Luppichini, Marco
11 results
Filters
Settings
The search returned 11 results
Now showing 1 - 10 of 11
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: Open Access , CleverRiver: an open source and free Google Colab toolkit for deep-learning river-flow models
In a period in which climate change is signifcantly varying rainfall regimes and their intensity all over the world, river-fow prediction is a major concern of geosciences. In recent years there has been an increase in the use of deep-learning models for river-fow prediction. However, in this feld we can observe two main issues: i) many case studies use similar (or the same) strategies without sharing the codes, and ii) the application of these techniques requires good computer knowledge. This work proposes to employ a Google Colab notebook called CleverRiver, which allows the application of deep-learning for river-fow predictions. CleverRiver is a dynamic software that can be upgraded and modifed not only by the authors but also by the users. The main advantages of CleverRiver are the following: the software is not limited by the client hardware, operating systems, etc.; the code is open-source; the toolkit is integrated with user-friendly interfaces; updated releases with new architectures, data management, and model parameters will be progressively uploaded. The software consists of three sections: the frst one enables to train the models by means of some architectures, parameters, and data; the second section allows to create predictions by using the trained models; the third section allows to send feedback and to share experiences with the authors, providing a fux of precious information able to improve scientifc research.59 121 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: Open Access , Beyond one-way determinism: San Frediano's miracle and climate change in Central and Northern Italy in late antiquity
Integrating palaeoclimatological proxies and historical records, which is necessary to achieve a more complete understanding of climate impacts on past societies, is a challenging task, often leading to unsatisfactory and even contradictory conclusions. This has until recently been the case for Italy, the heart of the Roman Empire, during the transition between Antiquity and the Middle Ages. In this paper, we present new high-resolution speleothem data from the Apuan Alps (Central Italy). The data document a period of very wet conditions in the sixth c. AD, probably related to synoptic atmospheric conditions similar to a negative phase of the North Atlantic Oscillation. For this century, there also exist a significant number of historical records of extreme hydroclimatic events, previously discarded as anecdotal. We show that this varied evidence reflects the increased frequency of floods and extreme rainfall events in Central and Northern Italy at the time. Moreover, we also show that these unusual hydroclimatic conditions overlapped with the increased presence of "water miracles" in Italian hagiographical accounts and social imagination. The miracles, performed by local Church leaders, strengthened the already growing authority of holy bishops and monks in Italian society during the crucial centuries that followed the "Fall of the Roman Empire". Thus, the combination of natural and historical data allows us to show the degree to which the impact of climate variability on historical societies is determined not by the nature of the climatic phenomena per se, but by the culture and the structure of the society that experienced it.142 35 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: Open Access , Insight into summer drought in southern Italy: palaeohydrological evolution of Lake Pergusa (Sicily) in the last 6700 years
The Sicily region (central Mediterranean) is at high risk of drying and desertification caused by current warming and land management. The aim of this study is to place current climatic changes within the past trajectories and natural climatic variability of the Holocene. For this we re‐examine a sediment core retrieved at Lake Pergusa covering the last ca. 6700 years. A multiproxy investigation, and in particular the oxygen isotope composition of lacustrine carbonate (δ18Oc), allowed us to reconstruct decadal‐ to centennial‐scale hydrological changes. The wettest period occurred between ca. 6700 and 6000 cal a BP. The δ18Oc record indicates a new period of wetter conditions between ca. 3700 and 2400 cal a BP. In particular, a δ18Oc minimum between 2850 and 2450 cal a BP overlaps with the period of the ‘Great Solar Minimum’ and corresponds to a dramatic reduction of arboreal pollen (AP%) and to an increase in synanthropic pollen, marking the onset of Greek colonization in the region. The longest driest interval corresponds to the Medieval Climate Anomaly, whereas the highest δ18Oc values are recorded in the last 150 years. The trend of the last 3000 years suggests that, considering future climate projections, the area will experience unprecedented drying exacerbated by human impact.53 39 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: Open Access , Deep learning models to predict flood events in fast-flowing watersheds
This study aims to explore the reliability of flood warning forecasts based on deep learning models, in particular Long-Short Term Memory (LSTM) architecture. We also wish to verify the applicability of flood event predictions for a river with flood events lasting only a few hours, with the aid of hydrometric control stations. This methodology allows for the creation of a system able to identify flood events with acceptable errors within several hours' notice. In terms of errors, the results obtained in this study can be compared to those obtained by using physics-based models for the same study area. These kinds of models use few types of data, unlike physical models that require the estimation of several parameters. However, the deep learning models are data-driven and for this reason they can influence the results obtained. Therefore, we tested the stability of the models by simulating the missing or wrong input data of the model, and this allowed us to achieve excellent results. Indeed, the models were stable even if several data were missing. This method makes it possible to lay the foundations for the future application of these techniques when there is an absence of geological-hydrogeological information preventing physical modeling of the run-off process or in cases of relatively small basins, where the complex system and the unsatisfactory modeling of the phenomenon do not allow a correct application of physical-based models. The forecast of flood events is fundamental for correct and adequate territory management, in particular when significant climatic changes occur. The study area is that of the Arno River (in Tuscany, Italy), which crosses some of the most important cities of central Italy, in terms of population, cultural heritage, and socio-economic activities.38 355 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: Open Access , High-resolution spatial analysis of temperature influence on the rainfall regime and extreme precipitation events in north-central Italy
In the last few years, several works have analyzed rainfall regime changes with the increase of temperature as a result of global warming. These changes, documented mainly in northern Europe, still need to be clarified in the Mediterranean area. Many studies have identified sometimes contradictory trends according to the type of data used, the methodology, and the daily or subdaily types of events. Therefore, an in-depth investigation of the Mediterranean area is required for the definition of more certain future scenarios. In this study, we examined a very large database including >1000 raingauges and thermometers in northern and central Italy to analyze the relationship between temperature and rainfall using the relation Clausius-Clapeyron. Furthermore, we analyzed the relationship between temperature and extreme precipitation events (EPEs, defined as the events higher than the 95th percentile) calculating the temperature anomalies occurred during these events. This large database covers a low rainfall accumulation period (RAP) that allowed us to study the relationship between temperature and rainfall and to distinguish rapid from long events related to rainfall intensity. The results show different relationships between rainfall and temperature in relation to seasons, RAPs, rainfall intensity, and geographical factors. The high spatial density of the database made it possible to identify spatial clusters with homogenous characteristics mainly influenced by geographical factors. With an increase in temperature, the wet season is characterized by a general increase in rainfall with a higher surge for intense and fast events. Instead, the dry season shows a general rainfall decrease for less intense and longer events, but an increase in rapid and more intensive rainfall events. This outcome has further implications involving a future decrease in water availability and an increase of the EPEs, causing an extremization of the climate during the dry season for northern and central Italy.27 101 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: Open Access , Machine learning models to complete rainfall time series databases affected by missing or anomalous data
In recent years, artificial intelligence in geosciences is spreading more and more, thanks to the availability of a large amount of data. In particular, the development of automatic raingauges networks allows to get rainfall data and makes these techniques effective, even if the performance of artificial intelligence models is a consequence of the coherency and quality of the input data. In this work, we intended to provide machine learning models capable of predicting rainfall data starting from the values of the nearest raingauges at one historic time point. Moreover, we investigated the influence of the anomalous input data on the prediction of rainfall data. We pursued these goals by applying machine learning models based on Linear Regression, LSTM and CNN architectures to several raingauges in Tuscany (central Italy). More than 75% of the cases show an R2 higher than 0.65 and a MAE lower than 4 mm. As expected, we emphasized a strong influence of the input data on the prediction capacity of the models. We quantified the model inaccuracy using the Pearson's correlation. Measurement anomalies in time series cause major errors in deep learning models. These anomalous data may be due to several factors such as temporary malfunctions of raingauges or weather conditions. We showed that, in both cases, the data-driven model features could highlight these situations, allowing a better management of the raingauges network and rainfall databases.33 35 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: Open Access , Seasonal rainfall trends of a key Mediterranean area in relation to large-scale atmospheric circulation: How does current global change affect the rainfall regime?
Current global warming causes a change in atmospheric dynamics, with consequent variations in the rainfall regimes. Understanding the relationship between global climate patterns, global warming, and rainfall regimes is crucial for the creation of future scenarios and for the relative modification of water management. The aim of this study is to improve knowledge of the relationship between North Atlantic Oscillation (NAO), East Atlantic (EA), and Western Mediterranean Oscillation (WeMO) with the seasonal rainfalls in Tuscany, Italy. The study area occupies a strategic position since it lies in a transition zone between the wet area of northern Europe and the dry area of the northern coast of Africa. This research, based on a statistical correlation method and on linear models, is designed to understand the relationship between seasonal rainfalls and climate patterns. The results of this study demonstrate that the use of linear models can yield more information than traditional statistical corre- lations. The results show a decrease in rainfall in the warm period of the year, namely in the summer, when its expression is most visible. This phenomenon is ascribable to current global warming, which causes an increase in sea-surface temperatures. An increase in the Northern Atlantic Sea Surface Temperature and in the Mediterra- nean Sea Surface Temperature causes a reduction of the Iceland Low, with an extension of the Azores High. Moreover, an increase in the Genoa Gulf SST27 105 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: Open Access , Web Mapping and Real–Virtual Itineraries to Promote Feasible Archaeological and Environmental Tourism in Versilia (Italy)
The Versilia plain (NW Italy) experiences forms of tourism that are mainly limited to the beach area and concentrated in the summer season. The area is rich in cultural and natural heritage, not yet adequately enhanced. The presence of four local archaeological museums and a natural park offers a great opportunity to favour feasible archaeological and environmental tourism. The aim of this study is to use a holistic methodology to improve a different type of tourism in the study area. We propose a consilient multidisciplinary approach based on geological, biological and archaeological data in order to enhance the cultural and natural heritage of the Versilia plain. We have based our study on the reconstruction of palaeoenvironment maps showing the evolution of the territory and used them as a leitmotiv to link the archaeological museums and the natural park. We define real and virtual itineraries to create a synergy between the most important archaeological and natural sites and museums. It is possible to promote a different type of tourism in the study area by decreasing human impact and creating a relationship between the fragmented natural and archaeological heritage. Palaeoenvironment maps and real and virtual itineraries can be consulted with the aid of a web application, more specifically web mapping, developed with free and open-source libraries. The web mapping also contains other geological, geomorphological and archaeological datasets, which allow to understand the evolution of the environment and the cultural and natural heritage of the study area. The dataset available on the web mapping is also downloadable.24 188 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: Open Access , Drones for litter mapping: An inter-operator concordance test in marking beached items on aerial images
Unmanned aerial systems (UAS, aka drones) are being used to map macro-litter on the environment. Sixteen qualified researchers (operators), with different expertise and nationalities, were invited to identify, mark and categorize the litter items (manual image screening, MS) on three UAS images collected at two beaches. The coefficient of concordance (W) among operators varied between 0.5 and 0.7, depending on the litter parameter (type, material and colour) considered. Highest agreement was obtained for the type of items marked on the highest resolution image, among experts in litter surveys (W = 0.86), and within territorial subgroups (W = 0.85). Therefore, for a detailed categorization of litter on the environment, the MS should be performed by experienced and local operators, familiar with the most common type of litter present in the target area. This work provides insights for future operational improvements and optimizations of UAS-based images analysis to survey environmental pollution.41 407 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: Open Access , A morphotectonic approach to the study of earthquakes in Rome
Rome has the world’s longest historical record of felt earthquakes, with more than 100 events during the last 2600 years. However, no destructive earthquake has been reported in the sources, and all of the greatest damage suffered in the past has been attributed to far-field events111 144
