A data-driven method for automated data superposition with applications in soft matter science
The superposition of data sets with internal parametric self-similarity is a longstanding and widespread technique for the analysis of many types of experimental data across the physical sciences. Typically, this superposition is performed manually, or recently through the application of one of a fe...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Cambridge University Press
2023-01-01
|
| Series: | Data-Centric Engineering |
| Subjects: | |
| Online Access: | https://www.cambridge.org/core/product/identifier/S2632673623000035/type/journal_article |
| _version_ | 1797821043836977152 |
|---|---|
| author | Kyle R. Lennon Gareth H. McKinley James W. Swan |
| author_facet | Kyle R. Lennon Gareth H. McKinley James W. Swan |
| author_sort | Kyle R. Lennon |
| collection | DOAJ |
| description | The superposition of data sets with internal parametric self-similarity is a longstanding and widespread technique for the analysis of many types of experimental data across the physical sciences. Typically, this superposition is performed manually, or recently through the application of one of a few automated algorithms. However, these methods are often heuristic in nature, are prone to user bias via manual data shifting or parameterization, and lack a native framework for handling uncertainty in both the data and the resulting model of the superposed data. In this work, we develop a data-driven, nonparametric method for superposing experimental data with arbitrary coordinate transformations, which employs Gaussian process regression to learn statistical models that describe the data, and then uses maximum a posteriori estimation to optimally superpose the data sets. This statistical framework is robust to experimental noise and automatically produces uncertainty estimates for the learned coordinate transformations. Moreover, it is distinguished from black-box machine learning in its interpretability—specifically, it produces a model that may itself be interrogated to gain insight into the system under study. We demonstrate these salient features of our method through its application to four representative data sets characterizing the mechanics of soft materials. In every case, our method replicates results obtained using other approaches, but with reduced bias and the addition of uncertainty estimates. This method enables a standardized, statistical treatment of self-similar data across many fields, producing interpretable data-driven models that may inform applications such as materials classification, design, and discovery. |
| first_indexed | 2024-03-13T09:46:57Z |
| format | Article |
| id | doaj.art-d6c14fb609044866a24089a864a232d4 |
| institution | Directory Open Access Journal |
| issn | 2632-6736 |
| language | English |
| last_indexed | 2024-03-13T09:46:57Z |
| publishDate | 2023-01-01 |
| publisher | Cambridge University Press |
| record_format | Article |
| series | Data-Centric Engineering |
| spelling | doaj.art-d6c14fb609044866a24089a864a232d42023-05-25T04:00:24ZengCambridge University PressData-Centric Engineering2632-67362023-01-01410.1017/dce.2023.3A data-driven method for automated data superposition with applications in soft matter scienceKyle R. Lennon0https://orcid.org/0000-0002-1251-5461Gareth H. McKinley1James W. Swan2Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USADepartment of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USADepartment of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USAThe superposition of data sets with internal parametric self-similarity is a longstanding and widespread technique for the analysis of many types of experimental data across the physical sciences. Typically, this superposition is performed manually, or recently through the application of one of a few automated algorithms. However, these methods are often heuristic in nature, are prone to user bias via manual data shifting or parameterization, and lack a native framework for handling uncertainty in both the data and the resulting model of the superposed data. In this work, we develop a data-driven, nonparametric method for superposing experimental data with arbitrary coordinate transformations, which employs Gaussian process regression to learn statistical models that describe the data, and then uses maximum a posteriori estimation to optimally superpose the data sets. This statistical framework is robust to experimental noise and automatically produces uncertainty estimates for the learned coordinate transformations. Moreover, it is distinguished from black-box machine learning in its interpretability—specifically, it produces a model that may itself be interrogated to gain insight into the system under study. We demonstrate these salient features of our method through its application to four representative data sets characterizing the mechanics of soft materials. In every case, our method replicates results obtained using other approaches, but with reduced bias and the addition of uncertainty estimates. This method enables a standardized, statistical treatment of self-similar data across many fields, producing interpretable data-driven models that may inform applications such as materials classification, design, and discovery.https://www.cambridge.org/core/product/identifier/S2632673623000035/type/journal_articleBayesian statisticsGaussian process regressionmethod of reduced variablesself-similarity |
| spellingShingle | Kyle R. Lennon Gareth H. McKinley James W. Swan A data-driven method for automated data superposition with applications in soft matter science Data-Centric Engineering Bayesian statistics Gaussian process regression method of reduced variables self-similarity |
| title | A data-driven method for automated data superposition with applications in soft matter science |
| title_full | A data-driven method for automated data superposition with applications in soft matter science |
| title_fullStr | A data-driven method for automated data superposition with applications in soft matter science |
| title_full_unstemmed | A data-driven method for automated data superposition with applications in soft matter science |
| title_short | A data-driven method for automated data superposition with applications in soft matter science |
| title_sort | data driven method for automated data superposition with applications in soft matter science |
| topic | Bayesian statistics Gaussian process regression method of reduced variables self-similarity |
| url | https://www.cambridge.org/core/product/identifier/S2632673623000035/type/journal_article |
| work_keys_str_mv | AT kylerlennon adatadrivenmethodforautomateddatasuperpositionwithapplicationsinsoftmatterscience AT garethhmckinley adatadrivenmethodforautomateddatasuperpositionwithapplicationsinsoftmatterscience AT jameswswan adatadrivenmethodforautomateddatasuperpositionwithapplicationsinsoftmatterscience AT kylerlennon datadrivenmethodforautomateddatasuperpositionwithapplicationsinsoftmatterscience AT garethhmckinley datadrivenmethodforautomateddatasuperpositionwithapplicationsinsoftmatterscience AT jameswswan datadrivenmethodforautomateddatasuperpositionwithapplicationsinsoftmatterscience |