{"id":1502,"date":"2023-06-26T23:24:27","date_gmt":"2023-06-27T03:24:27","guid":{"rendered":"https:\/\/sites.nd.edu\/jianxun-wang\/?page_id=1502"},"modified":"2023-06-27T00:11:44","modified_gmt":"2023-06-27T04:11:44","slug":"scientific-machine-learning","status":"publish","type":"page","link":"https:\/\/sites.nd.edu\/jianxun-wang\/scientific-machine-learning\/","title":{"rendered":"Scientific Machine Learning for Spatio-temporal Predictions"},"content":{"rendered":"\n<h2 class=\"wp-block-heading\">Topic 1\uff1aDifferentiable Neural Solver and GPU Computing<\/h2>\n\n\n\n<p>Aiming to develop next-gen computational modeling framework by combining classic numerical method, deep learning techniques, and data via differentiable programming and GPU computing &#8212; enabling efficient forward\/inverse modeling and data assimilation.      <\/p>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/sites.nd.edu\/jianxun-wang\/files\/2023\/06\/neuralsolver-1024x831.png\" alt=\"\" class=\"wp-image-1503\" width=\"808\" height=\"655\" srcset=\"https:\/\/sites.nd.edu\/jianxun-wang\/files\/2023\/06\/neuralsolver-1024x831.png 1024w, https:\/\/sites.nd.edu\/jianxun-wang\/files\/2023\/06\/neuralsolver-300x243.png 300w, https:\/\/sites.nd.edu\/jianxun-wang\/files\/2023\/06\/neuralsolver-768x623.png 768w, https:\/\/sites.nd.edu\/jianxun-wang\/files\/2023\/06\/neuralsolver.png 1240w\" sizes=\"auto, (max-width: 808px) 100vw, 808px\" \/><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">Topic 2\uff1aAdvance deep learning techniques<\/h2>\n\n\n\n<p>We are pushing the boundary of deep learning architecture, data-driven techniques for learning spatiotemporal system &#8211; graph neural networks, sequence2sequence networks, transformer, diffusion models et. <\/p>\n\n\n\n<figure class=\"wp-block-image size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/sites.nd.edu\/jianxun-wang\/files\/2023\/06\/ICLR.png\" alt=\"\" class=\"wp-image-1515\" width=\"804\" height=\"493\" srcset=\"https:\/\/sites.nd.edu\/jianxun-wang\/files\/2023\/06\/ICLR.png 628w, https:\/\/sites.nd.edu\/jianxun-wang\/files\/2023\/06\/ICLR-300x184.png 300w\" sizes=\"auto, (max-width: 804px) 100vw, 804px\" \/><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">Topic 3\uff1aPhysics-informed, PDE-regularized Machine\/Deep Learning<\/h2>\n\n\n\n<p>Using residual of governing PDEs to regularized or drive machine\/deep learning model training, e.g., physics-informed neural networks, B-PINN, physics-informed CNN, and FEM-GNN etc. <\/p>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/sites.nd.edu\/jianxun-wang\/files\/2023\/06\/PINN-1-1024x509.png\" alt=\"\" class=\"wp-image-1504\" width=\"839\" height=\"417\" srcset=\"https:\/\/sites.nd.edu\/jianxun-wang\/files\/2023\/06\/PINN-1-1024x509.png 1024w, https:\/\/sites.nd.edu\/jianxun-wang\/files\/2023\/06\/PINN-1-300x149.png 300w, https:\/\/sites.nd.edu\/jianxun-wang\/files\/2023\/06\/PINN-1-768x381.png 768w, https:\/\/sites.nd.edu\/jianxun-wang\/files\/2023\/06\/PINN-1.png 1337w\" sizes=\"auto, (max-width: 839px) 100vw, 839px\" \/><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>Topic 1\uff1aDifferentiable Neural Solver and GPU Computing Aiming to develop next-gen computational modeling framework by combining classic numerical method, deep learning techniques, and data via differentiable programming and GPU computing &#8212; enabling efficient forward\/inverse modeling and data assimilation. Topic 2\uff1aAdvance deep learning techniques We are pushing the boundary of deep learning architecture, data-driven techniques for [&hellip;]<\/p>\n","protected":false},"author":3220,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-1502","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/sites.nd.edu\/jianxun-wang\/wp-json\/wp\/v2\/pages\/1502","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/sites.nd.edu\/jianxun-wang\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/sites.nd.edu\/jianxun-wang\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/sites.nd.edu\/jianxun-wang\/wp-json\/wp\/v2\/users\/3220"}],"replies":[{"embeddable":true,"href":"https:\/\/sites.nd.edu\/jianxun-wang\/wp-json\/wp\/v2\/comments?post=1502"}],"version-history":[{"count":9,"href":"https:\/\/sites.nd.edu\/jianxun-wang\/wp-json\/wp\/v2\/pages\/1502\/revisions"}],"predecessor-version":[{"id":1517,"href":"https:\/\/sites.nd.edu\/jianxun-wang\/wp-json\/wp\/v2\/pages\/1502\/revisions\/1517"}],"wp:attachment":[{"href":"https:\/\/sites.nd.edu\/jianxun-wang\/wp-json\/wp\/v2\/media?parent=1502"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}