Using vis-NIRS and Machine Learning methods to diagnose sugarcane soil chemical properties

Knowing chemical soil properties might be determinant in crop management and total yield production. Traditional soil properties estimation approaches are time-consuming and require complex lab setups, refraining farmers from promptly taking steps towards optimal practices in their crops. Soil pr...

Full description

Bibliographic Details
Main Authors: Delgadillo Durana, Diego A., Vargas García, Cesar A., Varón Ramíreza, Viviana M., Calderón, Francisco C., Montenegroa, Andrea C., Reyes Herreraa, Paula H.
Format: article
Language:Inglés
Published: ArXiv 2025
Subjects:
Online Access:https://arxiv.org/abs/2012.12995
http://hdl.handle.net/20.500.12324/41001
id RepoAGROSAVIA41001
record_format dspace
institution Corporación Colombiana de Investigación Agropecuaria
collection Repositorio AGROSAVIA
language Inglés
topic Preparación del suelo - F07
Saccharum officinarum
Análisis del suelo
Aprendizaje automático
Transitorios
http://aims.fao.org/aos/agrovoc/c_6727
http://aims.fao.org/aos/agrovoc/c_7198
http://aims.fao.org/aos/agrovoc/c_49834
spellingShingle Preparación del suelo - F07
Saccharum officinarum
Análisis del suelo
Aprendizaje automático
Transitorios
http://aims.fao.org/aos/agrovoc/c_6727
http://aims.fao.org/aos/agrovoc/c_7198
http://aims.fao.org/aos/agrovoc/c_49834
Delgadillo Durana, Diego A.
Vargas García, Cesar A.
Varón Ramíreza, Viviana M.
Calderón, Francisco C.
Montenegroa, Andrea C.
Reyes Herreraa, Paula H.
Using vis-NIRS and Machine Learning methods to diagnose sugarcane soil chemical properties
description Knowing chemical soil properties might be determinant in crop management and total yield production. Traditional soil properties estimation approaches are time-consuming and require complex lab setups, refraining farmers from promptly taking steps towards optimal practices in their crops. Soil properties estimation from its spectral signals, vis-NIRS, emerged as a lowcost, non-invasive, and non-destructive alternative. Current approaches use mathematical and statistical techniques, avoiding machine learning frameworks. This proposal uses vis-NIRS in sugarcane soils and machine learning techniques such as three regression and six classification methods. The scope is to assess performance in predicting and inferring categories of common soil properties (pH, soil organic matter OM, Ca, Na, K, and Mg), evaluated by the most common metrics. We use regression to estimate properties and classification to assess soil property status. In both cases, we achieved comparable performance on similar setups reported in the literature for property estimation for pH(R2=0.8, =0.89), OM(R2=0.37, =0.63), Ca(R2=0.54, =0.74), Mg(R2=0.44, =0.66) in the validation set.
format article
author Delgadillo Durana, Diego A.
Vargas García, Cesar A.
Varón Ramíreza, Viviana M.
Calderón, Francisco C.
Montenegroa, Andrea C.
Reyes Herreraa, Paula H.
author_facet Delgadillo Durana, Diego A.
Vargas García, Cesar A.
Varón Ramíreza, Viviana M.
Calderón, Francisco C.
Montenegroa, Andrea C.
Reyes Herreraa, Paula H.
author_sort Delgadillo Durana, Diego A.
title Using vis-NIRS and Machine Learning methods to diagnose sugarcane soil chemical properties
title_short Using vis-NIRS and Machine Learning methods to diagnose sugarcane soil chemical properties
title_full Using vis-NIRS and Machine Learning methods to diagnose sugarcane soil chemical properties
title_fullStr Using vis-NIRS and Machine Learning methods to diagnose sugarcane soil chemical properties
title_full_unstemmed Using vis-NIRS and Machine Learning methods to diagnose sugarcane soil chemical properties
title_sort using vis-nirs and machine learning methods to diagnose sugarcane soil chemical properties
publisher ArXiv
publishDate 2025
url https://arxiv.org/abs/2012.12995
http://hdl.handle.net/20.500.12324/41001
work_keys_str_mv AT delgadilloduranadiegoa usingvisnirsandmachinelearningmethodstodiagnosesugarcanesoilchemicalproperties
AT vargasgarciacesara usingvisnirsandmachinelearningmethodstodiagnosesugarcanesoilchemicalproperties
AT varonramirezavivianam usingvisnirsandmachinelearningmethodstodiagnosesugarcanesoilchemicalproperties
AT calderonfranciscoc usingvisnirsandmachinelearningmethodstodiagnosesugarcanesoilchemicalproperties
AT montenegroaandreac usingvisnirsandmachinelearningmethodstodiagnosesugarcanesoilchemicalproperties
AT reyesherreraapaulah usingvisnirsandmachinelearningmethodstodiagnosesugarcanesoilchemicalproperties
_version_ 1842256038265356288
spelling RepoAGROSAVIA410012025-06-17T03:01:50Z Using vis-NIRS and Machine Learning methods to diagnose sugarcane soil chemical properties Using vis-NIRS and Machine Learning methods to diagnose sugarcane soil chemical properties Delgadillo Durana, Diego A. Vargas García, Cesar A. Varón Ramíreza, Viviana M. Calderón, Francisco C. Montenegroa, Andrea C. Reyes Herreraa, Paula H. Preparación del suelo - F07 Saccharum officinarum Análisis del suelo Aprendizaje automático Transitorios http://aims.fao.org/aos/agrovoc/c_6727 http://aims.fao.org/aos/agrovoc/c_7198 http://aims.fao.org/aos/agrovoc/c_49834 Knowing chemical soil properties might be determinant in crop management and total yield production. Traditional soil properties estimation approaches are time-consuming and require complex lab setups, refraining farmers from promptly taking steps towards optimal practices in their crops. Soil properties estimation from its spectral signals, vis-NIRS, emerged as a lowcost, non-invasive, and non-destructive alternative. Current approaches use mathematical and statistical techniques, avoiding machine learning frameworks. This proposal uses vis-NIRS in sugarcane soils and machine learning techniques such as three regression and six classification methods. The scope is to assess performance in predicting and inferring categories of common soil properties (pH, soil organic matter OM, Ca, Na, K, and Mg), evaluated by the most common metrics. We use regression to estimate properties and classification to assess soil property status. In both cases, we achieved comparable performance on similar setups reported in the literature for property estimation for pH(R2=0.8, =0.89), OM(R2=0.37, =0.63), Ca(R2=0.54, =0.74), Mg(R2=0.44, =0.66) in the validation set. Caña panelera-Saccharum officinarum - Saccharum officinarum L. 2025-06-16T20:56:34Z 2025-06-16T20:56:34Z 2021-05 2021 article Artículo científico http://purl.org/coar/resource_type/c_2df8fbb1 info:eu-repo/semantics/article https://purl.org/redcol/resource_type/ART http://purl.org/coar/version/c_970fb48d4fbd8a85 https://arxiv.org/abs/2012.12995 http://hdl.handle.net/20.500.12324/41001 reponame:Biblioteca Digital Agropecuaria de Colombia instname:Corporación colombiana de investigación agropecuaria AGROSAVIA eng ArXiv 1 1 1 13 E. K. B¨unemann, G. Bongiorno, Z. Bai, R. E. Creamer, G. De Deyn, R. de Goede, L. Fleskens, V. Geissen, T. W. Kuyper, P. M¨ader, et al., Soil quality–a critical review, Soil Biology and Biochemistry 120 (2018) 105–125. M. R. Nanni, J. A. M. Demattˆe, Spectral Reflectance Methodology in Comparison to Traditional Soil Analysis, Soil Science Society of America Journal 70 (2006) 393–407. URL: http://doi.wiley.com/10.2136/sssaj2003. 0285. doi:10.2136/sssaj2003.0285 J. C. Ca˜nasveras, V. Barr´on, M. C. del Campillo, R. A. Viscarra Rossel, Espectroscop´ıa de reflectancia: Una herramienta para predecir las propiedades del suelo relacionadas con la clorosis f´errica, Spanish Journal of Agricultural Research 10 (2012) 1133–1142. doi:10.5424/sjar/2012104-681-11 R. Viscarra Rossel, R. Rizzo, J. Demattˆe, T. Behrens, Spatial modeling of a soil fertility index using visible–nearinfrared spectra and terrain attributes, Soil Science Society of America Journal 74 (2010) 1293–1300. B. Stenberg, R. A. Viscarra Rossel, A. M. Mouazen, J. Wetterlind, Chapter five - visible and near infrared spectroscopy in soil science, in: D. L. Sparks (Ed.), Advances in Agronomy, volume 107, Academic Press, 2010, pp. 163 – 215. URL: http://www.sciencedirect.com/science/article/pii/S0065211310070057. doi:https://doi.org/10.1016/S0065-2113(10)07005-7. K. Kawamura, Y. Tsujimoto, M. Rabenarivo, H. Asai, A. Andriamananjara, T. Rakotoson, Vis-nir spectroscopy and pls regression with waveband selection for estimating the total c and n of paddy soils in madagascar, Remote Sensing 9 (2017) 1081. B. Stenberg, R. A. V. Rossel, A. M. Mouazen, J. Wetterlind, Visible and near infrared spectroscopy in soil science, Advances in agronomy 107 (2010) 163–215. A. D. Vibhute, K. V. Kale, S. C. Mehrotra, R. K. Dhumal, A. D. Nagne, Determination of soil physicochemical attributes in farming sites through visible, near-infrared di use reflectance spectroscopy and plsr modeling, Ecological Processes 7 (2018) 1–12. M. Yang, D. Xu, S. Chen, H. Li, Z. Shi, Evaluation of machine learning approaches to predict soil organic matter and pH using vis-NIR spectra, Sensors (Switzerland) 19 (2019). doi:10.3390/s19020263. J. Padarian, B. Minasny, A. B. McBratney, Machine learning and soil sciences: A review aided by machine learning tools, Soil 6 (2020) 35–52. J. Ding, A. Yang, J. Wang, V. Sagan, D. Yu, Machine-learning-based quantitative estimation of soil organic carbon content by vis/nir spectroscopy, PeerJ 6 (2018) e5714. M. Yang, D. Xu, S. Chen, H. Li, Z. Shi, Evaluation of machine learning approaches to predict soil organic matter and ph using vis-nir spectra, Sensors 19 (2019) 263. A. Morellos, X.-E. Pantazi, D. Moshou, T. Alexandridis, R. Whetton, G. Tziotzios, J. Wiebensohn, R. Bill, A. M. Mouazen, Machine learning based prediction of soil total nitrogen, organic carbon and moisture content by using vis-nir spectroscopy, Biosystems Engineering 152 (2016) 104–116. S. Nawar, A. Mouazen, On-line vis-nir spectroscopy prediction of soil organic carbon using machine learning, Soil and Tillage Research 190 (2019) 120–127. IGAC, Suelos y tierras de Colombia, 3 ed., Instituto Geogr´afico Agust´ın Codazzi, 2015. J. H. Camacho-Tamayo, Y. Rubiano S, M. d. P. Hurtado S, Near-infrared (nir) di use reflectance spectroscopy for the prediction of carbon and nitrogen in an oxisol, Agronomia colombiana 32 (2014) 86–94. J. H. Camacho-Tamayo, N. M. Forero-Cabrera, L. Ram´ırez-L´opez, Y. Rubiano, Near-infrared spectroscopic assessment of soil texture in an oxisol of the eastern plains of colombia, Colombia Forestal 20 (2017) 5–18. D. Chicco, G. Jurman, The advantages of the Matthews correlation coe cient (MCC) over F1 score and accuracy in binary classification evaluation, BMC Genomics 21 (2020) 6. URL: https://doi.org/10.1186/ s12864-019-6413-7. doi:10.1186/s12864-019-6413-7 D. Cozzolino, A. Mor´on, The potential of near-infrared reflectance spectroscopy to analyse soil chemical and physical characteristics, Journal of Agricultural Science 140 (2003) 65–71. doi:10.1017/S0021859602002836 R. Zornoza, C. Guerrero, J. Mataix-Solera, K. Scow, V. Arcenegui, J. Mataix-Beneyto, Near infrared spectroscopy for determination of various physical, chemical and biochemical properties in mediterranean soils, Soil Biology and Biochemistry 40 (2008) 1923–1930 S. B. Aguiar Herrera, Bases t´ecnicas para el establecimiento y manejo del cultivo de ca˜na en el departamento de Casanare, 1 ed., Corpoica, 2001 F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, E. Duchesnay, Scikit-learn: Machine learning in Python, Journal of Machine Learning Research 12 (2011) 2825–2830 P. Juszczak, D. M. J. Tax, R. P. W. Duin, Feature scaling in support vector data description, 2002. C.-C. Chang, C.-J. Lin, LIBSVM: A library for support vector machines, ACM Transactions on Intelligent Systems and Technology 2 (2011) 27:1–27:27. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm S. J. Russell, P. Norvig, E. Al, Artificial intelligence : a modern approach, Pearson, Cop, 2010 A. O. Awiti, M. G.Walsh, K. D. Shepherd, J. Kinyamario, Soil condition classification using infrared spectroscopy: A proposition for assessment of soil condition along a tropical forest-cropland chronosequence, Geoderma 143 (2008) 73–84. R. V. Morris, H. V. Lauer, C. A. Lawson, E. K. Gibson, G. A. Nace, C. Stewart, Spectral and other physicochemical properties of submicron powders of hematite (alpha -Fe2O3), maghemite (gamma - Fe2O3), magnetite (Fe3O4), goethite (alpha - FeOOH) and lepidocrocite (gamma -FeOOH)., Journal of Geophysical Research 90 (1985) 3126– 3144. doi:10.1029/JB090iB04p03126 E. Ben-Dor, s. J. R. Iron, G. F. Epema, PSoil reflectance, in: Remote Sensing for the Earth Sciences, volume 3 of Manual of Remote Sensing, Wiley, New York, 1999, pp. 111––188. R. Reda, T. Sa aj, B. Ilham, O. Saidi, K. Issam, L. Brahim, E. M. El Hadrami, A comparative study between a new method and other machine learning algorithms for soil organic carbon and total nitrogen prediction using near infrared spectroscopy, Chemometrics and Intelligent Laboratory Systems 195 (2019). doi:10.1016/j.chemolab. 2019.103873 R. V. Rossel, T. Behrens, Using data mining to model and interpret soil di use reflectance spectra, Geoderma 158 (2010) 46–54. R. N. Clark, T. V. King, M. Klejwa, G. A. Swayze, N. Vergo, High spectral resolution reflectance spectroscopy of minerals, Journal of Geophysical Research 95 (1990) 12653–12680. URL: https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/JB095iB08p12653https: //agupubs.onlinelibrary.wiley.com/doi/abs/10.1029/JB095iB08p12653https://agupubs. onlinelibrary.wiley.com/doi/10.1029/JB095iB08p12653. doi:10.1029/jb095ib08p12653. Q. Fang, H. Hong, L. Zhao, S. Kukolich, K. Yin, C. Wang, Visible and near-infrared reflectance spectroscopy for investigating soil mineralogy: A review, Journal of spectroscopy (2018). URL: http://hdl.handle.net/ 10150/628358. doi:10.1155/2018/3168974 U. Schwertmann, Solubility and dissolution of iron oxides, Plant and Soil 130 (1991) 1–25. M. Ali, W. Mindari, E ect of humic acid on soil chemical and physical characteristics of embankment, MATEC Web of Conferences (2015). doi:10.1051/conf/2016 H. R. Sindelar, M. T. Brown, T. H. Boyer, E ects of natural organic matter on calcium and phosphorus coprecipitation, Chemosphere 138 (2015) 218–224. doi:10.1016/j.chemosphere.2015.05.008 F. L. Wang, P. M. Huang, E ects of organic matter on the rate of potassium adsorption by soils, Canadian Journal of Soil science (2001). URL: www.nrcresearchpress.com. M. Yan, Y. Lu, Y. Gao, M. F. Benedetti, G. V. Korshin, In-Situ Investigation of Interactions between Magnesium Ion and Natural Organic Matter, Environmental Science and Technology 49 (2015) 8323–8329. doi:10.1021/ acs.est.5b00003 S. Droge, K. U. Goss, E ect of sodium and calcium cations on the ion-exchange a nity of organic cations for soil organic matter, Environmental Science and Technology 46 (2012) 5894–5901. doi:10.1021/es204449r Atribución-NoComercial-CompartirIgual 4.0 Internacional http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf application/pdf C.I Tibaitatá Colombia ArXiv Revista ICA; Vol. 12, Núm. 1 (1977): Revista ICA (Marzo);p. 55 -66.