[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126556-en":3,"doc-seo-126556-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},126556,13056712833777,"Logic","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","A New Machine Learning Approach Based on Range Corrected Deep Potential Model for Efficient Vibrational Frequency Computation","Vibrational spectrum simulation requires ensemble averaging and becomes costly with high-accuracy quantum methods. A machine learning framework is introduced using the range-corrected deep potential (DPRc) model to accelerate vibrational frequency computations. The method is applied to C-O stretching vibrational frequency shifts in a formic acid–water solution, dividing the system into probe and solvent regions. Probe-region designs and QVP-prepared datasets are evaluated, while a standard deep potential baseline tests interaction cut-off effects. Using a single-molecule probe region yields the best accuracy, about tenfold faster than regular DP and roughly fourfold reduced training time, with minimal accuracy loss despite reduced solvent–solvent distance information. The protocol is practical and extensible to other physical quantities.","arXiv :2303 . 15969v2 [physics .chem-ph] 1 Apr 2023  \nA New Machine Learning Approach Based on Range Corrected Deep Potential Model for Efficient Vibrational Frequency Computation  \nJitai Yang, Yang Cong, and Hui Li 􀀃  \nInstitute of Theoretical Chemistry, College of Chemistry, Jilin University, 2519 Jiefang  \nRoad, Changchun 130023, P.R. China  \nE-mail: [Prof_huili@jlu.edu.cn](Prof_huili@jlu.edu.cn)  \nAbstract  \nVibrational spectrum simulation, as an ensemble average result, can be very time consuming when using high accuracy methods. Here, we introduce a new machine learning approach based on the range corrected deep potential (DPRc) model to improve computing efficiency. The approach was applied to computing C ~~ ~~ O stretching vibrational frequency shifts of formic acid-water solution. DPRc is adapted for frequency shift calculation. The system was divided into “probe region” and “solvent region” by atom. Three kinds of “probe region” were tested: single atom with atomic contribution correction, a single atom, and a single molecule. All data sets were prepared using by Quantum Vibration Perturbation (QVP) approach. The deep potential (DP) model was also adapted for frequency shift calculation for comparison, and different interaction cut-off radii were tested. The single molecule “probe region” results show the best accuracy, running roughly ten times faster than regular DP, while reducing the training time by a factor of about four, making it fully applicable in practice. The results show  \nthat dropping information of interaction distances between solvent atoms can significantly increase computing and training efficiency while ensuring little loss of accuracy.  \nThe protocol is practical, easy to apply, and extendable to calculating other physical quantities.  \n1 Introduction  \nVibrational spectroscopy is a powerful experimental detection technique used in various systems, including molecular clusters, solids, solutions, proteins, and surface systems. 1–7 With the help of theoretical simulations, experimental spectra can be interpreted and gain additional insights such as dynamic spectral diffusion, vibrational quantum effects, and the complexity of the environment at the atomic level. Ensemble average must be performed if explicitly considering the dynamic and complex chemical environment around the chromophore. The average can be either based on a single chromophore or from a group consisting of all molecules. Because there are fewer atoms when starting with a single chromophore molecule, higher precision and more rigorous treatment can be utilized, and then undertake more analysis from a molecular view, such as solvatochromism and combining hydrogen bond analysis. However, introducing high precision or rigorous methods limits computing efficiency, and approximations must be reintroduced.8–13  \nThe Quantum Vibration Perturbation (QVP) approach is accurate and can handle the molecular quantum vibrational effect in complex systems. 14–18 Using contracted and localized basis from potential optimized discrete variable representation (PODVR), 19 the QVP approach is affordable in picosecond time scale or calculating tens of thousands of frequencies but still challenging in nanosecond time scale. Multi-dimension vibrational modes coupling problem also poses rigorous efficiency requirements.  \nIn particular, due to the development of the versatility of machine learning in recent years, machine learning methods can also be introduced to solve the efficiency problem in computational chemistry. Many models have been created for potential calculation and take  \nfunctions of atom coordinates as their inputs. Naturally, these methods can be expanded to compute other physical quantities. In this work, we are interested in vibrational frequencies and there have been many related studies.20–25 Using artificial neural networks (ANN) with atom-centered symmetry functions (ACSFs), Kananenka et al. reduced their map method's errors by more than 25 cm􀀀1 . The ","cbCait2nV4NSDbWD","https://ap.wps.com/l/cbCait2nV4NSDbWD","pdf",13629389,1,22,"English","en",105,"# Abstract\n# Introduction","[{\"question\":\"Why is vibrational spectrum simulation computationally expensive?\",\"answer\":\"Ensemble averaging over complex, dynamic chemical environments is required, and high-accuracy methods make the simulation time-consuming.\"},{\"question\":\"How does the proposed DPRc machine learning approach improve efficiency?\",\"answer\":\"It uses a range-corrected deep potential model by separating the system into probe and solvent regions and adapting DPRc for frequency-shift calculations, reducing costly interaction information without significant accuracy loss.\"},{\"question\":\"What probe-region setup performed best in the C-O stretching frequency shift study?\",\"answer\":\"The single-molecule probe region showed the best accuracy, running roughly ten times faster than regular DP and reducing training time by about four times.\"}]","A New Machine Learning Approach Based on Range Corrected Deep Potential Model for Efficient Vibrational Frequency Computation | PDF",1785933311,55,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"a-new-machine-learning-approach-based-on-range-corrected-deep-potential-model-for-efficient-vibrational-frequency-computation","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/a-new-machine-learning-approach-based-on-range-corrected-deep-potential-model-for-efficient-vibrational-frequency-computation/126556/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is vibrational spectrum simulation computationally expensive?","Question",{"text":76,"@type":77},"Ensemble averaging over complex, dynamic chemical environments is required, and high-accuracy methods make the simulation time-consuming.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the proposed DPRc machine learning approach improve efficiency?",{"text":81,"@type":77},"It uses a range-corrected deep potential model by separating the system into probe and solvent regions and adapting DPRc for frequency-shift calculations, reducing costly interaction information without significant accuracy loss.",{"name":83,"@type":74,"acceptedAnswer":84},"What probe-region setup performed best in the C-O stretching frequency shift study?",{"text":85,"@type":77},"The single-molecule probe region showed the best accuracy, running roughly ten times faster than regular DP and reducing training time by about four times.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]