Speeding up high-throughput characterization of materials libraries by active learning: autonomous electrical resistance measurements

High-throughput experimentation enables efficient search space exploration for the discovery and optimization of new materials. However, large search spaces of, e.g., compositionally complex materials, require decreasing characterization times significantly. Here, an autonomous measurement algorithm...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Thelen, Felix, Banko, Lars, Zehl, Rico, Baha, Sabrina, Ludwig, Alfred
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Thelen, Felix
Banko, Lars
Zehl, Rico
Baha, Sabrina
Ludwig, Alfred
description High-throughput experimentation enables efficient search space exploration for the discovery and optimization of new materials. However, large search spaces of, e.g., compositionally complex materials, require decreasing characterization times significantly. Here, an autonomous measurement algorithm was developed, which leverages active learning based on a Gaussian process model capable of iteratively scanning a materials library based on the highest uncertainty. The algorithm is applied to a four-point probe electrical resistance measurement device, frequently used to obtain indications for regions of interest in materials libraries. Ten materials libraries with different complexities of composition and property trends are analyzed to validate the model. By stopping the process before the entire library is characterized and predicting the remaining measurement areas, the measurement efficiency can be improved drastically. As robustness is essential for autonomous measurements, intrinsic outlier handling is built into the model and a dynamic stopping criterion based on the mean predicted covariance is proposed. A measurement time reduction of about 70-90% was observed while still ensuring an accuracy of above 90%.
doi_str_mv 10.48550/arxiv.2306.17277
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2306_17277</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2306_17277</sourcerecordid><originalsourceid>FETCH-LOGICAL-a677-27a5653b55a6e73f35f563edbbd4c5fea887303813cd2abee1e59a686de4f33f3</originalsourceid><addsrcrecordid>eNotkL1OwzAURrMwoMIDMHFfICGJYzuwoYo_qRID3aNr5zqxlMSR7VSUnfcmLZ0-fdLRGU6S3BV5VtWc5w_ov-0hK1kuskKWUl4nv18zUWunDpYZetv1aey9W7p-XiLoHj3qSN7-YLRuAmdgxNPHIcBglUdvKYA6worZA8FA6KfV9gS4RDe50S0BaCAdvdU4gKdgQ8RJE4yEYfE00hTDTXJlViXdXnaT7F9f9tv3dPf59rF93qUopExLiVxwpjhHQZIZxg0XjFql2kpzQ1jXkuWsLphuS1REBfFHFLVoqTJs5TfJ_b_23KGZvR3RH5tTj-bcg_0BSVpgKw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Speeding up high-throughput characterization of materials libraries by active learning: autonomous electrical resistance measurements</title><source>arXiv.org</source><creator>Thelen, Felix ; Banko, Lars ; Zehl, Rico ; Baha, Sabrina ; Ludwig, Alfred</creator><creatorcontrib>Thelen, Felix ; Banko, Lars ; Zehl, Rico ; Baha, Sabrina ; Ludwig, Alfred</creatorcontrib><description>High-throughput experimentation enables efficient search space exploration for the discovery and optimization of new materials. However, large search spaces of, e.g., compositionally complex materials, require decreasing characterization times significantly. Here, an autonomous measurement algorithm was developed, which leverages active learning based on a Gaussian process model capable of iteratively scanning a materials library based on the highest uncertainty. The algorithm is applied to a four-point probe electrical resistance measurement device, frequently used to obtain indications for regions of interest in materials libraries. Ten materials libraries with different complexities of composition and property trends are analyzed to validate the model. By stopping the process before the entire library is characterized and predicting the remaining measurement areas, the measurement efficiency can be improved drastically. As robustness is essential for autonomous measurements, intrinsic outlier handling is built into the model and a dynamic stopping criterion based on the mean predicted covariance is proposed. A measurement time reduction of about 70-90% was observed while still ensuring an accuracy of above 90%.</description><identifier>DOI: 10.48550/arxiv.2306.17277</identifier><language>eng</language><subject>Physics - Computational Physics ; Physics - Materials Science</subject><creationdate>2023-06</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,781,886</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2306.17277$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2306.17277$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Thelen, Felix</creatorcontrib><creatorcontrib>Banko, Lars</creatorcontrib><creatorcontrib>Zehl, Rico</creatorcontrib><creatorcontrib>Baha, Sabrina</creatorcontrib><creatorcontrib>Ludwig, Alfred</creatorcontrib><title>Speeding up high-throughput characterization of materials libraries by active learning: autonomous electrical resistance measurements</title><description>High-throughput experimentation enables efficient search space exploration for the discovery and optimization of new materials. However, large search spaces of, e.g., compositionally complex materials, require decreasing characterization times significantly. Here, an autonomous measurement algorithm was developed, which leverages active learning based on a Gaussian process model capable of iteratively scanning a materials library based on the highest uncertainty. The algorithm is applied to a four-point probe electrical resistance measurement device, frequently used to obtain indications for regions of interest in materials libraries. Ten materials libraries with different complexities of composition and property trends are analyzed to validate the model. By stopping the process before the entire library is characterized and predicting the remaining measurement areas, the measurement efficiency can be improved drastically. As robustness is essential for autonomous measurements, intrinsic outlier handling is built into the model and a dynamic stopping criterion based on the mean predicted covariance is proposed. A measurement time reduction of about 70-90% was observed while still ensuring an accuracy of above 90%.</description><subject>Physics - Computational Physics</subject><subject>Physics - Materials Science</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotkL1OwzAURrMwoMIDMHFfICGJYzuwoYo_qRID3aNr5zqxlMSR7VSUnfcmLZ0-fdLRGU6S3BV5VtWc5w_ov-0hK1kuskKWUl4nv18zUWunDpYZetv1aey9W7p-XiLoHj3qSN7-YLRuAmdgxNPHIcBglUdvKYA6worZA8FA6KfV9gS4RDe50S0BaCAdvdU4gKdgQ8RJE4yEYfE00hTDTXJlViXdXnaT7F9f9tv3dPf59rF93qUopExLiVxwpjhHQZIZxg0XjFql2kpzQ1jXkuWsLphuS1REBfFHFLVoqTJs5TfJ_b_23KGZvR3RH5tTj-bcg_0BSVpgKw</recordid><startdate>20230629</startdate><enddate>20230629</enddate><creator>Thelen, Felix</creator><creator>Banko, Lars</creator><creator>Zehl, Rico</creator><creator>Baha, Sabrina</creator><creator>Ludwig, Alfred</creator><scope>GOX</scope></search><sort><creationdate>20230629</creationdate><title>Speeding up high-throughput characterization of materials libraries by active learning: autonomous electrical resistance measurements</title><author>Thelen, Felix ; Banko, Lars ; Zehl, Rico ; Baha, Sabrina ; Ludwig, Alfred</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a677-27a5653b55a6e73f35f563edbbd4c5fea887303813cd2abee1e59a686de4f33f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Physics - Computational Physics</topic><topic>Physics - Materials Science</topic><toplevel>online_resources</toplevel><creatorcontrib>Thelen, Felix</creatorcontrib><creatorcontrib>Banko, Lars</creatorcontrib><creatorcontrib>Zehl, Rico</creatorcontrib><creatorcontrib>Baha, Sabrina</creatorcontrib><creatorcontrib>Ludwig, Alfred</creatorcontrib><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Thelen, Felix</au><au>Banko, Lars</au><au>Zehl, Rico</au><au>Baha, Sabrina</au><au>Ludwig, Alfred</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Speeding up high-throughput characterization of materials libraries by active learning: autonomous electrical resistance measurements</atitle><date>2023-06-29</date><risdate>2023</risdate><abstract>High-throughput experimentation enables efficient search space exploration for the discovery and optimization of new materials. However, large search spaces of, e.g., compositionally complex materials, require decreasing characterization times significantly. Here, an autonomous measurement algorithm was developed, which leverages active learning based on a Gaussian process model capable of iteratively scanning a materials library based on the highest uncertainty. The algorithm is applied to a four-point probe electrical resistance measurement device, frequently used to obtain indications for regions of interest in materials libraries. Ten materials libraries with different complexities of composition and property trends are analyzed to validate the model. By stopping the process before the entire library is characterized and predicting the remaining measurement areas, the measurement efficiency can be improved drastically. As robustness is essential for autonomous measurements, intrinsic outlier handling is built into the model and a dynamic stopping criterion based on the mean predicted covariance is proposed. A measurement time reduction of about 70-90% was observed while still ensuring an accuracy of above 90%.</abstract><doi>10.48550/arxiv.2306.17277</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2306.17277
ispartof
issn
language eng
recordid cdi_arxiv_primary_2306_17277
source arXiv.org
subjects Physics - Computational Physics
Physics - Materials Science
title Speeding up high-throughput characterization of materials libraries by active learning: autonomous electrical resistance measurements
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-12T15%3A32%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Speeding%20up%20high-throughput%20characterization%20of%20materials%20libraries%20by%20active%20learning:%20autonomous%20electrical%20resistance%20measurements&rft.au=Thelen,%20Felix&rft.date=2023-06-29&rft_id=info:doi/10.48550/arxiv.2306.17277&rft_dat=%3Carxiv_GOX%3E2306_17277%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true