Options
Fortuna, Luigi
Loading...
18 results
Now showing 1 - 10 of 18
- PublicationRestrictedModeling volcanomagnetic dynamics by recurrent least-squares support vector machines(2010)
; ; ; ; ; ; ;Jankowski, S.; Warsaw University of Technology, Poland ;Currenti, G.; Istituto Nazionale di Geofisica e Vulcanologia, Sezione Catania, Catania, Italia ;Napoli, R.; Istituto Nazionale di Geofisica e Vulcanologia, Sezione Catania, Catania, Italia ;Szymanski1, Z.; Warsaw University of Technology, Poland ;Fortuna, L.; Dipartimento Di Ingegneria Elettrica Elettronica e dei Sistemi Università di Catania, ;Del Negro, C.; Istituto Nazionale di Geofisica e Vulcanologia, Sezione Catania, Catania, Italia; ; ; ; ; Nonlinear dynamic systems can be described by means of statistical learning theory: neural networks and kernel machines. In this work the recurrent least-squares support vector machines are chosen as learning system. The unknown dynamic system is a mapping of past states into the future. The recurrent system is implemented by special data preparation in the learning phase. The next iterations can be calculated but the convergence is usually not guaranteed. Due to the fact that the predicted trajectory can diverge from the real trajectory the semi-directed mode can be applied, i.e. after several prediction steps the system is updated by using the current values of the considered process as new initial conditions. The idea was tested on the data generated by the chaotic dynamic system – the Chua’s circuit. The methodology was then applied to real magnetic data acquired at Etna volcano.123 22 - PublicationOpen AccessFEM and ANN combined approach for predicting pressure source(2010)
; ; ; ; ; ;Di Stefano, A.; Istituto Nazionale di Geofisica e Vulcanologia, Sezione Catania, Catania, Italia ;Currenti, G.; Istituto Nazionale di Geofisica e Vulcanologia, Sezione Catania, Catania, Italia ;Del Negro, C.; Istituto Nazionale di Geofisica e Vulcanologia, Sezione Catania, Catania, Italia ;Fortuna, L.; Università degli Studi di Catania ;Nunnari, G.; Università degli Studi di Catania; ; ; ; A hybrid approach for forward and inverse geophysical modeling, based on Artificial Neural Networks (ANN) and Finite Element Method (FEM), is proposed in order to properly identify the parameters of volcanic pressure sources from geophysical observations at ground surface. The neural network is trained and tested with a set of patterns obtained by the solutions of numerical models based on FEM. The geophysical changes caused by magmatic pressure sources were computed developing a 3-D FEM model with the aim to include the effects of topography and medium heterogeneities at Etna volcano. ANNs are used to interpolate the complex non linear relation between geophysical observations and source parameters both for forward and inverse modeling. The results show that the combination of neural networks and FEM is a powerful tool for a straightforward and accurate estimation of source parameters in volcanic regions.141 140 - PublicationOpen AccessImproving cloud detection with imperfect satellite images using an artificial neural network approach(2019)
; ; ; ; ; ; ; ; ; ; ; ;; The past few decades have seen an explosion of satellite remote sensing techniques for the monitoring of volcanic thermal features. Here, we propose an artificial neural network approach for improving the cloud detection through imperfect multispectral satellite images analysis. The cloud detection algorithm has been tested on a data set of MSGSEVIRI images acquired over the area of Etna volcano in Sicily (Italy) before and during the 2008 eruption. Results show that this approach is robust in terms of percentage of correctly classified pixels.822 75 - PublicationOpen AccessCombining Radar and Optical Satellite Imagery with Machine Learning to Map Lava Flows at Mount Etna and Fogo Island(2021)
; ; ; ; ; ; ; ; ; Lava flow mapping has direct relevance to volcanic hazards once an eruption has begun. Satellite remote sensing techniques are increasingly used to map newly erupted lava, thanks to their capability to survey large areas with frequent revisit time and accurate spatial resolution. Visible and infrared satellite data are routinely used to detect the distributions of volcanic deposits and monitor thermal features, even if clouds are a serious obstacle for optical sensors, since they cannot be penetrated by optical radiation. On the other hand, radar satellite data have been playing an important role in surface change detection and image classification, being able to operate in all weather conditions, although their use is hampered by the special imaging geometry, the complicated scattering process, and the presence of speckle noise. Thus, optical and radar data are complementary data sources that can be used to map lava flows effectively, in addition to alleviating cloud obstruction and improving change detection performance. Here, we propose a machine learning approach based on the Google Earth Engine (GEE) platform to analyze simultaneously the images acquired by the synthetic aperture radar (SAR) sensor, on board of Sentinel-1 mission, and by optical and multispectral sensors of Landsat-8 missions and Multi-Spectral Imager (MSI), on board of Sentinel-2 mission. Machine learning classifiers, including K-means algorithm (K-means) and support vector machine (SVM), are used to map lava flows automatically from a combination of optical and SAR images. We describe the operation of this approach by using a retrospective analysis of two recent lava flow-forming eruptions at Mount Etna (Italy) and Fogo Island (Cape Verde). We found that combining both radar and optical imagery improved the accuracy and reliability of lava flow mapping. The results highlight the need to fully exploit the extraordinary potential of complementary satellite sensors to provide time-critical hazard information during volcanic eruptions.476 118 - PublicationOpen AccessSimulating complex fluids with smoothed particle hydrodynamics(2017)
; ; ; ; ; ; ; ; ; ; ; ; ;; ;Complex fluid dynamics encompasses a large variety of flows, such as fluids with non-Newtonian rheology, multiphase and multi-fluid flows (suspensions, lather, solid/fluid interaction with floating objects, etc.), violent flows breaking waves, dam-breaks, etc.), fluids with thermal dependencies and phase transition or free-surface flows. Correctly modeling the behavior of such flows can be quite challenging, and has led to significant advances in the field of Computational Fluid Dynamics (CFD). Recently, the Smoothed Particle Hydrodynamics (SPH) method has emerged as a powerful alternative to more classic CFD methods (such as finite volumes or finite elements) in many fields, including oceanography, volcanology, structural engineering, nuclear physics and medicine. With SPH, the fluid is discretized by means of particles and thanks to the meshless, Lagrangian nature of the model, it easily allows the modeling and simulation of both simple and complex fluids, simplifying the treatment of aspects that can be challenging with more traditional methods: dynamic free surfaces, large deformations, phase transition, fluid/solid interaction and complex geometries. In addition, the most common SPH formulations are fully parallelizable, which favors implementation on high-performance parallel computing hardware, such as modern Graphics Processing Units (GPUs). We present here how GPUSPH, an implementation of the SPH method that runs on GPUs, can model a variety of complex fluids, highlighting the computational challenges that arise in its applications to problem of great interest in volcanology.704 159 - PublicationOpen AccessPreliminary validation of lava benchmark tests on the GPUSPH particle engine(2019)
; ; ; ; ; ; ; ; ; ; ; ; ;; ; Lava flow modeling is important in many practical applications, such as the simulation of potential hazard scenarios and the planning of risk mitigation measures, as well as in scientific research to improve our understanding of the physical processes governing the dynamics of lava flow emplacement. Existing predictive models of lava flow behavior include various methods and solvers, each with its advantages and disadvantages. Codes differ in their physical implementations, numerical accuracy, and computational efficiency. In order to validate their efficiency and accuracy, several benchmark test cases for computational lava flow modeling have been established. Despite the popularity gained by the Smoothed Particle Hydrodynamics (SPH) method in Computational Fluid Dynamics (CFD), very few validations against lava flows have been successfully conducted. At the Tecnolab of INGVCatania we designed GPUSPH, an implementation of the weakly-compressible SPH method running fully on Graphics Processing Units (GPUs). GPUSPH is a particle engine capable of modeling both Newtonian and non-Newtonian fluids, solving the three-dimensional Navier– Stokes equations, using either a fully explicit integration scheme, or a semi-implicit scheme in the case of highly viscous fluids. Thanks to the full coupling with the thermal equation, and its support for radiation, convection and phase transition, GPUSPH can be used to faithfully simulate lava flows. Here we present the preliminary results obtained with GPUSPH for a benchmark series for computational lava-flow modeling, including analytical, semi-analytical and experimental problems. The results are reported in terms of correctness and performance, highlighting the benefits and the drawbacks deriving from the use of SPH to simulate lava flows.962 82 - PublicationRestrictedFuzzy cellular systems for a new computational paradigm(1997)
; ; ; ; ; ; ;In this paper a new approach for processing arrays of data is proposed. It is based on fuzzy logic and the concepts of cellular computation. Arrays of simple, identical processing elements (called fuzzy cells) are defined by using fuzzy rules. Moreover, each fuzzy cell interacts with its local neighbors. The overall behavior of these locally interacting fuzzy systems is used to process arrays of data. Some examples of practical applications are proposed. Among these, the new approach is applied to image-processing problems, and to the simulation of heat diffusion phenomena.35 2 - PublicationOpen AccessSimulations of the 2004 lava flow at Etna volcano by the magflow cellular automata model(2007)
; ; ; ; ;Del Negro, C.; Istituto Nazionale di Geofisica e Vulcanologia, Sezione Catania, Catania, Italia ;Fortuna, L.; DIEES - Università di Catania ;Herault, A.; Universitè di Marnee la Vallee ;Vicari, A.; Istituto Nazionale di Geofisica e Vulcanologia, Sezione Catania, Catania, Italia; ; ; Lava flows represent a challenge for physically based modeling, since the mechanical properties of lava change over time. This change is ruled by a temperature field, which needs to be modeled. MAGFLOW Cellular Automata (CA) model was developed for physically based simulations of lava flows in near real-time. We introduced an algorithm based on the Monte Carlo approach to solve the anisotropic problem. As transition rule of CA, a steady state solution of Navier-Stokes equations was adopted in the case of isothermal laminar pressure-driven Bingham fluid. For the cooling mechanism, we consider the radiative heat loss only from the surface of the flow, and the change of the temperature due to mixture of lavas between cells with different temperatures. The model was applied to reproduce a real lava flow occurred during the 2004-2005 Etna eruption. The simulations were computed using three different empirical relationships between viscosity and temperature.149 375 - PublicationRestrictedLava flow simulations using discharge rates from thermal(2009)
; ; ; ; ;Vicari, A.; Istituto Nazionale di Geofisica e Vulcanologia, Sezione Catania, Catania, Italia ;Ciraudo, A.; Istituto Nazionale di Geofisica e Vulcanologia, Sezione Catania, Catania, Italia ;Del Negro, C.; Istituto Nazionale di Geofisica e Vulcanologia, Sezione Catania, Catania, Italia ;Fortuna, L.; Università degli studi di Catania, Dipartimento di Ingegneria Elettrica, Elettronica e dei Sistemi; ; ; Techniques capable of measuring lava discharge rates during an eruption are important for hazard prediction, warning, and mitigation. To this end, we developed an automated system that uses thermal infrared satellite MODIS data to estimate time-averaged discharge rate. MODIS-derived time-varying discharge rates were used to drive lava flow simulations calculated using the MAGFLOW cellular automata model, allowing us to simulate the discharge rate-dependent spread of lava as a function of time. During the July 2006 eruption of Mount Etna (Sicily, Italy), discharge rates were estimated at regular intervals (i.e., up to 2 times/day) using the MODIS data. The eruption lasted 10 days and produced a *3-km-long lava flow field. Time-averaged discharge rates extracted from 13 MODIS images were utilized to produce a detailed chronology of lava flow emplacement, demonstrating how infrared satellite data can be used to drive numerical simulations of lava flow paths during an ongoing eruptive event. The good agreement between simulated and mapped flow areas indicates that model-based inundation predictions, driven by timevarying discharge rate data, provide an excellent means for assessing the hazard posed by ongoing effusive eruptions.238 29 - PublicationRestrictedIntegrated inversion of numerical geophysical models using artificial neural networks(2010)
; ; ; ; ; ;Di Stefano, A.; Istituto Nazionale di Geofisica e Vulcanologia, Sezione Catania, Catania, Italia ;Currenti, G.; Istituto Nazionale di Geofisica e Vulcanologia, Sezione Catania, Catania, Italia ;Del Negro, C.; Istituto Nazionale di Geofisica e Vulcanologia, Sezione Catania, Catania, Italia ;Fortuna, L.; Università degli studi di Catania ;Nunnari, G.; Dike deflection modelling for inferring magma pressure and withdrawal,; ; ; ; A uni ed modelling procedure is proposed to jointly interpret the variations observed in geophysical data and to properly take into account the relation- ship between the intrusive processes and the geophysical variations expected at the ground surface. We focus on the joint inversion of geophysical data by a procedure based on Arti cial Neural Network (ANN) for the estimation of the volcanic source parameters. As forward model, we develop a 3D numerical model based on Finite Element Method (FEM) for computing ground deforma- tion, magnetic and gravity changes caused by magmatic overpressure sources, with the aim to consider a more realistic description of Etna volcano, including the e ects of topography and medium heterogeneities.151 27