{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T02:28:38Z","timestamp":1773714518230,"version":"3.50.1"},"reference-count":46,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T00:00:00Z","timestamp":1696636800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior: 001, Brasil (CAPES)"},{"name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico (CNPq)"},{"name":"CEAGRE \u2212 Centro de Excel\u00eancia em Agricultura Exponencial"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>In an effort to improve the efficiency of soil classification, traditional methods are being combined with analytical and computational techniques. This integration has strengthened the connection between conventional classification and the application of machine-learning (ML) models to interpret soil spectral reflectance data. Due to the time and computational cost, several studies are limited to testing the classification performance of a few algorithms and do not always explore the best parameters for model optimization. The study aims to assess the efficiency of combining soil spectral reflectance with prevalent ML models for classifying pedogenetic horizons and soil suborders, enhancing traditional classification methods. We collected seven soil monoliths, previously classified according to the Brazilian Soil Classification System (SiBCS) and soil taxonomy. Using the ASD Fieldspec spectroradiometer, we obtained spectral reflectance samples along each monolith (n = 800 per monolith) to classify horizons and n = 5600 for suborder classification. Spectral fingerprints were obtained and explored by Principal Component Analysis (PCA). The spectral data were subdivided into training (70%) and test (30%) sets and submitted to the Logistic Regression (LR), Artificial Neural Network (NN), Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosting (GB) models for the classification of horizons and suborders, considering the model\u2019s adjustment parameters. Accuracy and F-Score were used to verify the performance of the models. There was a significant influence of particle size and soil organic carbon on the spectral fingerprint of the soils. The PCA indicated that topsoil horizons clustered in most of the monoliths analyzed, while most of the subsoil horizons showed data overlap. The NN model showed the highest accuracy in the classification of horizons (97%), while the SVM showed the lowest performance (52% accuracy). The classification of soil suborders presented accuracies between 95% and 98%. Therefore, our study concludes that spectral data combined with ML models can enhance the discrimination and classification of soil horizons and suborders, improving upon traditional methods.<\/jats:p>","DOI":"10.3390\/rs15194859","type":"journal-article","created":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T04:52:36Z","timestamp":1696827156000},"page":"4859","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Rapid Determination of Soil Horizons and Suborders Based on VIS-NIR-SWIR Spectroscopy and Machine Learning Models"],"prefix":"10.3390","volume":"15","author":[{"given":"Karym Mayara","family":"de Oliveira","sequence":"first","affiliation":[{"name":"Graduate Program in Agronomy, Department of Agronomy, State University of Maring\u00e1, Av. Colombo, 5790, Maringa 87020-900, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2343-5045","authenticated-orcid":false,"given":"Renan","family":"Falcioni","sequence":"additional","affiliation":[{"name":"Graduate Program in Agronomy, Department of Agronomy, State University of Maring\u00e1, Av. Colombo, 5790, Maringa 87020-900, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7377-7070","authenticated-orcid":false,"given":"Jo\u00e3o Vitor Ferreira","family":"Gon\u00e7alves","sequence":"additional","affiliation":[{"name":"Graduate Program in Agronomy, Department of Agronomy, State University of Maring\u00e1, Av. Colombo, 5790, Maringa 87020-900, Brazil"}]},{"given":"Caio Almeida","family":"de Oliveira","sequence":"additional","affiliation":[{"name":"Graduate Program in Agronomy, Department of Agronomy, State University of Maring\u00e1, Av. Colombo, 5790, Maringa 87020-900, Brazil"}]},{"given":"Weslei Augusto","family":"Mendon\u00e7a","sequence":"additional","affiliation":[{"name":"Graduate Program in Agronomy, Department of Agronomy, State University of Maring\u00e1, Av. Colombo, 5790, Maringa 87020-900, Brazil"}]},{"given":"Lu\u00eds Guilherme Teixeira","family":"Crusiol","sequence":"additional","affiliation":[{"name":"Embrapa Soja (Empresa Brasileira de Pesquisa Agropecu\u00e1ria), Londrina 86001-970, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7338-2666","authenticated-orcid":false,"given":"Roney Berti","family":"de Oliveira","sequence":"additional","affiliation":[{"name":"Graduate Program in Agronomy, Department of Agronomy, State University of Maring\u00e1, Av. Colombo, 5790, Maringa 87020-900, Brazil"}]},{"given":"Renato Herrig","family":"Furlanetto","sequence":"additional","affiliation":[{"name":"Gulf Coast Research and Education Center, University of Florida, Wimauma, FL 33598, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5006-4887","authenticated-orcid":false,"given":"Amanda Silveira","family":"Reis","sequence":"additional","affiliation":[{"name":"Graduate Program in Agronomy, Department of Agronomy, State University of Maring\u00e1, Av. Colombo, 5790, Maringa 87020-900, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4854-2661","authenticated-orcid":false,"given":"Marcos Rafael","family":"Nanni","sequence":"additional","affiliation":[{"name":"Graduate Program in Agronomy, Department of Agronomy, State University of Maring\u00e1, Av. Colombo, 5790, Maringa 87020-900, Brazil"}]}],"member":"1968","published-online":{"date-parts":[[2023,10,7]]},"reference":[{"key":"ref_1","first-page":"16","article-title":"Management Options in Sandy Soils","volume":"44","author":"Nanni","year":"2018","journal-title":"Bol. Info. (SBCS)"},{"key":"ref_2","unstructured":"ONU\u2014United Nations (2023, August 26). World Population Prospects 2019: Highlights. Depart. of Economic and Social Affairs, Population Division, 2019. Available online: https:\/\/www.un.org\/development\/desa\/pd\/news\/world-population-prospects-2019-0."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/j.geoderma.2014.01.019","article-title":"Soil Classification Using Visible\/near-Infrared Diffuse Reflectance Spectra from Multiple Depths","volume":"223","author":"Vasques","year":"2014","journal-title":"Geoderma"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.rse.2016.03.025","article-title":"Evaluation of the Potential of the Current and Forthcoming Multispectral and Hyperspectral Imagers to Estimate Soil Texture and Organic Carbon","volume":"179","author":"Castaldi","year":"2016","journal-title":"Remote Sens. Environ."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1016\/j.catena.2016.01.001","article-title":"Spatial Prediction of Soil Surface Texture in a Semiarid Region Using Random Forest and Multiple Linear Regressions","volume":"139","author":"Chagas","year":"2016","journal-title":"Catena"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.geoderma.2011.07.015","article-title":"Relationships between particle size distribuition and VNIR reflectance spectra are weaker for soils formed from bedrock compared to transported parente materials","volume":"166","author":"Rawlins","year":"2011","journal-title":"Geoderma"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"4980","DOI":"10.1021\/es504272x","article-title":"In Situ Measurements of Organic Carbon in Soil Profiles Using Vis-NIR Spectroscopy on the Qinghai-Tibet Plateau","volume":"49","author":"Li","year":"2015","journal-title":"Environ. Sci. Technol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1016\/j.geoderma.2009.01.025","article-title":"In Situ Measurements of Soil Colour, Mineral Composition and Clay Content by Vis\u2013NIR Spectroscopy","volume":"150","author":"Cattle","year":"2009","journal-title":"Geoderma"},{"key":"ref_9","first-page":"74720W","article-title":"Spatial distribuition of soil water contente from airborne termal and optical remote sensing data","volume":"7472","author":"Richter","year":"2009","journal-title":"Remote Sens. Agric. Ecosyst. Hydrol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1016\/j.rse.2011.10.018","article-title":"A Method to Estimate Soil Moisture from Airborne Hyperspectral Scanner (AHS) and ASTER Data: Application to SEN2FLEX and SEN3EXP Campaigns","volume":"117","author":"Sobrino","year":"2012","journal-title":"Remote Sens. Environ."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1016\/j.geoderma.2008.11.020","article-title":"Comparing two diferente spectroscopic techniques for the characterization of soil iron oxides: Diffuse versus bi-directional reflectance","volume":"149","author":"Sellitto","year":"2009","journal-title":"Geoderma"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1111\/ejss.12715","article-title":"Rapid Determination of Soil Classes in Soil Profiles Using Vis\u2013NIR Spectroscopy and Multiple Objectives Mixed Support Vector Classification: Soil Classification Using Vis-NIR Spectroscopy","volume":"70","author":"Chen","year":"2019","journal-title":"Eur. J. Soil Sci."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1590\/0103-9016-2013-0365","article-title":"Morphological Interpretation of Reflectance Spectrum (MIRS) Using Libraries Looking towards Soil Classification","volume":"71","author":"Bellinaso","year":"2014","journal-title":"Sci. Agric."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1016\/j.geoderma.2015.05.010","article-title":"Fuzzy Clustering of Vis\u2013NIR Spectra for the Objective Recognition of Soil Morphological Horizons in Soil Profiles","volume":"263","author":"Fajardo","year":"2016","journal-title":"Geoderma"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Jeune, W., Francelino, M.R., Souza, E.D., Fernandes Filho, E.I., and Rocha, G.C. (2018). Multinomial Logistic Regression and Random Forest Classifiers in Digital Mapping of Soil Classes in Western Haiti. Rev. Bras. De Ci\u00eancia Do Solo, 42.","DOI":"10.1590\/18069657rbcs20170133"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"104485","DOI":"10.1016\/j.catena.2020.104485","article-title":"Prediction of Soil Texture Classes through Different Wavelength Regions of Reflectance Spectroscopy at Various Soil Depths","volume":"189","author":"Coblinski","year":"2020","journal-title":"Catena"},{"key":"ref_17","unstructured":"Fonseca, A.D., and Fernandes, J.C. (2004). Remote Detection, Lidel."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1016\/j.earscirev.2016.01.012","article-title":"Aglobal spectral library to characterize the world\u2019s soil","volume":"155","author":"Behrens","year":"2016","journal-title":"Earth Sci. Rev."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.geoderma.2018.03.029","article-title":"Identification of Soil Profile Classes Using Depth-Weighted Visible\u2013near-Infrared Spectral Reflectance","volume":"325","author":"Xie","year":"2018","journal-title":"Geoderma"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"114961","DOI":"10.1016\/j.geoderma.2021.114961","article-title":"Spectral signatures of soil horizons and soil orders\u2013An exploratory study of 270 soil profiles","volume":"389","author":"Zhang","year":"2021","journal-title":"Geoderma"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/j.biosystemseng.2016.04.019","article-title":"How Well Can VNIR Spectroscopy Distinguish Soil Classes?","volume":"152","author":"Zeng","year":"2016","journal-title":"Bios. Eng."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Xu, H., Xu, D., Chen, S., Ma, W., and Shi, Z. (2020). Rapid Determination of Soil Class Based on Visible-near Infrared, Mid-Infrared Spectroscopy and Data Fusion. Remote Sens., 12.","DOI":"10.3390\/rs12091512"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"S38","DOI":"10.1016\/j.rse.2008.09.019","article-title":"Using Imaging Spectroscopy to Study Soil Properties","volume":"113","author":"Chabrillat","year":"2009","journal-title":"Remote Sens. Environ."},{"key":"ref_24","unstructured":"Soil Survey Staff, S.S. (2014). Keys to Soil Taxonomy, United States Department of Agriculture."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1590\/0366-69132016623631992","article-title":"Preparation of low-cost alumina-mullite composites via reactive sintering between a kaolinite clay from Para\u00edba and aluminum hydroxide","volume":"62","author":"Medeiros","year":"2016","journal-title":"Cer\u00e2mica"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"259","DOI":"10.6028\/jres.101.027","article-title":"The Powder Diffraction File: Past, Present, and Future","volume":"101","author":"Smith","year":"1996","journal-title":"J. Res. Natl. Inst. Stand. Technol."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Nanni, M.R., Dematt\u00ea, J.A.M., Rodrigues, M., Santos, G.L.A.A.D., Reis, A.S., Oliveira, K.M.D.O., Cezar, E., Furlanetto, R.H., Crusiol, L.G.T., and Sun, L. (2021). Mapping Particle Size and Soil Organic Matter in Tropical Soil Based on Hyperspectral Imaging and Non-Imaging Sensors. Remote Sens., 13.","DOI":"10.3390\/rs13091782"},{"key":"ref_28","unstructured":"LRCL\u2014Labsphere Reflectance Calibration Laboratory (2009). Spectral Reflectance Target Calibrated From 0.25\u20132.5 nm Reported in 0.050 nm Intervals, LRCL. [1st ed.]."},{"key":"ref_29","unstructured":"Geron, A. (2017). Hands-On Machine Learning with Scikit-Learn TensorFlow: Concepts, Tools and Techniques to Build Intelligent Systems, O\u2019Reilly Media."},{"key":"ref_30","first-page":"2349","article-title":"Orange: Data Mining Toolbox in Python","volume":"14","author":"Demsar","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"R231","DOI":"10.1016\/j.cub.2019.02.034","article-title":"Neural network models and deep learning","volume":"29","author":"Kriegeskorte","year":"2019","journal-title":"Curr. Biol."},{"key":"ref_32","unstructured":"Brownlee, J. (2023, August 03). Machine Learning Mastery with Python: Understand Your Data, Create Accurate Models and Work Projects End-To-End. Machine Learning Mastery: 2016. Available online: https:\/\/machinelearningmastery.com\/machine-learning-with-python\/."},{"key":"ref_33","unstructured":"Besser, M.L., Brumatti, M., and Spisila, A.L. (2023, August 20). Mapa Geol\u00f3gico e de Recursos Minerais do Estado do Paran\u00e1. Programa Geologia, Minera\u00e7\u00e3o e Transforma\u00e7\u00e3o Mineral. Curitiba: SGB-CPRM, 2021, Escala 1:600.000, Available online: https:\/\/rigeo.cprm.gov.br\/jspui\/handle\/doc\/22492."},{"key":"ref_34","unstructured":"Melo, V.F., and Alleoni, L.R.F. (2009). Qu\u00edmica e Mineralogia do Solo: Parte II\u2014Aplica\u00e7\u00f5es, Soc. Bras. de Ci\u00eancia do Solo."},{"key":"ref_35","unstructured":"Lepsch, I.F. (2011). 19 Li\u00e7\u00f5es de Pedologia, Oficina de Textos."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Mart\u00ednez-Mart\u00ednez, V., Gomez-Gil, J., Machado, M.L., and Pinto, F.A.C. (2018). Leaf and Canopy Reflectance Spectrometry Applied to the Estimation of Angular Leaf Spot Disease Severity of Common Bean Crops. PLoS ONE, 13.","DOI":"10.1371\/journal.pone.0196072"},{"key":"ref_37","first-page":"413","article-title":"Spectral Behavior of Some Modal Soil Profiles from S\u00e3o Paulo State, Brazil","volume":"71","author":"Terra","year":"2012","journal-title":"Bragantia Bol. Tec. Do Inst. Agro. Do Estado De S\u00e3o Paulo"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"679","DOI":"10.5935\/1806-6690.20150054","article-title":"Espectroscopia VIS-NIR-SWIR na avalia\u00e7\u00e3o de solos ao longo de uma topossequ\u00eancia em Piracicaba (SP)","volume":"46","author":"Fiorio","year":"2015","journal-title":"Rev. Ci\u00eancia Agron."},{"key":"ref_39","unstructured":"Moreira, M.A. (2007). Fundamentos do Sensoriamento Remoto e Tecnologias de Aplica\u00e7\u00e3o, Vi\u00e7osa; UFV. [3rd ed.]."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.geoderma.2009.12.025","article-title":"Using Data Mining to Model and Interpret Soil Diffuse Reflectance Spectra","volume":"158","author":"Behrens","year":"2010","journal-title":"Geoderma"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"116582","DOI":"10.1016\/j.geoderma.2023.116582","article-title":"Using PXRF and Vis-NIR for Characterizing Diagnostic Horizons of Fine-Textured Podzolic Soils in Subtropical Forests","volume":"437","author":"Huang","year":"2023","journal-title":"Geoderma"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"393","DOI":"10.2136\/sssaj2003.0285","article-title":"Spectral Reflectance Methodology in Comparison to Traditional Soil Analysis","volume":"70","author":"Nanni","year":"2006","journal-title":"Soil Sci. Soc. Am. J."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1016\/j.palaeo.2017.07.007","article-title":"Assessing the Utility of Visible-to-Shortwave Infrared Reflectance Spectroscopy for Analysis of Soil Weathering Intensity and Paleoclimate Reconstruction","volume":"512","author":"Zhao","year":"2018","journal-title":"Palaeogeogr. Palaeoclimatol. Palaeoecol."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1111\/j.1365-2389.2011.01356.x","article-title":"Discrimination of Australian Soil Horizons and Classes from Their Visible-near Infrared Spectra","volume":"62","author":"Webster","year":"2011","journal-title":"Eur. J. Soil Sci."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"113885","DOI":"10.1016\/j.geoderma.2019.113885","article-title":"Parent Material Distribution Mapping from Tropical Soils Data via Machine Learning and Portable X-Ray Fluorescence (PXRF) Spectrometry in Brazil","volume":"354","author":"Mancini","year":"2019","journal-title":"Geoderma"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"e00331","DOI":"10.1016\/j.geodrs.2020.e00331","article-title":"Tropical Soil Order and Suborder Prediction Combining Optical and X-Ray Approaches","volume":"23","author":"Andrade","year":"2020","journal-title":"Geoderma"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/19\/4859\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:02:38Z","timestamp":1760130158000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/19\/4859"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,7]]},"references-count":46,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2023,10]]}},"alternative-id":["rs15194859"],"URL":"https:\/\/doi.org\/10.3390\/rs15194859","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,7]]}}}