Related papers: Using Multiple Instance Learning for Explainable S…
We examine SDO/EVE data to better understand solar flare irradiance, and how that irradiance may vary for large events. We measure scaling laws relating GOES flare classes to irradiance in 21 lines measured with SDO/EVE, formed across a…
Digitizing pathological images into gigapixel Whole Slide Images (WSIs) has opened new avenues for Computational Pathology (CPath). As positive tissue comprises only a small fraction of gigapixel WSIs, existing Multiple Instance Learning…
Multiple Instance learning (MIL) models have been extensively used in pathology to predict biomarkers and risk-stratify patients from gigapixel-sized images. Machine learning problems in medical imaging often deal with rare diseases, making…
Solar flare ribbons are intense brightenings of principally chromospheric material that are responsible for a large fraction of the chromospheric emission in solar and stellar flares. We present an on-disc observation of flare ribbon…
A triplet of subordinate lines of Mg II exists in the region around the h&k lines. In solar spectra these lines are seen mostly in absorption, but in some cases can become emission lines. The aim of this work is to study the formation of…
Small reconnection events in the lower solar atmosphere can lead to its heating, but whether such heating can propagate into higher atmospheric layers and potentially contribute to coronal heating is an open question. We carry out a large…
Multiple instance learning (MIL) is the standard approach for whole-slide image (WSI) classification and survival prediction, where attention-based models ag gregate patch features into slide-level predictions. These models treat attention…
The triggering mechanism(s) and critical condition(s) of solar flares are still not completely clarified, although various studies have attempted to elucidate them. We have also proposed a theoretical flare-trigger model based on MHD…
Neutrinos generated during solar flares remain elusive. However, after $50$ years of discussion and search, the potential knowledge unleashed by their discovery keeps the search crucial. Neutrinos associated with solar flares provide…
We developed an operational solar flare prediction model using deep neural networks, named Deep Flare Net (DeFN). DeFN can issue probabilistic forecasts of solar flares in two categories, such as >=M-class and <M-class events or >=C-class…
We analyze the relationship between the flare X-ray peak flux, and characteristics of the Polarity Inversion Line (PIL) and Active Regions (AR), derived from line-of-sight (LOS) magnetograms. The PIL detection algorithm based on a…
Multiple instance learning (MIL) is the preferred approach for whole slide image classification. However, most MIL approaches do not exploit the interdependencies of tiles extracted from a whole slide image, which could provide valuable…
In this paper, we introduce a novel methodology for leveraging shape-based characteristics of magnetograms of active region (AR) patches and provide a novel capability for predicting solar flares covering the entirety of the solar disk (AR…
AI-FLARES (Artificial Intelligence for the Analysis of Solar Flares Data) is a research project funded by the Agenzia Spaziale Italiana and by the Istituto Nazionale di Astrofisica within the framework of the ``Attivit\`a di Studio per la…
Aims: This paper aims to demonstrate the importance of short-exposure extreme ultraviolet (EUV) observations of solar flares in the study of particle acceleration, heating and energy partition in flares. This work highlights the…
Solar energetic particles (SEPs) are an essential source of space radiation, which are hazards for humans in space, spacecraft, and technology in general. In this paper we propose a deep learning method, specifically a bidirectional long…
Current solar flare predictions often lack precise quantification of their reliability, resulting in frequent false alarms, particularly when dealing with datasets skewed towards extreme events. To improve the trustworthiness of space…
A new multi-attention based method for solving the MIL problem (MAMIL), which takes into account the neighboring patches or instances of each analyzed patch in a bag, is proposed. In the method, one of the attention modules takes into…
A Bayesian approach to solar flare prediction has been developed, which uses only the event statistics of flares already observed. The method is simple, objective, and makes few ad hoc assumptions. It is argued that this approach should be…
Multi-Instance Learning (MIL) is pivotal for analyzing complex, weakly labeled datasets, such as whole-slide images (WSIs) in computational pathology, where bags comprise unordered collections of instances with sparse diagnostic relevance.…