{"corpus_id":4575852,"paper_sha":"0acd117521ef5aafb09fed02ab415523b330b058","doi":"10.1126/sciadv.1602614","arxiv_id":"1609.06401","pmid":28508044,"pmcid":"5406137","mag_id":2950893882,"dblp_id":null,"acl_id":null,"title":"Data-driven discovery of partial differential equations","year":2016,"publication_date":"2016-09-21","venue":"Science Advances","journal":{"name":"Science Advances","pages":null,"volume":"3"},"journal_issn":null,"journal_title":null,"publication_types":["JournalArticle"],"pubmed_pub_types":["Journal Article"],"s2_fields_of_study":["Physics","Computer Science","Mathematics","Engineering","Environmental Science","Medicine"],"reference_count":56,"citation_count":1584,"influential_citation_count":122,"is_open_access":true,"arxiv_categories":["nlin.PS"],"arxiv_license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","arxiv_journal_ref":null,"mesh_headings":null,"chemicals":null,"comments_corrections":null,"source_flags":5,"s2_open_access_pdf_url":"https://advances.sciencemag.org/content/advances/3/4/e1602614.full.pdf","s2_open_access_landing_url":"https://www.semanticscholar.org/paper/0acd117521ef5aafb09fed02ab415523b330b058","s2_open_access_license":"CCBYNC","s2_open_access_status":"GOLD","pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"Researchers propose sparse regression for identifying governing partial differential equations for spatiotemporal systems. We propose a sparse regression method capable of discovering the governing partial differential equation(s) of a given system by time series measurements in the spatial domain. The regression framework relies on sparsity-promoting techniques to select the nonlinear and partial derivative terms of the governing equations that most accurately represent the data, bypassing a combinatorially large search through all possible candidate models. The method balances model complexity and regression accuracy by selecting a parsimonious model via Pareto analysis. Time series measurements can be made in an Eulerian framework, where the sensors are fixed spatially, or in a Lagrangian framework, where the sensors move with the dynamics. The method is computationally efficient, robust, and demonstrated to work on a variety of canonical problems spanning a number of scientific domains including Navier-Stokes, the quantum harmonic oscillator, and the diffusion equation. Moreover, the method is capable of disambiguating between potentially nonunique dynamical terms by using multiple time series taken with different initial data. Thus, for a traveling wave, the method can distinguish between a linear wave equation and the Korteweg–de Vries equation, for instance. The method provides a promising new technique for discovering governing equations and physical laws in parameterized spatiotemporal systems, where first-principles derivations are intractable.","claims":[{"public_id":"cl_5d32f7b0fa075da32cb868cfa2aa88d3","status":"active","text":"Sparse regression can discover governing partial differential equations from time series measurements in the spatial domain.","confidence":0.95,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_5d32f7b0fa075da32cb868cfa2aa88d3"},{"public_id":"cl_39dc7800444135680f1b0297e0c780e5","status":"active","text":"The method balances model complexity and regression accuracy by selecting a parsimonious model via Pareto analysis.","confidence":0.9,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_39dc7800444135680f1b0297e0c780e5"},{"public_id":"cl_5f2b8bb145681de422c82d0ec7c6cfc0","status":"active","text":"The method can disambiguate between a linear wave equation and the Korteweg–de Vries equation using multiple time series with different initial data.","confidence":0.9,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_5f2b8bb145681de422c82d0ec7c6cfc0"},{"public_id":"cl_dc992a6dc8117233d4846c5225448a53","status":"active","text":"The method works on Navier-Stokes, the quantum harmonic oscillator, and the diffusion equation.","confidence":0.95,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_dc992a6dc8117233d4846c5225448a53"}],"concepts":[{"public_id":"co_009048318a8e4e9c53d2774ab3a054c4","status":"active","name":"sparse regression","description":"A regression framework that uses sparsity-promoting techniques to select the nonlinear and partial derivative terms of governing equations.","types":["method"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_009048318a8e4e9c53d2774ab3a054c4"},{"public_id":"co_14e1866e3fa0eeb08239ee66f44b9df4","status":"active","name":"linear wave equation","description":"A type of traveling wave equation that the method can distinguish from the Korteweg–de Vries equation.","types":["equation"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_14e1866e3fa0eeb08239ee66f44b9df4"},{"public_id":"co_1f3f0c0d56e0352a975a27b9625cfd10","status":"active","name":"Korteweg–de Vries equation","description":"A nonlinear partial differential equation for traveling waves that the method can distinguish from the linear wave equation.","types":["equation"],"aliases":["KdV equation"],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_1f3f0c0d56e0352a975a27b9625cfd10"},{"public_id":"co_26c72ad62f3ff1aac50bb3b8ae2851c2","status":"active","name":"parsimonious model","description":"A model that balances complexity and accuracy, selected via Pareto analysis.","types":["model"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_26c72ad62f3ff1aac50bb3b8ae2851c2"},{"public_id":"co_2c41e0943cb0215b6974ac18c6157861","status":"active","name":"quantum harmonic oscillator","description":"A canonical problem from quantum mechanics used to demonstrate the method.","types":["equation","system"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_2c41e0943cb0215b6974ac18c6157861"},{"public_id":"co_35578bcde908f89a93918e0cfb1a6395","status":"active","name":"Navier-Stokes","description":"A canonical problem from fluid dynamics used to demonstrate the method.","types":["equation","system"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_35578bcde908f89a93918e0cfb1a6395"},{"public_id":"co_400b897b0c4d7b50cad790adc0b36b23","status":"active","name":"multiple time series","description":"Time series taken with different initial data used to disambiguate between potentially nonunique dynamical terms.","types":["data type"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_400b897b0c4d7b50cad790adc0b36b23"},{"public_id":"co_40b5244a74994cc67e9cfd60dc787054","status":"active","name":"partial differential equations","description":"Governing equations for spatiotemporal systems that the method aims to discover.","types":["mathematical object"],"aliases":["PDEs"],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_40b5244a74994cc67e9cfd60dc787054"},{"public_id":"co_4ce5d0cf9d4de085a8dccc7d14057a08","status":"active","name":"Pareto analysis","description":"A technique used to balance model complexity and regression accuracy by selecting a parsimonious model.","types":["technique"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_4ce5d0cf9d4de085a8dccc7d14057a08"},{"public_id":"co_7789b5ac5e65abc3b9ddf58402a7401b","status":"active","name":"time series measurements","description":"Measurements taken over time in the spatial domain, either in an Eulerian or Lagrangian framework.","types":["data type"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_7789b5ac5e65abc3b9ddf58402a7401b"},{"public_id":"co_89d71e55a4eea5e4d47e0fce4b9a1643","status":"active","name":"diffusion equation","description":"A canonical problem used to demonstrate the method.","types":["equation"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_89d71e55a4eea5e4d47e0fce4b9a1643"}],"external_ids":{"DOI":"10.1126/sciadv.1602614","ArXiv":"1609.06401","PubMed":28508044,"PubMedCentral":"5406137","MAG":2950893882,"DBLP":null,"ACL":null},"open_access":{"is_open_access":true,"pdf_url":"https://advances.sciencemag.org/content/advances/3/4/e1602614.full.pdf","landing_url":"https://www.semanticscholar.org/paper/0acd117521ef5aafb09fed02ab415523b330b058","source":"semantic_scholar","pdf_url_source":"semantic_scholar_open_access_pdf","license":"CCBYNC","status":"GOLD","reason":null},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":true,"full_text_source":"arxiv","count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":5},"paper_id":634943,"paper_uid":"1f676299-d151-4d08-94ec-74b5a72ddc8c","canonical_identity":{"paper_id":634943,"paper_uid":"1f676299-d151-4d08-94ec-74b5a72ddc8c","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/4575852"}