold of 0.30 for statistical and 0.03 for ML algorithms. Conclusively, we found that removing the least important features does not impact the overall accuracy of LSM for all three models. Based on the results of our study, the most commonly available features, for example, the topographic features, contributes to comparable results after removing the least important ones, namely the aspect plan and profile curvature, topographic wetness index (TWI), topographic roughness index (TRI), and normalized difference vegetation index (NDVI) in the case of the statistical model and the plan and profile curvature, TWI, and topographic position index (TPI) for ML algorithms. This confirms that the requirement for the important conditioning factor maps can be assessed based on the physiography of the region. [ABSTRACT FROM AUTHOR]

Habitat models rarely consider macroinvertebrate communities as ecological targets in rivers. Available approaches mainly focus on single macroinvertebrate species, not addressing the ecological needs and functionality of the whole community. This research aimed at providing an approach to model the habitat of the macroinvertebrate communities. The study was carried out in three rivers, located in Italy and characterized by a braiding morphology, gravel riverbeds, and low flows during the summer period. The approach is based on the recently developed Flow-T index, together with a Random Forest (RF) regression, which is employed to apply the Flow-T index at the mesohabitat scale. Using different datasets gathered from field data collection and 2D hydrodynamic simulations, the model was calibrated in the Trebbia River (2019 field campaign) and validated in the Trebbia, Taro, and Enza rivers (2020 field campaign). The RF model selected 12 mesohabitat descriptors as important for the macroinvertebrate community. These descriptors belong to different frequency classes of water depth, flow velocity, substrate grain size, and connectivity to the main river channel. The cross-validation R2 coefficient (R2 cv) of the training dataset was 0.71, whereas the R2 coefficient (R2 test) for the validation dataset was 0.63. The agreement between the simulated results and the experimental data shows sufficient accuracy and reliability. The outcomes of the study reveal that the model can identify the ecological response of the macroinvertebrate community to possible flow regime alterations and river morphological modifications. Lastly, the proposed approach allowed to extend the MesoHABSIM methodology, widely used for the fish habitat assessment, to a different ecological target community. Further applications of the approach can be related to ecological flows design in both perennial and non-perennial rivers, including river reaches in which fish fauna is absent. [Display omitted] • A meso-scale habitat model for the macroinvertebrate community is developed. • Flow velocity preferences are used to describe the community assemblage and distribution. • Random Forest is applied to assess the ecological response to flow variation. • The free online service SimStream-Web is available to perform calculations. • Meso-Scale habitat model (MesoHABSIM) is extended to the macroinvertebrate community. [ABSTRACT FROM AUTHOR]

Modern farming causes a decline in the recycling of the soil's inorganic matter due to losses by leaching, runoff, or infiltration into the groundwater. The Soil System Budget approach was applied to evaluate the net N budget at the catchment and sub-catchment levels of the Tiber River (central Italy) in order to establish the causes for different N budgets among the sub-catchments. Statistical Entropy Analysis (SEA) was used to evaluate the N efficiency of the Tiber River and its sub-catchments, providing information on the dispersion of different N forms in the environment. The total N inputs exceeded the total outputs, showing a low N retention (15.8%) at the catchment level, although some sub-catchments showed higher N retention values. The Utilized Agricultural Area was important in the determination of the N balance, as it was linked to zoo- and agricultural activities, although the Random Forest analysis showed that the importance ranking changed with the land use. The low N retention of the Tiber catchment was due to the soil characteristics (Cambisols and Leptosols), loads from atmospheric deposition, biological fixation, and the livestock industry. The SEA simulations showed a reduction of the N released into the atmosphere and groundwater compartments from 34% to 6% through a reduction of the N loads by 50%. [ABSTRACT FROM AUTHOR]

This paper explores the relationship between received inheritances and the distribution of wealth (financial, non-financial and total) in four developed countries: the United States, Canada, Italy and Spain. We follow the inequality of opportunity (IOp) literature and − considering inheritances as the only circumstance− we show that traditional IOp approaches can lead to non-robust and arbitrary measures of IOp depending on discretionary cut-off choices of a continuous circumstance such as inheritances. To overcome this limitation, we apply Machine Learning methods ('random forest' algorithm) to optimize the choice of cut-offs and we find that IOp explains over 60% of wealth inequality in the US and Spain (using the Gini coefficient), and more than 40% in Italy and Canada. Including parental education as an additional circumstance −available for the US and Italy− we find that inheritances are still the main contributor. Finally, using the S-Gini index with different parameters to weight different parts of the distribution, we find that the effect of inheritances is more prominent at the middle of the wealth distribution, while parental education is more important for the asset-poor. [ABSTRACT FROM AUTHOR]

In the domain of landslide risk science, landslide susceptibility mapping (LSM) is very important as it helps spatially identify potential landslide-prone regions. This study used a statistical ensemble model (Frequency Ratio and Evidence Belief Function) and two machine learning (ML) models (Random Forest and XG-Boost) for LSM in the Belluno province (Veneto Region, NE Italy). The study investigated the importance of the conditioning factors in predicting landslide occurrences using the mentioned models. In this paper, we evaluated the importance of the conditioning factors (features) in the overall prediction capabilities of the statistical and ML algorithms. By the trial-and-error method, we eliminated the least "important" features by using a common threshold. Conclusively, we found that removing the least "important" features does not impact the overall accuracy of the LSM for all three models. Based on the results of our study, the most commonly available features, for example, the topographic features, contributes to comparable results after removing the least "important" ones. This confirms that the requirement for the important factor maps can be assessed based on the physiography of the region. Based on the analysis of the three models, it was observed that most commonly available feature data can be useful for carrying out LSM at regional scale, eliminating the least available ones in most of the use cases due to data scarcity. Identifying LSMs at regional scale has implications for understanding landslide phenomena in the region and post-event relief measures, planning disaster risk reduction, mitigation, and evaluating potentially affected areas. [ABSTRACT FROM AUTHOR]

This study evaluated the effectiveness of various remote sensing (RS) data (Sentinel-1, Sentinel-2, and Landsat 8) in the early recognition of irrigated areas in a densely cultivated area of central Italy. The study was based on crop data collected on more than 2000 plots in 2016 and 2017, characterized by quite different climatic conditions. The different RS data sources were used both alone and combined and with precipitation to define corresponding random forest (RF) classifiers whose overall accuracy (OA) was assessed by gradually increasing the number of available features from the beginning of the irrigation season. All tested RF classifiers reach stable OAs (OA 0.9) after 7-8 weeks from the start of the irrigation season. The performance of the radar indexes slightly improves when used in combination with precipitation data, but three weeks of features are required to obtain OA above 80%. The optical indices alone (Sentinel-2 and Landsat 8) reach OA ?85% in the first week of observation. However, they are ineffective in cloudy conditions or when rainfed and irrigated fields have similar vigour. The most effective and robust indices are those based on combined sources (radar, optical, and meteorological), allowing OAs of about 92% and 96% at the beginning and in the middle of the irrigation season, respectively. [ABSTRACT FROM AUTHOR]

Background: During the Neolithic expansion, cattle accompanied humans and spread from their domestication centres to colonize the ancient world. In addition, European cattle occasionally intermingled with both indicine cattle and local aurochs resulting in an exclusive pattern of genetic diversity. Among the most ancient European cattle are breeds that belong to the so-called Podolian trunk, the history of which is still not well established. Here, we used genome-wide single nucleotide polymorphism (SNP) data on 806 individuals belonging to 36 breeds to reconstruct the origin and diversification of Podolian cattle and to provide a reliable scenario of the European colonization, through an approximate Bayesian computation random forest (ABC-RF) approach. Results: Our results indicate that European Podolian cattle display higher values of genetic diversity indices than both African taurine and Asian indicine breeds. Clustering analyses show that Podolian breeds share close genomic relationships, which suggests a likely common genetic ancestry. Among the simulated and tested scenarios of the colonization of Europe from taurine cattle, the greatest support was obtained for the model assuming at least two waves of diffusion. Time estimates are in line with an early migration from the domestication centre of non-Podolian taurine breeds followed by a secondary migration of Podolian breeds. The best fitting model also suggests that the Italian Podolian breeds are the result of admixture between different genomic pools. Conclusions: This comprehensive dataset that includes most of the autochthonous cattle breeds belonging to the so-called Podolian trunk allowed us not only to shed light onto the origin and diversification of this group of cattle, but also to gain new insights into the diffusion of European cattle. The most well-supported scenario of colonization points to two main waves of migrations: with one that occurred alongside with the Neolithic human expansion and gave rise to the non-Podolian taurine breeds, and a more recent one that favoured the diffusion of European Podolian. In this process, we highlight the importance of both the Mediterranean and Danube routes in promoting European cattle colonization. Moreover, we identified admixture as a driver of diversification in Italy, which could represent a melting pot for Podolian cattle. [ABSTRACT FROM AUTHOR]

Land Cover (LC) plays a key role in many disciplines and its classification from optical imagery is one of the prevalent applications of remote sensing. Besides years of researches and innovation on LC, the classification of some areas of the World is still challenging due to environmental and climatic constraints, such as the one of the mountainous chains. In this contribution, we propose a specific methodology for the classification of the Land Cover in mountainous areas using Sentinel 2, 1C-level imagery. The classification considers some specific high-altitude mountainous classes: clustered bare soils that are particularly prone to erosion, glaciers, and solid-rocky areas. It consists of a pixel-based multi-epochs classification using random forest algorithm performed in Google Earth Engine (GEE). The study area is located in the western Alps between Italy and France and the analyzed dataset refers to 2017–2019 imagery captured in the summertime only. The dataset was pre-processed, enriched of derivative features (radiometric, histogram-based and textural). A workflow for the reduction of the computational effort for the classification, which includes correlation and importance analysis of input features, was developed. Each image of the dataset was separately classified using random forest classification algorithm and then aggregated each other by the most frequent pixel value. The results show the high impact of textural features in the separation of the mountainous-specific classes the overall accuracy of the final classification achieves 0.945. [ABSTRACT FROM AUTHOR]

The aim of the study was to measure the impact of antibiotic exposure on the acquisition of colonization with extended-spectrum β-lactamase-producing Gram-negative bacteria (ESBL-GNB) accounting for individual- and group-level confounding using machine-learning methods. Patients hospitalized between September 2010 and June 2013 at six medical and six surgical wards in Italy, Serbia and Romania were screened for ESBL-GNB at hospital admission, discharge, antibiotic start, and after 3, 7, 15 and 30 days. Primary outcomes were the incidence rate and predictive factors of new ESBL-GNB colonization. Random forest algorithm was used to rank antibiotics according to the risk of selection of ESBL-GNB colonization in patients not colonized before starting antibiotics. We screened 10 034 patients collecting 28 322 rectal swab samples. New ESBL-GNB colonization incidence with and without antibiotic treatment was 22/1000 and 9/1000 exposure-days, respectively. In the adjusted regression analyses, antibiotic exposure (hazard ratio (HR) 2.38; 95% CI 1.29–4.40), age 60–69 years (HR 1.19; 95% CI 1.05–1.34), and spring season (HR 1.25; 95% CI 1.14–1.38) were independently associated with new colonization. Monotherapy ranked higher als combination therapy in promoting ESBL-GNB colonization. Among monotherapy, cephalosporins ranked first followed by tetracycline (second), macrolide (fourth) and cotrimoxazole (seventh). Overall the ranking of cephalosporins was lower when used in combination. Among combinations not including cephalosporins, quinolones plus carbapenems ranked highest (eighth). Among sequential therapies, quinolones ranked highest (tenth) when prescribed within 30 days of therapy with cephalosporins. Impact of antibiotics on selecting ESBL-GNB at intestinal level varies if used in monotherapy or combination and according to previous antibiotic exposure. These finding should be explored in future clinical trials on antibiotic stewardship interventions. NCT01208519. [ABSTRACT FROM AUTHOR]

Two main approaches are commonly used to map fire-prone areas when designing firefighting and prevention campaigns: fire spread simulators and machine learning models. Despite they used mainly the same environmental variables, they differ in handling them. Thus, it is worth assessing differences in results and interpretations for supporting reliable decision-making process. Burn probabilities (BP) were calculated in Southern Italy using FlamMap and the Random Forest algorithm. Results showed contrasting spatial patterns, with Random Forest projecting more smoothed results than Flammap, which showed medium-high BP values only across some locations. In addition, BP from FlamMap and Random Forest differ across fuel types and environmental conditions. Results suggest that decisions based on fire simulators might be more tightly linked with actions preventing fire spread. In contrast, those based on machine learning might be more linked with fire occurrence elements not necessarily related to spreading, e.g., socioeconomic causes. • Burn probability differs between fire simulators and machine learning models. • The relationships between environmental factors and BP change across approaches. • Results interpretation depend on the approach used and it is mandatory. [ABSTRACT FROM AUTHOR]

[Display omitted] • We quantify the impact of desert dust on particulate matter air quality over Italy. • We derive a multiannual dataset of desert dust-PM10 values resolved by site and day. • In Italy desert dust contributes to exceed PM10 limit values fixed by EU and WHO. • Random forest modelling is used to obtain a spatially continuous dust-PM10 field. • Geostatistical model outcomes will serve as a basis to study dust impact on health. Desert dust storms pose real threats to air quality and health of millions of people in source regions, with associated impacts extending to downwind areas. Europe (EU) is frequently affected by atmospheric transport of desert dust from the Northern Africa and Middle East drylands. This investigation aims at quantifying the role of desert dust transport events on air quality (AQ) over Italy, which is among the EU countries most impacted by this phenomenon. We focus on the particulate matter (PM) metrics regulated by the EU AQ Directive. In particular, we use multiannual (2006–2012) PM10 records collected in hundreds monitoring sites within the national AQ network to quantify daily and annual contributions of dust during transport episodes. The methodology followed was built on specific European Commission guidelines released to evaluate the natural contributions to the measured PM-levels, and was partially modified, tested and adapted to the Italian case in a previous study. Overall, we show that impact of dust on the yearly average PM10 has a clear latitudinal gradient (from less than 1 to greater than 10 µg/m3 going from north to south Italy), this feature being mainly driven by an increased number of dust episodes per year with decreasing latitude. Conversely, the daily-average dust-PM10 (≅12 µg/m3) is more homogenous over the country and shown to be mainly influenced by the site type, with enhanced values in more urbanized locations. This study also combines the PM10 measurements-approach with geostatistical modelling. In particular, exploiting the dust-PM10 dataset obtained at site- and daily-resolution over Italy, a geostatistical, random-forest model was set up to derive a daily, spatially-continuous field of desert-dust PM10 at high (1-km) resolution. This finely resolved information represent the basis for a follow up investigation of both acute and chronic health effects of desert dust over Italy, stemming from daily and annual exposures, respectively. [ABSTRACT FROM AUTHOR]

With the general objective of producing a 2018–2020 Land Use/Land Cover (LULC) map of the Maiella National Park (central Italy), useful for a future long-term LULC change analysis, this research aimed to develop a Landsat 8 (L8) data composition and classification process using Google Earth Engine (GEE). In this process, we compared two pixel-based (PB) and two object-based (OB) approaches, assessing the advantages of integrating the textural information in the PB approach. Moreover, we tested the possibility of using the L8 panchromatic band to improve the segmentation step and the object's textural analysis of the OB approach and produce a 15-m resolution LULC map. After selecting the best time window of the year to compose the base data cube, we applied a cloud-filtering and a topography-correction process on the 32 available L8 surface reflectance images. On this basis, we calculated five spectral indices, some of them on an interannual basis, to account for vegetation seasonality. We added an elevation, an aspect, a slope layer, and the 2018 CORINE Land Cover classification layer to improve the available information. We applied the Gray-Level Co-Occurrence Matrix (GLCM) algorithm to calculate the image's textural information and, in the OB approaches, the Simple Non-Iterative Clustering (SNIC) algorithm for the image segmentation step. We performed an initial RF optimization process finding the optimal number of decision trees through out-of-bag error analysis. We randomly distributed 1200 ground truth points and used 70% to train the RF classifier and 30% for the validation phase. This subdivision was randomly and recursively redefined to evaluate the performance of the tested approaches more robustly. The OB approaches performed better than the PB ones when using the 15 m L8 panchromatic band, while the addition of textural information did not improve the PB approach. Using the panchromatic band within an OB approach, we produced a detailed, 15-m resolution LULC map of the study area. [ABSTRACT FROM AUTHOR]

The present work aims to identify the predictors of COVID-19 in-hospital mortality testing a set of Machine Learning Techniques (MLTs), comparing their ability to predict the outcome of interest. The model with the best performance will be used to identify in-hospital mortality predictors and to build an in-hospital mortality prediction tool. The study involved patients with COVID-19, proved by PCR test, admitted to the "Ospedali Riuniti Padova Sud" COVID-19 referral center in the Veneto region, Italy. The algorithms considered were the Recursive Partition Tree (RPART), the Support Vector Machine (SVM), the Gradient Boosting Machine (GBM), and Random Forest. The resampled performances were reported for each MLT, considering the sensitivity, specificity, and the Receiving Operative Characteristic (ROC) curve measures. The study enrolled 341 patients. The median age was 74 years, and the male gender was the most prevalent. The Random Forest algorithm outperformed the other MLTs in predicting in-hospital mortality, with a ROC of 0.84 (95% C.I. 0.78–0.9). Age, together with vital signs (oxygen saturation and the quick SOFA) and lab parameters (creatinine, AST, lymphocytes, platelets, and hemoglobin), were found to be the strongest predictors of in-hospital mortality. The present work provides insights for the prediction of in-hospital mortality of COVID-19 patients using a machine-learning algorithm. [ABSTRACT FROM AUTHOR]

Riparian habitats provide a series of ecological services vital for the balance of the environment, and are niches and resources for a wide variety of species. Monitoring riparian environments at the intra-habitat level is crucial for assessing and preserving their conservation status, although it is challenging due to their landscape complexity. Unmanned aerial vehicles (UAV) and multi-spectral optical sensors can be used for very high resolution (VHR) monitoring in terms of spectral, spatial, and temporal resolutions. In this contribution, the vegetation species of the riparian habitat (91E0*, 3240 of Natura 2000 network) of North-West Italy were mapped at individual tree (ITD) level using machine learning and a multi-temporal phenology-based approach. Three UAV flights were conducted at the phenological-relevant time of the year (epochs). The data were analyzed using a structure from motion (SfM) approach. The resulting orthomosaics were segmented and classified using a random forest (RF) algorithm. The training dataset was composed of field-collected data, and was oversampled to reduce the effects of unbalancing and size. Three-hundred features were computed considering spectral, textural, and geometric information. Finally, the RF model was cross-validated (leave-one-out). This model was applied to eight scenarios that differed in temporal resolution to assess the role of multi-temporality over the UAV's VHR optical data. Results showed better performances in multi-epoch phenology-based classification than single-epochs ones, with 0.71 overall accuracy compared to 0.61. Some classes, such as Pinus sylvestris and Betula pendula, are remarkably influenced by the phenology-based multi-temporality: the F1-score increased by 0.3 points by considering three epochs instead of two. [ABSTRACT FROM AUTHOR]

Simple Summary: Sustainability is a necessary goal for animal-derived products due to the mounting pressure on the livestock sector to meet the growing demand of an increasing population with rising incomes and the need to reduce the exploitation of resources and environmental impact, while safeguarding animal welfare. We found that by considering a precision livestock farming approach to feeding, advanced numerical methods could represent a reliable and viable tool for the evaluation of future productive scenarios of dairy cows in the presence of changing climate conditions. We believe that the model proposed here could help to develop and improve decision support for farmers to increase both milk yield and animal welfare and, on the other hand, to reduce the resources needed, hence increasing sustainability of the dairy sector. Precision Livestock Farming (PLF) relies on several technological approaches to acquire, in the most efficient way, precise and real-time data concerning production and welfare of individual animals. In this regard, in the dairy sector, PLF devices are being increasingly adopted, automatic milking systems (AMSs) are becoming increasingly widespread, and monitoring systems for animals and environmental conditions are becoming common tools in herd management. As a consequence, a great amount of daily recorded data concerning individual animals are available for the farmers and they could be used effectively for the calibration of numerical models to be used for the prediction of future animal production trends. On the other hand, the machine learning approaches in PLF are nowadays considered an extremely promising solution in the research field of livestock farms and the application of these techniques in the dairy cattle farming would increase sustainability and efficiency of the sector. The study aims to define, train, and test a model developed through machine learning techniques, adopting a Random Forest algorithm, having the main goal to assess the trend in daily milk yield of a single cow in relation to environmental conditions. The model has been calibrated and tested on the data collected on 91 lactating cows of a dairy farm, located in northern Italy, and equipped with an AMS and thermo-hygrometric sensors during the years 2016–2017. In the statistical model, having seven predictor features, the daily milk yield is evaluated as a function of the position of the day in the lactation curve and the indoor barn conditions expressed in terms of daily average of the temperature-humidity index (THI) in the same day and its value in each of the five previous days. In this way, extreme hot conditions inducing heat stress effects can be considered in the yield predictions by the model. The average relative prediction error of the milk yield of each cow is about 18% of daily production, and only 2% of the total milk production. [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]

The introduction of Douglas-fir [Pseudotsuga menziesii (Mirb.) Franco] in Europe has been one of the most important and extensive silvicultural experiments since the 1850s. This success was mainly supported by the species' wide genome and phenotypic plasticity even if the genetic origin of seeds used for plantations is nowadays often unknown. This is especially true for all the stands planted before the IUFRO experimentation in the 1960s. In this paper, a methodology to estimate the Douglas-fir provenances currently growing in Italy is proposed. The raw data from the last Italian National Forest Inventory were combined with literature information to obtain the current spatial distribution of the species in the country representing its successful introduction. Afterwards, a random forest classification model was run using downscaled climatic data as predictors and the classification scheme adopted in previous research studies in the Pacific North West of America. The analysis highlighted good matching between the native and the introduction range in Italy. Coastal provenances from British Columbia and the dry coast of Washington were detected as the most likely seed sources, covering 63.4% and 33.8% of the current distribution of the species in the country, respectively. Interior provenances and those from the dry coast of Oregon were also represented but limited to very few cases. The extension of the model on future scenarios predicted a gradual shift in suitable provenances with the dry coast of Oregon in the mid-term (2050s) and afterwards California (2080s) being highlighted as possible new seed sources. However, only further analysis with genetic markers and molecular methods will be able to confirm the proposed scenarios. A validation of the genotypes currently available in Italy will be mandatory as well as their regeneration processes (i.e., adaptation), which may also diverge from those occurring in the native range due to a different environmental pressure. This new information will also add important knowledge, allowing a refinement of the proposed modeling framework for a better support for forest managers. [ABSTRACT FROM AUTHOR]

Farmers that intend to access Common Agricultural Policy (CAP) contributions must submit an application to the territorially competent Paying Agencies (PA). Agencies are called to verify consistency of CAP contributions requirements through ground campaigns. Recently, EU regulation (N. 746/2018) proposed an alternative methodology to control CAP applications based on Earth Observation data. Accordingly, this work was aimed at designing and implementing a prototype of service based on Copernicus Sentinel-2 (S2) data for the classification of soybean, corn, wheat, rice, and meadow crops. The approach relies on the classification of S2 NDVI time-series (TS) by "user-friendly" supervised classification algorithms: Minimum Distance (MD) and Random Forest (RF). The study area was located in the Vercelli province (NW Italy), which represents a strategic agricultural area in the Piemonte region. Crop classes separability proved to be a key factor during the classification process. Confusion matrices were generated with respect to ground checks (GCs); they showed a high Overall Accuracy (>80%) for both MD and RF approaches. With respect to MD and RF, a new raster layer was generated (hereinafter called Controls Map layer), mapping four levels of classification occurrences, useful for administrative procedures required by PA. The Control Map layer highlighted that only the eight percent of CAP 2019 applications appeared to be critical in terms of consistency between farmers' declarations and classification results. Only for these ones, a GC was warmly suggested, while the 12% must be desirable and the 80% was not required. This information alone suggested that the proposed methodology is able to optimize GCs, making possible to focus ground checks on a limited number of fields, thus determining an economic saving for PA and/or a more effective strategy of controls. [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]

Google Earth Engine (GEE) is a versatile cloud platform in which pixel-based (PB) and object-oriented (OO) Land Use–Land Cover (LULC) classification approaches can be implemented, thanks to the availability of the many state-of-art functions comprising various Machine Learning (ML) algorithms. OO approaches, including both object segmentation and object textural analysis, are still not common in the GEE environment, probably due to the difficulties existing in concatenating the proper functions, and in tuning the various parameters to overcome the GEE computational limits. In this context, this work is aimed at developing and testing an OO classification approach combining the Simple Non-Iterative Clustering (SNIC) algorithm to identify spatial clusters, the Gray-Level Co-occurrence Matrix (GLCM) to calculate cluster textural indices, and two ML algorithms (Random Forest (RF) or Support Vector Machine (SVM)) to perform the final classification. A Principal Components Analysis (PCA) is applied to the main seven GLCM indices to synthesize in one band the textural information used for the OO classification. The proposed approach is implemented in a user-friendly, freely available GEE code useful to perform the OO classification, tuning various parameters (e.g., choose the input bands, select the classification algorithm, test various segmentation scales) and compare it with a PB approach. The accuracy of OO and PB classifications can be assessed both visually and through two confusion matrices that can be used to calculate the relevant statistics (producer's, user's, overall accuracy (OA)). The proposed methodology was broadly tested in a 154 km2 study area, located in the Lake Trasimeno area (central Italy), using Landsat 8 (L8), Sentinel 2 (S2), and PlanetScope (PS) data. The area was selected considering its complex LULC mosaic mainly composed of artificial surfaces, annual and permanent crops, small lakes, and wooded areas. In the study area, the various tests produced interesting results on the different datasets (OA: PB RF (L8 = 72.7%, S2 = 82%, PS = 74.2), PB SVM (L8 = 79.1%, S2 = 80.2%, PS = 74.8%), OO RF (L8 = 64%, S2 = 89.3%, PS = 77.9), OO SVM (L8 = 70.4, S2 = 86.9%, PS = 73.9)). The broad code application demonstrated very good reliability of the whole process, even though the OO classification process resulted, sometimes, too demanding on higher resolution data, considering the available computational GEE resources. [ABSTRACT FROM AUTHOR]

In this research, we develop ordinal decision-tree-based ensemble approaches in which an objective-based information gain measure is used to select the classifying attributes. We demonstrate the applicability of the approaches using AdaBoost and random forest algorithms for the task of classifying the regional daily growth factor of the spread of an epidemic based on a variety of explanatory factors. In such an application, some of the potential classification errors could have critical consequences. The classification tool will enable the spread of the epidemic to be tracked and controlled by yielding insights regarding the relationship between local containment measures and the daily growth factor. In order to benefit maximally from a variety of ordinal and non-ordinal algorithms, we also propose an ensemble majority voting approach to combine different algorithms into one model, thereby leveraging the strengths of each algorithm. We perform experiments in which the task is to classify the daily COVID-19 growth rate factor based on environmental factors and containment measures for 19 regions of Italy. We demonstrate that the ordinal algorithms outperform their non-ordinal counterparts with improvements in the range of 6–25% for a variety of common performance indices. The majority voting approach that combines ordinal and non-ordinal models yields a further improvement of between 3% and 10%. [ABSTRACT FROM AUTHOR]

Coastal dunes are found at the boundary between continents and seas representing unique transitional mosaics hosting highly dynamic habitats undergoing substantial seasonal changes. Here, we implemented a land cover classification approach specifically designed for coastal landscapes accounting for the within-year temporal variability of the main components of the coastal mosaic: vegetation, bare surfaces and water surfaces. Based on monthly Sentinel-2 satellite images of the year 2019, we used hierarchical clustering and a Random Forest model to produce an unsupervised land cover map of coastal dunes in a representative site of the Adriatic coast (central Italy). As classification variables, we used the within-year diversity computed through Rao's Q index, along with three spectral indices describing the main components of the coastal mosaic (i.e., Modified Soil-adjusted Vegetation Index 2—MSAVI2, Normalized Difference Water Index 2—NDWI2 and Brightness Index 2—BI2). We identified seven land cover classes with high levels of accuracy, highlighting different covariates as the most important in differentiating them. The proposed framework proved effective in mapping a highly seasonal and heterogeneous landscape such as that of coastal dunes, highlighting Rao's Q index as a sound base for natural cover monitoring and mapping. The applicability of the proposed framework on updated satellite images emphasizes the procedure as a reliable and replicable tool for coastal ecosystems monitoring. [ABSTRACT FROM AUTHOR]