[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119208-en":3,"doc-seo-119208-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"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},119208,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","EDXRF and Machine Learning for Predicting Soil Fertility Attributes - Accepted Study Abstract","Soil fertility evaluation underpins sustainable agricultural practices but often depends on conventional laboratory procedures that are laborious, time-consuming, and chemical-reagent intensive. Energy-dispersive X-ray fluorescence (EDXRF) provides a rapid, non-destructive alternative, yet accurate fertility prediction requires well-calibrated machine learning models. This study compares four algorithms—MLR, PLS, SVM, and RF—using EDXRF data from two soil datasets to predict pH, SOC, BS, and CEC. Results show PLS as the most accurate approach (PLS > MLR > SVM > RF), especially for BS and CEC, with RPD values above 2.0, supporting quantitative analysis. Predictions for pH and SOC are less accurate, highlighting the benefit of integrating PLS with EDXRF to reduce reliance on traditional soil analysis.","10. 5433/1679-0375.2024.v45.51475  \nEDXRF and Machine Learning for Predicting Soil Fertility Attributes  \nEDXRF e Aprendizado de Máquina para Prever Atributos de Fertilidade do Solo  \nJosé Vinícius Ribeiro1, Felipe Rodrigues dos Santos1, José Vitor de Oliveira Alves1, Mariana Spinardi Fossaluza1, Igor Marques Nogueira1, José Francirlei de Oliveira2, Graziela M.C. Barbosa2, Marcelo Marques Lopes Müller3, Renata Alesandra Borecki3, Cristiano Andre Pott3, Fábio Luiz Melquiades1  \nReceived: 20 September 2024 Received in revised form: 30 October 2024 Accepted: 8 November 2024 Available online: 28 November 2024  \nABSTRACT  \nSoil fertility evaluation is fundamental for sustainable agricultural practices, often relying on conventional laboratory methods. These methods, while accurate, are labor-intensive, time-consuming, and require chemical reagents. Spectroscopic sensors, such as energy-dispersive X-ray fluorescence (EDXRF), offera rapid and non-destructive alternative but require calibration of machine learning models for accurate prediction of fertility attributes. In this context, this study compares the performance of four machine learning algorithms in predicting soil pH, organic carbon (SOC), sum of exchangeable bases (BS), and cation exchange capacity (CEC) using EDXRF data from two soil datasets. These algorithms are: multiple linear regression (MLR), partial least square regression (PLS), support vector machine regression (SVM), and random forest regression (RF) . Results indicate that PLS models outperformed others (the hierarchy of accuracy was PLS > MLR > SVM > RF), particularly for BS and CEC, with RPD (Ratio of Performance to Deviation) values above 2.0, making them suitable for quantitative analysis. In contrast, pH and SOC predictions showed lower accuracy. Overall, we emphasize the benefits of integrating PLS with EDXRF, capable of mitigating the use of traditional soil analysis.  \nkeywords soil fertility attributes, machine learning, PLS, EDXRF  \nRESUMO  \nA avaliação da fertilidade do solo é fundamental para práticas agrícolas sustentáveis, muitas vezes contando com métodos laboratoriais convencionais. Esses métodos, embora precisos, são trabalhosos, demorados erequerem reagentes químicos. Sensores espectroscópicos, como fluorescência de raios X por dispersão deenergia (EDXRF), oferecem uma alternativa rápida e não destrutiva, mas requerem calibração através demodelos de aprendizado de máquina para predição precisa dos atributos de fertilidade. Nesse contexto, este estudo compara o desempenho de quatro algoritmos de aprendizado de máquina na predição do pH, carbono orgânico do solo (SOC), soma de bases trocáveis (BS) e capacidade de troca catiônica (CEC) utilizando dados de EDXRF de dois tipos de solo. Esses algoritmos são: regressão linear múltipla (MLR), regressão linear por mínimos quadrados parciais (PLS), regressão por máquina de vetores de suporte (SVM) e regressãopor floresta aleatória (RF) . Os resultados indicaram que os modelos PLS superaram outros (a hierarquiade precisão foi PLS > MLR > SVM > RF), particularmente para BS e CEC, com valores de RPD (razão entre desempenho e desvio) acima de 2,0, tornando-os adequados para análise quantitativa. Em contraste, aspredições de pH e SOC mostraram menor precisão. No geral, enfatizamos os benefícios da integração de PLS com EDXRF, capaz de mitigar o uso da análise tradicional de solo.  \npalavras-chave atributos de fertilidade, aprendizagem de máquina, PLS, EDXRF  \n1Applied Nuclear Physics Laboratory, UEL, Londrina, PR, Brazil; {j.viniciusribeiro15, frsantos, jose.vitor.oliveira, mariana.spinardi, igor.marques.nogueira, [fmelquiades}@uel.br](fmelquiades}@uel.br)  \n2Soil Department, IDR-Paraná, Londrina, PR, Brazil; {jfoliveira79, [graziela_barbosa}@idr.pr.gov.br](graziela_barbosa}@idr.pr.gov.br)  \n3Soil Science and Plant Nutrition Laboratory, UNICENTRO, Guarapuava, PR, Brazil; [mmuller@unicentro.br](mmuller@unicentro.br), [boreckirenata12@outlook.com.br](boreckirenata","cbCaib8bXRVO0PFI","https://ap.wps.com/l/cbCaib8bXRVO0PFI","pdf",5754690,1,16,"English","en",105,"# Introduction\n## Motivation for rapid soil fertility evaluation\n## Limitations of conventional laboratory methods\n## Rationale for EDXRF and machine learning","[{\"question\":\"Why are conventional laboratory methods used for soil fertility evaluation considered challenging?\",\"answer\":\"They are labor-intensive, time-consuming, and require chemical reagents, with separate protocols and instruments for different attributes.\"},{\"question\":\"What machine learning models are compared for predicting soil fertility attributes?\",\"answer\":\"The study compares multiple linear regression (MLR), partial least squares regression (PLS), support vector machine regression (SVM), and random forest regression (RF).\"},{\"question\":\"Which algorithm performs best overall, and for which attributes?\",\"answer\":\"PLS outperforms the others overall, with the strongest results for sum of exchangeable bases (BS) and cation exchange capacity (CEC), supported by RPD values above 2.0.\"}]","EDXRF and Machine Learning for Predicting Soil Fertility Attributes - Accepted Study Abstract | PDF",1785723104,40,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"edxrf-and-machine-learning-for-predicting-soil-fertility-attributes-accepted-study-abstract","",{"@graph":36,"@context":85},[37,54,68],{"@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/edxrf-and-machine-learning-for-predicting-soil-fertility-attributes-accepted-study-abstract/119208/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why are conventional laboratory methods used for soil fertility evaluation considered challenging?","Question",{"text":75,"@type":76},"They are labor-intensive, time-consuming, and require chemical reagents, with separate protocols and instruments for different attributes.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What machine learning models are compared for predicting soil fertility attributes?",{"text":80,"@type":76},"The study compares multiple linear regression (MLR), partial least squares regression (PLS), support vector machine regression (SVM), and random forest regression (RF).",{"name":82,"@type":73,"acceptedAnswer":83},"Which algorithm performs best overall, and for which attributes?",{"text":84,"@type":76},"PLS outperforms the others overall, with the strongest results for sum of exchangeable bases (BS) and cation exchange capacity (CEC), supported by RPD values above 2.0.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":29,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]