<\/p>\n\n\n\n
The CORNERSTONE project aims to answer to three scientific questions:
1) How often an active region that produces an M- or X-class flare also produces a CME or SEPs ? <\/p>\n\n\n\n
2) Which magnetogram-based features are most correlated with a CME or a SEP occurrence ?<\/p>\n\n\n\n
3) Can we set up an Italian warning machine for flare and CME and SEP prediction based on magnetogram-based features ?<\/p>\n\n\n\n
From a methodological viewpoint the idea is to exploit the knowledge developed in recent years to build innovative deep learningalgorithms based on the physics of the Sun.<\/p>\n\n\n\n
In particular, we aim to develop:<\/p>\n\n\n\n
1) A method for generating non linear combinations of existing features such that the unit measure of the novel generated featuresis always the same, e.g. power or energy. Combinations of this kind should involve nonlinear elementary functions of known featuresand should result in a novel set of features all with the same unit of measure.<\/p>\n\n\n\n
2) Physics based kernel learning and\/or deep learning algorithms which, applied to the novel set of features sharing the same unit ofmeasure, predict the active region\u2019s probability of producing a CME, an X-class Flare, an M-class Flare, or a Solar Energetic ParticleEvent from a free-energy proxy measured from SOHO\/MDI line-of-sight magnetograms.<\/p>\n\n\n\n
The first point can be accomplished from the various known features of active regions that are candidate precursors of solar activity,for which calculation methods are available; the second point can be carried out on the basis of an historical database of labeledactive regions. The main scientific advantage of the project is the use of machine learning in a physics-driven manner, enabling machine learning results to be physically interpretable.<\/p>\n","protected":false},"excerpt":{"rendered":"
The CORNERSTONE project aims to answer to three scientific questions:1) How often an active region that produces an M- or X-class flare also produces a CME or SEPs ? 2) Which magnetogram-based features are most correlated with a CME or a SEP occurrence ? 3) Can we set up an Italian warning machine for flare […]<\/p>\n","protected":false},"author":1,"featured_media":21,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3],"tags":[8],"class_list":["post-20","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-project-description","tag-project"],"_links":{"self":[{"href":"https:\/\/cornerstone.web.roma2.infn.it\/index.php?rest_route=\/wp\/v2\/posts\/20","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cornerstone.web.roma2.infn.it\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/cornerstone.web.roma2.infn.it\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/cornerstone.web.roma2.infn.it\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/cornerstone.web.roma2.infn.it\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=20"}],"version-history":[{"count":2,"href":"https:\/\/cornerstone.web.roma2.infn.it\/index.php?rest_route=\/wp\/v2\/posts\/20\/revisions"}],"predecessor-version":[{"id":55,"href":"https:\/\/cornerstone.web.roma2.infn.it\/index.php?rest_route=\/wp\/v2\/posts\/20\/revisions\/55"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cornerstone.web.roma2.infn.it\/index.php?rest_route=\/wp\/v2\/media\/21"}],"wp:attachment":[{"href":"https:\/\/cornerstone.web.roma2.infn.it\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=20"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/cornerstone.web.roma2.infn.it\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=20"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/cornerstone.web.roma2.infn.it\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=20"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}