[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128405-en":3,"doc-seo-128405-105":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},128405,8796095027276,"Valentina","https://avatar.qwps.com/avatar/d3BzX2FwX3Rlc3RfMjUxMTI2XzAxODA=",8,"Research & Report","Analysis of Machine Learning Algorithms for the Computer Simulation of Moisture Sorption Isotherms of Coffee Beans - read online","Digital twin–based machine learning techniques improve control of storage conditions for dried products by extending classical water sorption isotherm modeling with additional process variables. Water sorption isotherms for dried parchment and green coffee beans were measured experimentally at 25, 35, and 45 °C using the dynamic dew point (DDI) method. SVM, random forest (RF), and ANN simultaneously modeled all datasets with 75% training and 25% validation. Hyperparameters were tuned by minimizing MSE and evaluated via multiway ANOVA using MRE, R2, and computation time, showing SVM as best (MRE \u003C 1%, R2 > 99%, CT \u003C 13 s), enabling fast moisture-content prediction and supporting industrial storage management.","Food and Bioprocess Technology (2025) 18:5419–5430  \n[https://doi.org/10.1007/s1](https://doi.org/10.1007/s1) 1947-025-03785-x  \nAnalysis of Machine Learning Algorithms for the Computer Simulation of Moisture Sorption Isotherms of Coffee Beans  \nGentil A. Collazos‑Escobar1,2 · Nelson Gutiérrez‑Guzmán2 · Henry A. Váquiro3 · José V. García‑Pérez1 · Juan A. Cárcel1  \nReceived: 19 November 2024 / Accepted: 11 February 2025 / Published online: 18 February 2025 © The Author(s) 2025, corrected publication 2025  \nAbstract  \nDigital twin–based machine learning (ML) techniques can improve the control of the storage conditions of dried products, strengthening the classical water sorption isotherm–based approach by including additional process variables. In this study, water sorption isotherms of dried parchment and green coffee beans were experimentally determined at 25, 35, and 45 °C using the dynamic dew point (DDI) method. Experimental data (both coffee bean types and temperatures) were simultaneously modeled by means of three ML techniques, support vector machine (SVM), random forest (RF), and artificial neural networks (ANN), with 75% of data used for model training and 25% for validation. The hyperparameters were identified by minimizing the mean square error (MSE). The ML model’s accuracy was addressed by a multiway ANOVA on the mean relative error (MRE), the coefficient of determination (R2), and the computation time (CT) . The sorption isotherms were significantly (p-value \u003C 0.05) affected by the type of coffee and the temperature. The SVM model provided the best fit (MRE \u003C 1% and R2 > 99%) in a reasonable CT (\u003C 13 s) . These results revealed the potential of ML models as a robust tool for the fast prediction of the equilibrium moisture content, including additional variables such as the type of coffee stage (dried parchment or green) and temperature; this paves the way for their industrial-level implementation to assist storage management.  \nKeywords Dynamic dew point · Machine learning modeling · Parchment coffee · Green coffee · Process optimization · Real-time moisture monitoring  \nIntroduction  \nIn terms of global consumption, coffee is one of the most important agricultural commodities (Collazos-Escobar et al., 2022), and this is due to its sensory attributes, stimulating effects, and health benefits (Scholz et al., 2018) . The sensory quality characteristics of the final coffee beverage depended not only on the steps followed during its harvesting, but also  \n* Juan A. Cárcel[jcarcel@tal.upv.es](jcarcel@tal.upv.es)  \n1 Grupo de Análisis y Simulación de Procesos Agroalimentarios (ASPA), Instituto Universitario de Ingeniería de Alimentos – FoodUPV, Universitat Politècnica de València, C/Camí de Vera S/N, Edificio 3F, 46022 Valencia, Spain  \n2 Centro Surcolombiano de Investigación en Café CESURCAFÉ, Universidad Surcolombiana,  \n410001 Neiva-Huila, Colombia  \n3 Facultad de Ingeniería Agronómica, Universidad del Tolima, 730006 Ibagué-Tolima, Colombia  \non those taken in the post-harvesting, such as the drying, storage, roasting, grinding, and other preparation processes. These operations greatly contribute to the characteristic sensory attributes of coffee (Barbosa et al., 2019) .  \nStorage is one of the most relevant post-harvest steps in coffee processing because its impact on the sensory characteristics of the final product (Meira et al. , 2013) . Thus, most of the coffee is cultivated and processed on farms in mountains where the relative humidity is high (Donovan et al. , 2019) . In the Colombian coffee-growing region, the standard post-harvest process includes depulping, soaking/ fermentation, and drying. Subsequently, the coffee beans are stored with (parchment coffee) and/or without (green coffee) the parchment layer: this usually takes place in big warehouses under the same conditions, which have to be optimum to maintain the quality (Tripetch & Borompichaichartkul, 2019) .  \nThe water sorption isotherms represent the","cbCaioL7IbDoVnH3","https://ap.wps.com/l/cbCaioL7IbDoVnH3","pdf",1386758,1,12,"English","en",105,"# Abstract\n## Machine learning–based modeling approach\n## Experimental setup and temperatures\n## Model training, validation, and hyperparameter tuning\n## Evaluation metrics and statistical analysis\n## Key findings and industrial implications","[{\"question\":\"Which machine learning algorithms were used to model the coffee moisture sorption isotherms?\",\"answer\":\"The study modeled experimental isotherm data using three techniques: support vector machine (SVM), random forest (RF), and artificial neural networks (ANN).\"},{\"question\":\"How were the moisture sorption isotherms for coffee beans measured?\",\"answer\":\"Water sorption isotherms were experimentally determined at 25, 35, and 45 °C using the dynamic dew point (DDI) method for both dried parchment and green coffee beans.\"},{\"question\":\"Which model achieved the best accuracy and performance results?\",\"answer\":\"SVM provided the best fit, with mean relative error under 1%, R2 above 99%, and computation time below 13 seconds, as supported by the evaluation metrics and statistical testing.\"}]","Analysis of Machine Learning Algorithms for the Computer Simulation of Moisture Sorption Isotherms of Coffee Beans - read online | PDF",1785947336,30,{"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},"analysis-of-machine-learning-algorithms-for-the-computer-simulation-of-moisture-sorption-isotherms-of-coffee-beans-read-online","",{"@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/analysis-of-machine-learning-algorithms-for-the-computer-simulation-of-moisture-sorption-isotherms-of-coffee-beans-read-online/128405/",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},"Which machine learning algorithms were used to model the coffee moisture sorption isotherms?","Question",{"text":76,"@type":77},"The study modeled experimental isotherm data using three techniques: support vector machine (SVM), random forest (RF), and artificial neural networks (ANN).","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How were the moisture sorption isotherms for coffee beans measured?",{"text":81,"@type":77},"Water sorption isotherms were experimentally determined at 25, 35, and 45 °C using the dynamic dew point (DDI) method for both dried parchment and green coffee beans.",{"name":83,"@type":74,"acceptedAnswer":84},"Which model achieved the best accuracy and performance results?",{"text":85,"@type":77},"SVM provided the best fit, with mean relative error under 1%, R2 above 99%, and computation time below 13 seconds, as supported by the evaluation metrics and statistical testing.","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},[94,98,102,106,111,116,121,123,128,131,135],{"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":29,"slug":122},"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]