arXiv subjects

Sabrina Guastavino

Publications and source records attributed to Sabrina Guastavino.

26 records · Page 2Linked to original sources

arXiv2022

Operational solar flare forecasting via video-based deep learning

Operational flare forecasting aims at providing predictions that can be used to make decisions, typically at a daily scale, about the space weather impacts of flare occurrence. This study shows that video-based deep learning can be used for operational purposes when the training and validation sets used for the network optimization are generated while accounting for the periodicity of the solar cycle. Specifically, the paper describes an algorithm that can be applied to build up sets of active regions that are balanced according to the flare class rates associated to a specific cycle phase. These sets are used to train and validate a Long-term Recurrent Convolutional Network made of a combination of a convolutional neural network and a Long-Short Memory network. The reliability of this approach is assessed in the case of two prediction windows containing the solar storm of March 2015 and September 2017, respectively.

astro-ph.SR↗

arXiv2021

Implementation paradigm for supervised flare forecasting studies: a deep learning application with video data

Solar flare forecasting can be realized by means of the analysis of magnetic data through artificial intelligence techniques. The aim is to predict whether a magnetic active region (AR) will originate solar flares above a certain class within a certain amount of time. A crucial issue is concerned with the way the adopted machine learning method is implemented, since forecasting results strongly depend on the criterion with which training, validation, and test sets are populated. In this paper we propose a general paradigm to generate these sets in such a way that they are independent from each other and internally well-balanced in terms of AR flaring effectiveness. This set generation process provides a ground for comparison for the performance assessment of machine learning algorithms. Finally, we use this implementation paradigm in the case of a deep neural network, which takes as input videos of magnetograms recorded by the Helioseismic and Magnetic Imager on-board the Solar Dynamics Observatory (SDO/HMI). To our knowledge, this is the first time that the solar flare forecasting problem is addressed by means of a deep neural network for video classification, which does not require any a priori extraction of features from the HMI magnetograms.

astro-ph.SR↗

arXiv2021

Prediction of severe thunderstorm events with ensemble deep learning and radar data

The problem of nowcasting extreme weather events can be addressed by applying either numerical methods for the solution of dynamic model equations or data-driven artificial intelligence algorithms. Within this latter framework, the present paper illustrates how a deep learning method, exploiting videos of radar reflectivity frames as input, can be used to realize a warning machine able to sound timely alarms of possible severe thunderstorm events. From a technical viewpoint, the computational core of this approach is the use of a value-weighted skill score for both transforming the probabilistic outcomes of the deep neural network into binary classification and assessing the forecasting performances. The warning machine has been validated against weather radar data recorded in the Liguria region, in Italy,

cs.LG↗

arXiv2021

Flare Forecasting Algorithms Based on High-Gradient Polarity Inversion Lines in Active Regions

Solar flares emanate from solar active regions hosting complex and strong bipolar magnetic fluxes. Estimating the probability of an active region to flare and defining reliable precursors of intense flares is an extremely challenging task in the space weather field. In this work, we focus on two metrics as flare precursors, the unsigned flux R, tested on MDI/SOHO data and one of the most used parameters for flare forecasting applications, and a novel topological parameter D representing the complexity of a solar active region. More in detail, we propose an algorithm for the computation of the R value which exploits the higher spatial resolution of HMI maps. This algorithm leads to a differently computed R value, whose functionality is tested on a set of cycle 24th solar flares. Furthermore, we introduce a topological parameter based on the automatic recognition of magnetic polarity-inversion lines in identified active regions, and able to evaluate its magnetic topological complexity. We use both a heuristic approach and a supervised machine learning method to validate the effectiveness of these two descriptors to predict the occurrence of X- or M- class flares in a given solar active region during the following 24 hours period. Our feature ranking analysis shows that both parameters play a significant role in prediction performances. Moreover, the analysis demonstrates that the new topological parameter D is the only one, among 173 overall predictors, which is always present for all test subsets and is systematically ranked within the top-ten positions in all tests concerning the computation of the weighs with which each predictor impacts the flare forecasting.

astro-ph.SR↗

arXiv2021

Score-oriented loss (SOL) functions

Loss functions engineering and the assessment of forecasting performances are two crucial and intertwined aspects of supervised machine learning. This paper focuses on binary classification to introduce a class of loss functions that are defined on probabilistic confusion matrices and that allow an automatic and a priori maximization of the skill scores. The performances of these loss functions are validated during the training phase of two experimental forecasting problems, thus showing that the probability distribution function associated with the confusion matrices significantly impacts the outcome of the score maximization process.

cs.LG↗

arXiv2021

Bad and good errors: value-weighted skill scores in deep ensemble learning

In this paper we propose a novel approach to realize forecast verification. Specifically, we introduce a strategy for assessing the severity of forecast errors based on the evidence that, on the one hand, a false alarm just anticipating an occurring event is better than one in the middle of consecutive non-occurring events, and that, on the other hand, a miss of an isolated event has a worse impact than a miss of a single event, which is part of several consecutive occurrences. Relying on this idea, we introduce a novel definition of confusion matrix and skill scores giving greater importance to the value of the prediction rather than to its quality. Then, we introduce a deep ensemble learning procedure for binary classification, in which the probabilistic outcomes of a neural network are clustered via optimization of these value-weighted skill scores. We finally show the performances of this approach in the case of three applications concerned with pollution, space weather and stock prize forecasting.

cs.LG↗

arXiv2019

Desaturating EUV observations of solar flaring storms

Image saturation has been an issue for several instruments in solar astronomy, mainly at EUV wavelengths. However, with the launch of the Atmospheric Imaging Assembly (AIA) as part of the payload of the Solar Dynamic Observatory (SDO) image saturation has become a big data issue, involving around 10^$ frames of the impressive dataset this beautiful telescope has been providing every year since February 2010. This paper introduces a novel desaturation method, which is able to recover the signal in the saturated region of any AIA image by exploiting no other information but the one contained in the image itself. This peculiar methodological property, jointly with the unprecedented statistical reliability of the desaturated images, could make this algorithm the perfect tool for the realization of a reconstruction pipeline for AIA data, able to work properly even in the case of long-lasting, very energetic flaring events.

astro-ph.SR↗

arXiv2018

On the connection between supervised learning and linear inverse problems

In this paper we investigate the connection between supervised learning and linear inverse problems. We first show that a linear inverse problem can be view as a function approximation problem in a reproducing kernel Hilbert space (RKHS) and then we prove that to each of these approximation problems corresponds a class of inverse problems. Analogously, we show that Tikhonov solutions of this class correspond to the Tikhonov solution of the approximation problem. Thanks to this correspondence, we show that supervised learning and linear discrete inverse problems can be thought of as two instances of the approximation problem in a RKHS. These instances are formalized by means of a sampling operator which takes into account both deterministic and random samples and leads to discretized problems. We then analyze the discretized problems and we study the convergence of their solutions to the ones of the approximation problem in a RKHS, both in the deterministic and statistical framework. Finally, we prove there exists a relation between the convergence rates computed with respect to the noise level and the ones computed with respect to the number of samples. This allows us to compare upper and lower bounds given in the statistical learning and in the deterministic infinite dimensional inverse problems theory.

math.NA↗