{"id":1062,"date":"2023-07-03T01:17:55","date_gmt":"2023-07-03T00:17:55","guid":{"rendered":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/?page_id=1062"},"modified":"2023-07-03T01:17:55","modified_gmt":"2023-07-03T00:17:55","slug":"abstract186","status":"publish","type":"page","link":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/programme\/abstract186\/","title":{"rendered":"Abstract 186"},"content":{"rendered":"

[vc_row][vc_column][vc_column_text]Abstract ID:<\/strong> 186<\/p>\n

Introducing the AI4S2S project; open-source python packages to make data-driven pipelines for S2S forecasting more efficient, transparent, and scalable<\/h2>\n

Lead Author:<\/strong> Sem Vijverberg
\nVrije Universiteit, Institute for Environmental Studies, Netherlands
\n<\/span><\/p>\n

Keywords:<\/strong> open-source software, Machine Learning, S2S forecasting<\/p>\n

Abstract: <\/strong>Reliable S2S forecasts remain a huge scientific challenge. The lead-time is too long such that the memory from the atmosphere\u2019s initial condition is lost, but too short for the atmosphere\u2019s boundary conditions to be felt strongly. Only for specific \u2018windows of predictability\u2019 (i.e. specific regions, timescales and climatic background states), skillful forecasts are possible, in an otherwise largely unpredictable future. The interest in machine learning (ML) is growing fast due to a number of successes in S2S forecasting. However, we argue there is a need for more standardization, consensus on best practices, higher efficiency, and higher reproducibility. Typical S2S ML use-cases, such as (1) pure statistical forecasting based on observations, (2) transfer learning, and (3) post-processing of dynamical model ensembles, require a large coding and preprocessing effort. Such experiments are not trivial to set up, and without sufficient experience and expertise there is a large risk of improper cross-validation and\/or improper and non-standard verification.<\/p>\n

Within a 3-year project, a dedicated team of software engineers and researchers are working on light-weight Python packages that make the construction of ML-based pipelines for S2S forecasting much more efficient, transparent, and scalable.<\/p>\n

We developed the python package \u201clilio\u201d to handle user-defined sequences of precursor and target periods, to be able to reliably and repeatedly resample raw input data to these periods. The \u201cs2spy\u201d package continues where \u201clilio\u201d leaves off, and facilitates orchestrating full S2S machine learning pipelines, from preprocessing and cross-validation, to dimensionality reduction, model fitting and model interpretation. Flexibility for the user is an important pillar of s2spy, leaving as much flexibility as possible for the user to insert their own new methods to forecast and\/or reduce dimensionality. Once such a clean ML pipeline has been designed, it becomes both more transparent, reproducible, as well as easily scalable to any HPC system and climate data platform.<\/p>\n

The AI4S2S project aims to contribute to a higher reproducibility and works towards a wider acceptance of ML standards and best practices. We will present our vision and the capabilities of our package, show-casing that we can build a model from raw climate data up to verification in only a few lines of code.<\/p>\n

Co-authors:
\n<\/strong>Bart Schilperoort (Netherlands eScience Center)
\nYang Liu (Netherlands eScience Center)
\nJannes van Ingen (Vrije Universiteit, Institute for Environmental Studies)
\nPeter Kalverla (Netherlands eScience Center)
\nFakhereh (Sarah) Alidoost (Netherlands eScience Center)
\nDim Coumou (Vrije Universiteit, Institute for Environmental Studies)[\/vc_column_text][vc_separator][\/vc_column][\/vc_row][vc_row][vc_column width=”1\/6″][vc_single_image image=”344″ img_size=”full” onclick=”custom_link” link=”http:\/\/s2sprediction.net\/”][\/vc_column][vc_column width=”1\/6″][vc_single_image image=”345″ img_size=”full” onclick=”custom_link” link=”https:\/\/public.wmo.int\/en”][\/vc_column][vc_column width=”1\/6″][vc_single_image image=”346″ img_size=”full” onclick=”custom_link” link=”https:\/\/community.wmo.int\/activity-areas\/wwrp”][\/vc_column][vc_column width=”1\/6″][vc_single_image image=”347″ img_size=”full” onclick=”custom_link” link=”https:\/\/www.wcrp-climate.org\/”][\/vc_column][vc_column width=”1\/6″][vc_single_image image=”348″ img_size=”full”][\/vc_column][vc_column width=”1\/6″][vc_single_image image=”349″ img_size=”full” onclick=”custom_link” link=”https:\/\/www.reading.ac.uk\/”][\/vc_column][\/vc_row]<\/p>\n","protected":false},"excerpt":{"rendered":"

[vc_row][vc_column][vc_column_text]Abstract ID: 186 Introducing the AI4S2S project; open-source python packages to make data-driven pipelines for S2S forecasting more efficient, transparent, and scalable Lead Author: Sem Vijverberg Vrije Universiteit, Institute for…Read More ><\/a><\/p>\n","protected":false},"author":145,"featured_media":0,"parent":528,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_acf_changed":false,"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"__cvm_playback_settings":[],"__cvm_video_id":"","footnotes":""},"coauthors":[13],"class_list":["post-1062","page","type-page","status-publish","hentry"],"acf":[],"yoast_head":"\nAbstract 186 - WWRP\/WCRP S2S Summit 2023<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/research.reading.ac.uk\/s2s-summit2023\/programme\/abstract186\/\" \/>\n<meta property=\"og:locale\" content=\"en_GB\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Abstract 186 - WWRP\/WCRP S2S Summit 2023\" \/>\n<meta property=\"og:description\" content=\"[vc_row][vc_column][vc_column_text]Abstract ID: 186 Introducing the AI4S2S project; open-source python packages to make data-driven pipelines for S2S forecasting more efficient, transparent, and scalable Lead Author: Sem Vijverberg Vrije Universiteit, Institute for...Read More >\" \/>\n<meta property=\"og:url\" content=\"https:\/\/research.reading.ac.uk\/s2s-summit2023\/programme\/abstract186\/\" \/>\n<meta property=\"og:site_name\" content=\"WWRP\/WCRP S2S Summit 2023\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Estimated reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"3 minutes\" \/>\n\t<meta name=\"twitter:label2\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data2\" content=\"Robert Lee\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/research.reading.ac.uk\/s2s-summit2023\/programme\/abstract186\/\",\"url\":\"https:\/\/research.reading.ac.uk\/s2s-summit2023\/programme\/abstract186\/\",\"name\":\"Abstract 186 - WWRP\/WCRP S2S Summit 2023\",\"isPartOf\":{\"@id\":\"https:\/\/research.reading.ac.uk\/s2s-summit2023\/#website\"},\"datePublished\":\"2023-07-03T00:17:55+00:00\",\"dateModified\":\"2023-07-03T00:17:55+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/research.reading.ac.uk\/s2s-summit2023\/programme\/abstract186\/#breadcrumb\"},\"inLanguage\":\"en-GB\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/research.reading.ac.uk\/s2s-summit2023\/programme\/abstract186\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/research.reading.ac.uk\/s2s-summit2023\/programme\/abstract186\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/research.reading.ac.uk\/s2s-summit2023\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Programme\",\"item\":\"https:\/\/research.reading.ac.uk\/s2s-summit2023\/programme\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Abstract 186\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/research.reading.ac.uk\/s2s-summit2023\/#website\",\"url\":\"https:\/\/research.reading.ac.uk\/s2s-summit2023\/\",\"name\":\"WWRP\/WCRP S2S Summit 2023\",\"description\":\"Advancing Sub-seasonal to Seasonal Predictions and their Applications\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/research.reading.ac.uk\/s2s-summit2023\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-GB\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Abstract 186 - WWRP\/WCRP S2S Summit 2023","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/programme\/abstract186\/","og_locale":"en_GB","og_type":"article","og_title":"Abstract 186 - WWRP\/WCRP S2S Summit 2023","og_description":"[vc_row][vc_column][vc_column_text]Abstract ID: 186 Introducing the AI4S2S project; open-source python packages to make data-driven pipelines for S2S forecasting more efficient, transparent, and scalable Lead Author: Sem Vijverberg Vrije Universiteit, Institute for...Read More >","og_url":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/programme\/abstract186\/","og_site_name":"WWRP\/WCRP S2S Summit 2023","twitter_card":"summary_large_image","twitter_misc":{"Estimated reading time":"3 minutes","Written by":"Robert Lee"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/programme\/abstract186\/","url":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/programme\/abstract186\/","name":"Abstract 186 - WWRP\/WCRP S2S Summit 2023","isPartOf":{"@id":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/#website"},"datePublished":"2023-07-03T00:17:55+00:00","dateModified":"2023-07-03T00:17:55+00:00","breadcrumb":{"@id":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/programme\/abstract186\/#breadcrumb"},"inLanguage":"en-GB","potentialAction":[{"@type":"ReadAction","target":["https:\/\/research.reading.ac.uk\/s2s-summit2023\/programme\/abstract186\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/programme\/abstract186\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/"},{"@type":"ListItem","position":2,"name":"Programme","item":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/programme\/"},{"@type":"ListItem","position":3,"name":"Abstract 186"}]},{"@type":"WebSite","@id":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/#website","url":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/","name":"WWRP\/WCRP S2S Summit 2023","description":"Advancing Sub-seasonal to Seasonal Predictions and their Applications","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-GB"}]}},"_links":{"self":[{"href":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/wp-json\/wp\/v2\/pages\/1062","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/wp-json\/wp\/v2\/users\/145"}],"replies":[{"embeddable":true,"href":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/wp-json\/wp\/v2\/comments?post=1062"}],"version-history":[{"count":2,"href":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/wp-json\/wp\/v2\/pages\/1062\/revisions"}],"predecessor-version":[{"id":1091,"href":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/wp-json\/wp\/v2\/pages\/1062\/revisions\/1091"}],"up":[{"embeddable":true,"href":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/wp-json\/wp\/v2\/pages\/528"}],"wp:attachment":[{"href":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/wp-json\/wp\/v2\/media?parent=1062"}],"wp:term":[{"taxonomy":"author","embeddable":true,"href":"https:\/\/research.reading.ac.uk\/s2s-summit2023\/wp-json\/wp\/v2\/coauthors?post=1062"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}