[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-290965-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-290965-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","towards-a-fast-machine-learning-assisted-prediction-of-the-mechanoelectric-response-inorganic-crystals","Towards a fast machine-learning-assisted prediction of the mechanoelectric response inorganic crystals","","Research presents a fast computational protocol to predict the mechanoelectric response of inorganic crystals relevant to wearable electronics, e-skins, and pressure sensors. The method integrates molecular dynamics, density functional theory, machine learning, and kinetic Monte Carlo to overcome the heavy first-principles cost of computing figures of merit. A fast ML model evaluates millions of molecular electronic interactions affected by thermal fluctuations, enabling efficient prediction of charge mobility under mechanical deformation. Results for C10-DNBDT-NW align with experiments, supporting strain screening and faster materials discovery.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/towards-a-fast-machine-learning-assisted-prediction-of-the-mechanoelectric-response-inorganic-crystals/290965/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/towards-a-fast-machine-learning-assisted-prediction-of-the-mechanoelectric-response-inorganic-crystals/290965.png","ImageObject",300,407,{"name":42,"@type":43},"Quinn","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-29","2026-09-17",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",8,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does the protocol aim to solve?","Question",{"text":63,"@type":64},"It targets the lack of fast and reliable computational protocols for predicting relevant figures of merit from first principles, which is computationally expensive.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"Which computational methods are combined in the proposed approach?",{"text":68,"@type":64},"Molecular dynamics, density functional theory, machine learning, and kinetic Monte Carlo simulations are integrated to enable efficient prediction.",{"name":70,"@type":61,"acceptedAnswer":71},"How is the protocol validated and what does it enable?",{"text":72,"@type":64},"Predictions of charge mobility versus mechanical deformation for C10-DNBDT-NW are consistent with experimental measurements, demonstrating potential for screening materials with desired mechanoelectric properties.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},290965,1789643053,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":55,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":123,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":80,"read_time":143,"preview_page_count":4},962075114765,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","Journal of  \nMaterials Chemistry C  \n|  | \u003Cbr>APER   |\n| --- | --- |\n| P |  |\n|  |  |\n\nCite this: J. Mater. Chem. C, 2023, 11, 12297  \nReceived 26th June 2023, Accepted 18th August 2023  \nDOI: 10.1039/d3tc02235h[rsc.li/materials-c](rsc.li/materials-c)  \nTowards a fast machine-learning-assisted prediction of the mechanoelectric response inorganic crystals†  \nDaniele Padula,  *a Leonardo Barneschi,  a Andrea Peluso,  b  \nTommaso Cinagliaa and Alessandro Landi  *b  \nOrganic semiconductors can improve the performance of wearable electronics, e-skins, and pressure sensors by exploiting their mechanoelectric response. However, identifying new materials for these applications is challenging due to the lack of fast and reliable computational protocols, whose major limitation is the computational burden required to evaluate the relevant figures of merit from first principles. To overcome this challenge, we present a new protocol that combines molecular dynamics, density functional theory, machine learning, and kinetic Monte Carlo simulations. The fast machine learning model enables the evaluation of millions of specific electronic interactions between molecules and their thermal fluctuations, which play a key role in modulating charge transport. We use this protocol to study the dependence of charge mobility on mechanical deformations for C10-DNBDT-NW. Several analyses are performed to rationalise and predict the impact of strain on the material in a reduced amount of time. The predictions are consistent with experimental measurements, indicating its potential for screening themechanoelectric response to identify materials with the desired properties. This new protocol presents aneffective approach to predict the performance of organic semiconductors under external mechanical strain, which could lead to the discovery of new materials for advanced technologies.  \nOne of the most praised advantages regarding the adoption of organic semiconductors (OSCs) is their flexibility.1 This property, a consequence of the fact that aggregates of organic molecules are held together by weak van der Waals interactions, enables a range of applications that are not possible with other types of substrates, ranging from already commercial devices, such as flexible OLED displays,2–4 to more specialized applications,5–7 such as skin-wearable solar cells,8 biosensors,9 stretchable transistors,10–12 flexible actuators,13 which are still under study. Apart from specific applications where flexibility is required, mechanical strain can also be used as an ingenious way to modify the electronic properties of a material: examples of performance increase upon mechanical deformation are well  \na Dipartimento di Biotecnologie, Chimica e Farmacia, Universit di Siena, Via A. Moro 2, 53100 Siena, Italy. E-mail: [daniele.padula@unisi.it](daniele.padula@unisi.it)  \nb Dipartimento di Chimica e Biologia Adolfo Zambelli, Universit di Salerno, Via Giovanni Paolo II, I-84084 Fisciano, SA, Italy. E-mail: [alelandi1@unisa.it](alelandi1@unisa.it)[ ](alelandi1@unisa.it)† Electronic supplementary information (ESI) available: Parameters for the QMD-FF derived for C10-DNBDT-NW, further details for simulations, geometries and transfer integral used to train ML models, description of ML models with hyperparameter tuning, performance on the test set, and learning curves, details on the  \ncalculation of spectral densities, details and results on kMC simulations. Electronic versions of data are available at this public GitHub repository [https://github.com/](https://github.com/)[ ](https://github.com/)dpadula85/OFET_strain. See DOI: [https://doi.org/10.1039/d3tc02235h](https://doi.org/10.1039/d3tc02235h)  \nknown and commercially practicable for silicon-based devices,14 where increases of electron and hole mobilities up to 100% have been achieved.15  \nThe understanding of the interplay between mechanical and electronic properties of OSCs is fundamental for many reasons: first of all, it is ","cbCaiokZ6iyemlKv","https://ap.wps.com/l/cbCaiokZ6iyemlKv","pdf",2084389,"English","# Introduction\n## Organic semiconductors and mechanoelectric effects\n## Challenges in fast computational prediction\n## Integrated protocol for strain-dependent charge transport\n## Prior studies and motivation","[{\"question\":\"What problem does the protocol aim to solve?\",\"answer\":\"It targets the lack of fast and reliable computational protocols for predicting relevant figures of merit from first principles, which is computationally expensive.\"},{\"question\":\"Which computational methods are combined in the proposed approach?\",\"answer\":\"Molecular dynamics, density functional theory, machine learning, and kinetic Monte Carlo simulations are integrated to enable efficient prediction.\"},{\"question\":\"How is the protocol validated and what does it enable?\",\"answer\":\"Predictions of charge mobility versus mechanical deformation for C10-DNBDT-NW are consistent with experimental measurements, demonstrating potential for screening materials with desired mechanoelectric properties.\"}]","Towards a fast machine-learning-assisted prediction of the mechanoelectric response inorganic crystals | PDF",25]