[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127812-en":3,"doc-seo-127812-105":32,"detail-sidebar-cat-0-en-105":76},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":29,"update_tm":30,"read_time":31},127812,1099523882367,"Hazel","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","Arsenic Mercury Remote sensing Random forest Soil Plant","\u003Cp>A low-density geochemical survey was integrated with multispectral Unmanned Aerial Vehicle remote sensing (UAV-RS) and machine learning to model a statistically robust distribution of Hg and As in soil and vegetation. A novel workflow used limited topsoil and vegetation sampling plus UAV-derived spectral indices to characterize soil-plant responses. Four models (Multiple Linear Regression, Random Forest, Generalized Boosted Models, MARS) were tested; Random Forest best predicted As and Hg with acceptable RPD and RPIQ. Vegetation predictions outperformed topsoil, accuracy was higher for As than Hg, and results exceeded comparable satellite or spectrometry-based studies. The approach offers a powerful alternative to time-consuming, costly classical geochemical surveys.\u003C/p>","\u003Cp>Environmental Pollution 333 (2023) 122066  \u003C/p>\u003Cp>Contents lists available at ScienceDirect  \u003C/p>\u003Cp>Environmental Pollution  \u003C/p>\u003Cp>journal [homepage:](homepage: www.elsevier.com/locate/envpol)[ www.elsevier.com/locate/envpol](homepage: www.elsevier.com/locate/envpol)  \u003C/p>\u003Cp>| Hg and As pollution in the soil-plant system evaluated by combining multispectral UAV-RS, geochemical survey and machine learning☆ |  |  |  |\u003C/p>\u003Cp>| --- | --- | --- | --- |\u003C/p>\u003Cp>| L. Salgado a, b, C.A. L´opez-S´anchez a, A. Colinab, c, D. Baraga˜no b, d, R. Forj´an b, e, J.R. Gallegob, *\u003Cbr>a SMartForest Research Group, Department of Biology of Organisms and Systems Biology, University of Oviedo, 33600 Mieres, Spain\u003Cbr>b Environmental Biogeochemistry & Raw Materials Group and Institute of Natural Resources and Territorial Planning (INDUROT), University of Oviedo, 33600 Mieres, Spain\u003Cbr>c Department of Geography, Campus del Mila´n, University of Oviedo, 33011 Oviedo, Spain\u003Cbr>d Escuela Polit´ecnica de Ingeniería de Minas y Energía, University of Cantabria, 39316 Torrelavega, Spain\u003Cbr>e Plant Production Area, Department of Biology of Organisms and Systems Biology, University of Oviedo, 33600 Mieres, Spain |  |  |  |\u003C/p>\u003Cp>| A R T I C L E I N F O |  | A B S T R A C T |  |\u003C/p>\u003Cp>| Keywords: Arsenic Mercury Remote sensing\u003Cbr>Random forest Soil\u003Cbr>Plant |  | The combination of a low-density geochemical survey, multispectral data obtained with Unmanned Aerial Vehicle-Remote Sensing (UAV-RS), and a machine learning technique was tested in the search for a statistically robust prediction of contaminant distribution in soil and vegetation, for zones with a highly variable pollutant load. To this end, a novel methodology was devised by means of a limited geochemical study of topsoil and vegetation combined with multispectral data obtained by UAV-RS. The methodology was verified in an area affected by Hg and As contamination that typifies abandoned mining-metallurgy sites in recent decades. A broad selection of spectral indices were calculated to evaluate soil-plant system response, and four machine learning techniques (Multiple Linear Regression, Random Forest, Generalized Boosted Models, and Multivariate Adaptive Regression Spline) were tested to obtain robust statistical models. Random Forest (RF) provided the best nonbiased models for As and Hg concentration in soil and vegetation, with R2 and rRMSE (%) ranging from 0.501 to 0.630 and from 180.72 to 46.31, respectively, and with acceptable values for RPD and RPIQ statistics. The prediction and mapping of contaminant content and distribution in the study area were well enough adjusted to the geochemical data and revealed superior accuracy for As than Hg, and for vegetation than topsoil. The results were more precise than those obtained in comparable studies that applied satellite or spectrometry data. In conclusion, the methodology presented emerges as a powerful tool for studies addressing soil and vegetation pollution and an alternative approach to classical geochemical studies, which are time-consuming and expensive. |  |\u003C/p>\u003Cp>\u003Cbr>\u003C/p>\u003Cp>1. Introduction  \u003C/p>\u003Cp>Soil degradation, in particular pollution, affects the supply of ecosystem services such as carbon sequestration, nutrient and water cycles, erosion control, climate regulation, and habitats for plants and animals, as well as opportunities for human development . Industrial and mining areas are often sources of pollutants, causing severe deterioration of environmental compartments, particularly soil . Potentially Toxic Elements (PTEs), such as heavy metals and As, are among the most common soil pollutants, and the evaluation of their abundance, distribution, and mobility is complex (Boente et al., 2022; Forj´an et al., 2018) and may condition risk assessment and the selection of the most suitable  \u003C/p>\u003Cp>remediation technologies. Wherever potentially polluted soils are used for farming and/or agricultural activities, it is crucial to determine PTE concentrations in order to evaluate health risks (Ballabio et al., 2021; Gil-\u003C/p>","cbCaii3GxwqM6a3s","https://ap.wps.com/l/cbCaii3GxwqM6a3s","pdf",12612475,7,1,13,"English","en",105,"# Introduction\n## Motivation: soil and vegetation pollution and PTE risks\n## Monitoring need beyond costly grid sampling\n## Remote sensing and UAV-RS as a higher-resolution alternative","","Arsenic Mercury Remote sensing Random forest Soil Plant | PDF","A low-density geochemical survey was integrated with multispectral Unmanned Aerial Vehicle remote sensing (UAV-RS) and machine learning to model a statistically robust distribution of Hg and As in soil and vegetation. A novel workflow used limited topsoil and vegetation sampling plus UAV-derived spectral indices to characterize soil-plant responses. Four models (Multiple Linear Regression, Random Forest, Generalized Boosted Models, MARS) were tested; Random Forest best predicted As and Hg with acceptable RPD and RPIQ. Vegetation predictions outperformed topsoil, accuracy was higher for As than Hg, and results exceeded comparable satellite or spectrometry-based studies. The approach offers a powerful alternative to time-consuming, costly classical geochemical surveys.",1787314100,33,{"code":4,"msg":33,"data":34},"ok",{"site_id":25,"language":24,"slug":35,"title":28,"keywords":27,"description":29,"schema_data":36,"social_meta":71,"head_meta":73,"extra_data":75,"updated_unix":30},"evaluation-of-hg-and-as-pollution-in-the-soil-plant-system-by-combining-multispectral-uav-rs-geochemical-survey-and-machine-learning",{"@graph":37,"@context":70},[38,55],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":28,"@type":44,"position":54},"https://docshare.wps.com/document/evaluation-of-hg-and-as-pollution-in-the-soil-plant-system-by-combining-multispectral-uav-rs-geochemical-survey-and-machine-learning/127812/",4,{"url":53,"name":28,"@type":56,"author":57,"headline":28,"publisher":59,"fileFormat":62,"inLanguage":24,"description":29,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-09-03","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction","https://schema.org",{"og:url":53,"og:type":72,"og:title":28,"og:site_name":60,"og:description":29},"article",{"robots":74,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":77},[78,82,86,90,95,100,104,107,112,115,119],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":79,"show_sort_weight":80,"slug":81},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":83,"show_sort_weight":84,"slug":85},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":87,"show_sort_weight":88,"slug":89},"Exam",70,"exam",{"id":91,"doc_module":4,"doc_module_name":47,"category_name":92,"show_sort_weight":93,"slug":94},5,"Comic",60,"comic",{"id":96,"doc_module":4,"doc_module_name":47,"category_name":97,"show_sort_weight":98,"slug":99},6,"Technology",50,"technology",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":101,"show_sort_weight":102,"slug":103},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":105,"slug":106},30,"research-report",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},9,"Religion & Spirituality",20,"religion-spirituality",{"id":110,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":110,"slug":114},"World Cup","world-cup",{"id":116,"doc_module":4,"doc_module_name":47,"category_name":117,"show_sort_weight":116,"slug":118},10,"Lifestyle","lifestyle",{"id":120,"doc_module":4,"doc_module_name":47,"category_name":121,"show_sort_weight":91,"slug":122},19,"General","general"]