Machine Learning for Ultra High Throughput Screening of Organic Solar Cells: Solving the Needle in the Haystack Problem

Hußner, Markus; Pacalaj, Richard Adam; Müller‐Dieckert, Gerhard Olaf; Liu, Chao; Zhou, Zhisheng; Majeed, Nahdia; Greedy, Steve; Ramirez, Ivan; Li, Ning; Hosseini, Seyed Mehrdad; Uhrich, Christian; Brabec, Christoph Josef; Durrant, James; Deibel, Carsten; Ian, Roderick Charles

doi:10.1002/aenm.202303000

Journal article 176 views 21 downloads

Machine Learning for Ultra High Throughput Screening of Organic Solar Cells: Solving the Needle in the Haystack Problem

Markus Hußner

, Richard Adam Pacalaj

, Gerhard Olaf Müller‐Dieckert, Chao Liu, Zhisheng Zhou, Nahdia Majeed, Steve Greedy, Ivan Ramirez, Ning Li, Seyed Mehrdad Hosseini, Christian Uhrich, Christoph Josef Brabec, James Durrant, Carsten Deibel, Roderick Charles Ian MacKenzie

Advanced Energy Materials, Volume: 14, Issue: 3, Start page: 2303000

Swansea University Author: James Durrant

PDF | Version of Record

© 2023 The Authors. This is an open access article under the terms of the Creative Commons Attribution License (CC BY).
Download (4.28MB)

Check full text

DOI (Published version): 10.1002/aenm.202303000

Abstract

Over the last two decades the organic solar cell community has synthesized tens of thousands of novel polymers and small molecules in the search for an optimum light harvesting material. These materials are often crudely evaluated simply by measuring the current–voltage (JV) curves in the light to o...

Full description

Published in:	Advanced Energy Materials
ISSN:	1614-6832 1614-6840
Published:	Wiley 2024
Online Access:	Check full text
URI:	https://cronfa.swan.ac.uk/Record/cronfa70700

first_indexed	2025-10-16T11:20:07Z
last_indexed	2025-10-17T09:31:27Z
id	cronfa70700
recordtype	SURis
fullrecord	<?xml version="1.0"?><rfc1807><datestamp>2025-10-16T12:21:11.2278513</datestamp><bib-version>v2</bib-version><id>70700</id><entry>2025-10-16</entry><title>Machine Learning for Ultra High Throughput Screening of Organic Solar Cells: Solving the Needle in the Haystack Problem</title><swanseaauthors><author><sid>f3dd64bc260e5c07adfa916c27dbd58a</sid><firstname>James</firstname><surname>Durrant</surname><name>James Durrant</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-10-16</date><abstract>Over the last two decades the organic solar cell community has synthesized tens of thousands of novel polymers and small molecules in the search for an optimum light harvesting material. These materials are often crudely evaluated simply by measuring the current–voltage (JV) curves in the light to obtain power conversion efficiencies (PCEs). Materials with low PCEs are quickly disregarded in the search for higher efficiencies. More complex measurements such as frequency/time domain characterization that could explain why the material performed as it is often not performed as they are too time consuming/complex. This limited feedback forced the field to advance using a more or less random walk of material development and has significantly slowed progress. Herein, a simple technique based on machine learning that can quickly and accurately extract recombination time constants and charge carrier mobilities as a function of light intensity simply from light/dark JV curves alone. This technique reduces the time to fully analyze a working cell from weeks to seconds and opens up the possibility of not only fully characterizing new devices as they are fabricated, but also data mining historical data sets for promising materials the community has overlooked.</abstract><type>Journal Article</type><journal>Advanced Energy Materials</journal><volume>14</volume><journalNumber>3</journalNumber><paginationStart>2303000</paginationStart><paginationEnd/><publisher>Wiley</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1614-6832</issnPrint><issnElectronic>1614-6840</issnElectronic><keywords>drift diffusion, machine learning, organic photovoltaic, solar</keywords><publishedDay>19</publishedDay><publishedMonth>1</publishedMonth><publishedYear>2024</publishedYear><publishedDate>2024-01-19</publishedDate><doi>10.1002/aenm.202303000</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm>Another institution paid the OA fee</apcterm><funders>The authors thank Heliatek GmbH for funding MH's PhD through the EPSRC Centre for Doctoral Training in Renewable Energy Northeast Universities (ReNU). The authors also thank the Deutsche Forschungsgemeinschaft (DFG Research Unit FOR 5387 POPULAR, Project No. 461909888) for their support. R.A.P. would further like to acknowledge the support through the Centre for Processable Electronics CDT program as well as the ATIP project (grant number EP/L016702/1 and EP/T028513/1). This work was supported by the Engineering and Physical Sciences Research Council (grant number EP/S023836/1).</funders><projectreference/><lastEdited>2025-10-16T12:21:11.2278513</lastEdited><Created>2025-10-16T12:13:45.6891506</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Engineering and Applied Sciences - Materials Science and Engineering</level></path><authors><author><firstname>Markus</firstname><surname>Hußner</surname><orcid>0009-0005-1365-9052</orcid><order>1</order></author><author><firstname>Richard Adam</firstname><surname>Pacalaj</surname><orcid>0000-0002-6242-3880</orcid><order>2</order></author><author><firstname>Gerhard Olaf</firstname><surname>Müller‐Dieckert</surname><order>3</order></author><author><firstname>Chao</firstname><surname>Liu</surname><order>4</order></author><author><firstname>Zhisheng</firstname><surname>Zhou</surname><order>5</order></author><author><firstname>Nahdia</firstname><surname>Majeed</surname><order>6</order></author><author><firstname>Steve</firstname><surname>Greedy</surname><order>7</order></author><author><firstname>Ivan</firstname><surname>Ramirez</surname><order>8</order></author><author><firstname>Ning</firstname><surname>Li</surname><order>9</order></author><author><firstname>Seyed Mehrdad</firstname><surname>Hosseini</surname><order>10</order></author><author><firstname>Christian</firstname><surname>Uhrich</surname><order>11</order></author><author><firstname>Christoph Josef</firstname><surname>Brabec</surname><order>12</order></author><author><firstname>James</firstname><surname>Durrant</surname><order>13</order></author><author><firstname>Carsten</firstname><surname>Deibel</surname><order>14</order></author><author><firstname>Roderick Charles Ian</firstname><surname>MacKenzie</surname><orcid>0000-0002-8833-2872</orcid><order>15</order></author></authors><documents><document><filename>70700__35359__b8e5469ae87a416986a1205819143ecd.pdf</filename><originalFilename>70700.VOR.pdf</originalFilename><uploaded>2025-10-16T12:19:08.6243168</uploaded><type>Output</type><contentLength>4490977</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© 2023 The Authors. This is an open access article under the terms of the Creative Commons Attribution License (CC BY).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling	2025-10-16T12:21:11.2278513 v2 70700 2025-10-16 Machine Learning for Ultra High Throughput Screening of Organic Solar Cells: Solving the Needle in the Haystack Problem f3dd64bc260e5c07adfa916c27dbd58a James Durrant James Durrant true false 2025-10-16 Over the last two decades the organic solar cell community has synthesized tens of thousands of novel polymers and small molecules in the search for an optimum light harvesting material. These materials are often crudely evaluated simply by measuring the current–voltage (JV) curves in the light to obtain power conversion efficiencies (PCEs). Materials with low PCEs are quickly disregarded in the search for higher efficiencies. More complex measurements such as frequency/time domain characterization that could explain why the material performed as it is often not performed as they are too time consuming/complex. This limited feedback forced the field to advance using a more or less random walk of material development and has significantly slowed progress. Herein, a simple technique based on machine learning that can quickly and accurately extract recombination time constants and charge carrier mobilities as a function of light intensity simply from light/dark JV curves alone. This technique reduces the time to fully analyze a working cell from weeks to seconds and opens up the possibility of not only fully characterizing new devices as they are fabricated, but also data mining historical data sets for promising materials the community has overlooked. Journal Article Advanced Energy Materials 14 3 2303000 Wiley 1614-6832 1614-6840 drift diffusion, machine learning, organic photovoltaic, solar 19 1 2024 2024-01-19 10.1002/aenm.202303000 COLLEGE NANME COLLEGE CODE Swansea University Another institution paid the OA fee The authors thank Heliatek GmbH for funding MH's PhD through the EPSRC Centre for Doctoral Training in Renewable Energy Northeast Universities (ReNU). The authors also thank the Deutsche Forschungsgemeinschaft (DFG Research Unit FOR 5387 POPULAR, Project No. 461909888) for their support. R.A.P. would further like to acknowledge the support through the Centre for Processable Electronics CDT program as well as the ATIP project (grant number EP/L016702/1 and EP/T028513/1). This work was supported by the Engineering and Physical Sciences Research Council (grant number EP/S023836/1). 2025-10-16T12:21:11.2278513 2025-10-16T12:13:45.6891506 Faculty of Science and Engineering School of Engineering and Applied Sciences - Materials Science and Engineering Markus Hußner 0009-0005-1365-9052 1 Richard Adam Pacalaj 0000-0002-6242-3880 2 Gerhard Olaf Müller‐Dieckert 3 Chao Liu 4 Zhisheng Zhou 5 Nahdia Majeed 6 Steve Greedy 7 Ivan Ramirez 8 Ning Li 9 Seyed Mehrdad Hosseini 10 Christian Uhrich 11 Christoph Josef Brabec 12 James Durrant 13 Carsten Deibel 14 Roderick Charles Ian MacKenzie 0000-0002-8833-2872 15 70700__35359__b8e5469ae87a416986a1205819143ecd.pdf 70700.VOR.pdf 2025-10-16T12:19:08.6243168 Output 4490977 application/pdf Version of Record true © 2023 The Authors. This is an open access article under the terms of the Creative Commons Attribution License (CC BY). true eng http://creativecommons.org/licenses/by/4.0/
title	Machine Learning for Ultra High Throughput Screening of Organic Solar Cells: Solving the Needle in the Haystack Problem
spellingShingle	Machine Learning for Ultra High Throughput Screening of Organic Solar Cells: Solving the Needle in the Haystack Problem James Durrant
title_short	Machine Learning for Ultra High Throughput Screening of Organic Solar Cells: Solving the Needle in the Haystack Problem
title_full	Machine Learning for Ultra High Throughput Screening of Organic Solar Cells: Solving the Needle in the Haystack Problem
title_fullStr	Machine Learning for Ultra High Throughput Screening of Organic Solar Cells: Solving the Needle in the Haystack Problem
title_full_unstemmed	Machine Learning for Ultra High Throughput Screening of Organic Solar Cells: Solving the Needle in the Haystack Problem
title_sort	Machine Learning for Ultra High Throughput Screening of Organic Solar Cells: Solving the Needle in the Haystack Problem
author_id_str_mv	f3dd64bc260e5c07adfa916c27dbd58a
author_id_fullname_str_mv	f3dd64bc260e5c07adfa916c27dbd58a_***_James Durrant
author	James Durrant
author2	Markus Hußner Richard Adam Pacalaj Gerhard Olaf Müller‐Dieckert Chao Liu Zhisheng Zhou Nahdia Majeed Steve Greedy Ivan Ramirez Ning Li Seyed Mehrdad Hosseini Christian Uhrich Christoph Josef Brabec James Durrant Carsten Deibel Roderick Charles Ian MacKenzie
format	Journal article
container_title	Advanced Energy Materials
container_volume	14
container_issue	3
container_start_page	2303000
publishDate	2024
institution	Swansea University
issn	1614-6832 1614-6840
doi_str_mv	10.1002/aenm.202303000
publisher	Wiley
college_str	Faculty of Science and Engineering
hierarchytype
hierarchy_top_id	facultyofscienceandengineering
hierarchy_top_title	Faculty of Science and Engineering
hierarchy_parent_id	facultyofscienceandengineering
hierarchy_parent_title	Faculty of Science and Engineering
department_str	School of Engineering and Applied Sciences - Materials Science and Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Engineering and Applied Sciences - Materials Science and Engineering
document_store_str	1
active_str	0
description	Over the last two decades the organic solar cell community has synthesized tens of thousands of novel polymers and small molecules in the search for an optimum light harvesting material. These materials are often crudely evaluated simply by measuring the current–voltage (JV) curves in the light to obtain power conversion efficiencies (PCEs). Materials with low PCEs are quickly disregarded in the search for higher efficiencies. More complex measurements such as frequency/time domain characterization that could explain why the material performed as it is often not performed as they are too time consuming/complex. This limited feedback forced the field to advance using a more or less random walk of material development and has significantly slowed progress. Herein, a simple technique based on machine learning that can quickly and accurately extract recombination time constants and charge carrier mobilities as a function of light intensity simply from light/dark JV curves alone. This technique reduces the time to fully analyze a working cell from weeks to seconds and opens up the possibility of not only fully characterizing new devices as they are fabricated, but also data mining historical data sets for promising materials the community has overlooked.
published_date	2024-01-19T05:31:27Z
_version_	1851098071552753664
score	11.089572

Machine Learning for Ultra High Throughput Screening of Organic Solar Cells: Solving the Needle in the Haystack Problem

Similar Items